The NAB Show in Las Vegas was long the epicentre of breakthroughs in broadcast, media, and production technology. Once sprawling across the entire Las Vegas Convention Center and hosting over 100,000+ attendees, the show now presents a more focused and intense experience; this year, the Conference is expecting just over 60,000 visitors, but with attendees from 160 countries and filling only part of the South Hall. But while the scale may have shifted, the ambition certainly hasnt.Known for historic firsts like the debut of HDTV and the original unveiling of the RED Digital Cinema Camera, NAB remains the place Where Content Comes to Life. In 2025, the spotlight turns squarely toward innovation in AI, automation, and next-generation production tools. From real-time visual effects to AI-driven editorial workflows, the show reflects an industry rapidly evolving under the weight and potential of machine learning and intelligent automation.Here are some of the most interesting new technologies and tools that are reshaping post-production.Blackmagic DesignIn Las Vegas, Blackmagic Design has unveiled DaVinci Resolve 20, a significant update packed with over 100 new features, many of which are powered by AI. While the NAB show may be smaller this year, Blackmagics booth is showcasing some key transformative tools for post, -and AI is clearly taking the lead. This release brings a host of intelligent features designed to streamline workflows and enhance creative control.DaVinci Resolve 20Among the headline tools is AI IntelliScript, which can automatically generate timelines from a text script, effectively turning written dialogue into structured edits. AI Animated Subtitles adds a dynamic layer to captioning by animating words in sync with spoken audio, while AI Multicam SmartSwitch uses speaker detection to automate camera switching in multicam edits. Audio post also gets an upgrade with the AI Audio Assistant, which analyzes entire timelines and builds a professional mix without manual intervention.All of these features represent a deepening integration of AI into the DaVinci editing and finishing process as a practical assistant across real-world workflows. Beyond AI, DaVinci Resolve 20 introduces a new keyframe editor, voiceover recording palettes, expanded compositing capabilities in Fusion, and enhanced grading tools like Chroma Warp.DaVinci Resolve 20 is available now as a public beta from the Blackmagic Design website. We expect a lot of buzz around the booth this week, especially from those watching how AI is integrating into the editorial and finishing landscape.With the Blackmagic URSA Cine Immersive, the worlds first cinema camera designed to shoot for Apple Immersive Video and Apple Vision Pro (AVP) DaVinci Resolve Studio 20 also introduces powerful new features for Apple Immersive Video. Filmmakers can now edit, colour grade, mix Spatial Audio, and deliver Apple Immersive Video captured using the new Blackmagic URSA Cine Immersive camera.AdobeAt NAB 2025, Adobe has just unveiled powerful new updates to Premiere Pro and After Effects, with a strong emphasis on AI-driven features that enhance creative workflows and make editing smarter and faster.In Premiere Pro 25.2, Adobe introduces Firefly-powered Generative Extend, a tool that allows editors to seamlessly add extra 4K frames to a clip, which is perfect for fixing cuts that start too early or end too soon. Generative Extend works in the background as you continue editing, and it is powered by Adobes Firefly AI. It also importantly includes Content Credentials, providing transparency about when and where AI was used.https://www.fxguide.com/wp-content/uploads/2025/04/Generative-Extend-Sizzle-VideoS.mp4Also debuting is Media Intelligence, an AI-based feature that simplifies finding the right shot. By automatically recognizing content, including objects, environments, camera angles, and dialogue. Editors can now search hours of footage using natural language queries. Editors can search for anything from close-ups of hands working in a kitchen to mentions of herbs and Premiere will surface relevant clips, transcripts, and metadata.As this AI analysis happens locally, theres no need for an internet connection, and Adobe emphasizes that no user content is ever used to train its models. Other workflow upgrades in Premiere include dynamic waveforms, improved colour management with drag-and-drop ease, coloured sequence labels, and expanded GPU accelerationsolid quality-of-life features requested by working professionals.In After Effects version 25.2 there is a new high-performance playback engine for faster previews, fresh 3D motion design tools, and support for HDR monitoring, pushing the boundaries of motion graphics and VFX workflows. Together, these updates mark a push from Adobe toward AI-assisted editing that doesnt replace the artist, but rather assists them, automating the repetitive, surfacing whats useful, and letting creators focus more on storytelling according to Adobe.Foundry: Nuke Stage Virtual Production ProductFoundry has announced Nuke Stage, a new standalone application purpose-built for virtual production and in-camera VFX (ICVFX). Designed to streamline workflows from pre-production through final pixels, Nuke Stage gives VFX artists end-to-end control over imagery and colour in a unified pipeline. The tool enables real-time playback of photoreal environments on LED walls, live compositing, and layout, using industry standards like OpenUSD, OpenEXR, and OpenColorIO.Nuke StageNuke Stage has afamiliar node-based interface consistent with Nuke, the new tool is built to deliver efficiency and flexibility for productions of all sizes. Developed in collaboration with the VFX and virtual production community, Nuke Stage fills a gap in on-set workflows by integrating VFX compositing tools into real-time production. Our hope is that Nuke Stage brings the expertise of VFX artists even closer to creative decision-making, said Christy Anzelmo, Chief Product Officer at Foundry. Industry professional Dan Hall of 80six called it a handshake between VFX and virtual production, while Framestores Connor Ling noted that familiarity with Nuke will build confidence in whats seen on the LED wall. Garden Studios Sam Kemp praised the ability to tweak 2D assets live, calling it something thats been missing from virtual production for a long time.Key features of Nuke Stage include real-time photoreal playback, live compositing, comprehensive colour support, and hardware-agnostic operation; with no specialized media servers,Nuke Stage runs on standard hardware. The tool supports 2D, 2.5D, and 3D content playback and allows teams to work in a linear, HDR-ready colour space using a consistent toolset from prep to post. As part of the Nuke ecosystem, Nuke Stage is designed to offer a seamless, efficient pipeline from the first frame captured on set through to the final delivery.NVIDIANVIDIA is showcasing Real-Time AI and Intelligent Media Workflows at NAB. NVIDIA is focused on the Blackwell platform, which serves as the foundation of NVIDIA Media2. This is a collection of NVIDIA technologies, including NVIDIA NIM microservices and NVIDIA AI Blueprints for live video analysis, accelerated computing platforms and generative AI software.NVIDIA Holoscan is also being shown for Media, as an advanced real-time AI platform designed for live media workflows and applications and their NVIDIA AI Blueprint for video search and summarization. These tools make it easy to build and customize video analytics AI agents.Cinnafilm Upconversion toolAdditionally, Cinnafilm and NVIDIA have partnered on a new AI-powered HD-to-UHD upconversion tool, which will be commercially available later this year inside Cinnafilms flagship conversion platform, PixelStrings and it is launching at the 2025 NAB Show this week. Combining Cinnafilms GPU-accelerated engine with a custom version of NVIDIA RTX AI Image Processing, the system delivers ultra-high-definition results in a single pass with what Cinnafilm says is 2530% greater detail than its current tools. Designed for speed, scalability, and top-tier visual quality, the new solution sets a fresh benchmark for media upscaling.DeepDubDeepdub has unveiled Deepdub Live, a real-time multilingual dubbing solution designed for live sports, esports, and breaking news coverage. DeepDub is audio only, but a significant step forward for broadcasters. Powered by the companys proprietary Emotive Text-to-Speech (eTTS) engine, Deepdub Live delivers expressive, emotionally nuanced voiceovers that the company claims are just like the native-language production. The eTTS system dynamically adjusts vocal tone, intensity, and energy to match the emotional cadence of live events, whether its the urgency of breaking news or the excitement of a sports final. Broadcasters can choose to use AI-cloned voices of original speakers or select from Deepdubs licensed voice bank, all cleared for broadcast and streaming. Built for enterprise deployment, the API-driven platform supports more than 100 languages and dialects, with ultra-low latency and frame-accurate synchronisation to ensure seamless, high-quality multilingual experiences in real-time.

At the recent Hollywood Professional Association (HPA) Tech Retreat, Michael Cioni delivered a bold and provocative talk about the existential challenges facing Hollywood in the age of the creator economy. Framing his insights through the lens of cinematography and camera innovation, he made the case that traditional Hollywood can no longer rely on legacy systems, prestige, or scale to maintain its dominance. Platforms like YouTube and TikTok, paired with cheap, accessible production tools, have leveled the playing field.Now, creators anywherewith little more than a smartphone and an ideaare commanding global audiences that rival major studios. But while that talk focused on the front end of productioncameras, workflows, and onset innovationtheres another half of the story thats just as critical to the industrys future: post-production and VFX.In this follow-up conversation, Cioni turns his attention to what happens after the camera stops rolling. With his deep roots in post, from founding the pioneering post house LightIron, to leading innovation at Panavision, Frame.io, and Adobe, he brings a unique perspective to how technology is reshaping the back end of filmmaking. From cloud workflows and real-time collaboration to AI-powered editing and metadata-driven pipelines, Cioni argues that Hollywoods survival depends not just on changes to capturebut on radically rethinking how we finish and deliver content.In this fxpodcast, Michael brings both clarity and urgency to the conversation, drawing on decades of experience at the intersection of creativity and technology. In this conversation he discuss why post-production may be the key frontier where Hollywood either adapts or fades.He also discusses one new key solution for distributed workflow : Strada. This new technology provides an alturnative to Cloud storage in a way that is both fast and provides real flexibility.Strada Agents will be on display at the 2025 NAB Show in Las Vegas where the Strada team will demonstrate this technology breakthrough at Booth SL4807 in the South Hall.

When John Knoll first heard about Star Wars: Skeleton Crew in the fall of 2021, it was through a familiar channel: ILMs Rob Bredow, asking if hed be interested in heading up visual effects on one of Lucasfilms new streaming projects. For Knoll, the prospect was immediately appealing, not just because of the storys tone or its place within what ILM affectionately calls the Favre-verse (the Jon FavreauDave Filoni era of Star Wars TV)but also because production was based in Manhattan Beach Studios, a welcome proximity bonus given how many countries projects could now shoot in.What sealed the deal, though, were the scripts. John Knoll was taken with their humour and spirit of the project (with early Speliberg overtones). His early meetings with director Jon Watts made it clear this was a collaboration built on trust and shared creative instinct.And that trust was crucial. Knoll prefers to show VFX work earlyearly enough to course-correct meaningfully, but not so early that a client might panic at a rough version. With Watts, he found a Director open to that kind of iterative process. That kind of openness meant fewer surprises laterand, more importantly, visuals that aligned closely with the storys intent.Noe the use of practicals (but with a viewing gauze on the truckFinal shotThe puzzle of working with kids (and their doubles)One of the unique challenges of Skeleton Crew was the cast itself: the show centers on a group of kids navigating a Star Wars-scale adventure. That meant tight work schedules, limited hours on set, and a heavy reliance on planning. Knoll and the team strategically structured shoot days, starting with adult doubles for wide shots and saving close-ups with the child actors for their limited hours.The use of doubles, who were carefully matched in proportions and costuming, proved more effective than expected. In some cases, edits progressed far into post before anyone even realized a particular shot featured a double, not the child actor. There are more shots than youd guess, Knoll noted. They were pretty darn good doubles.Blending miniatures and digital: the art behind the illusionSkeleton Crew continues ILMs modern embrace of miniature photography, something thats become a staple on Star Wars shows like The Mandalorian and Ahsoka. But for Knoll, this isnt about nostalgia or marketing opticsits about results.He recalls how The Mandalorian kicked off the return to miniatures with a bit of uncertainty. An early Razor Crest flyby received mixed feedback from Favreausomething about it just wasnt selling. What began as a suggestion to build a reference model for lighting escalated into a full miniature shoot, complete with motion control. The resulting footage wasnt just usableit was inspiring. ILM ended up reworking their CG Razor Crest to match the practical version, and the result was indistinguishable. That pattern repeated on Ahsoka, and again with Skeleton Crew.For Knoll, the process has become a proven workflow: shoot a beautiful miniature, use it to inform the CG model, and evolve the digital version until its virtually indistinguishable from the real thing. Whether its subtle scuff marks, directional scratches on metal panels, or the play of stylized bounce cards sculpting highlights in space, the final CG shots benefit immeasurably from miniature-informed lighting and texture references.A puppet with personality: SM-33When it came to SM-33, the shows quirky droid character, Knoll leaned on a tried-and-true method: full-body puppetry with puppeteers removed in posta technique that traces back to his work on The Phantom Menace. Drawing inspiration from Japanese Bunraku puppetry, the approach allowed for expressive, in-camera performances.https://www.fxguide.com/wp-content/uploads/2025/04/Skeleton-Crew-Creatures-Droids.mp4Legacy Effects built a beautifully detailed puppet, and the performance imbued it with a distinct, slightly wobbly charm. For the shots where the puppet couldnt do what was neededrunning, fighting, complex movementCG took over. But by carefully matching the puppets physical quirks in animation, the handoff between real and digital remained seamless. In many shots, viewers wouldnt know the switch had occurred at all. Knoll recalls a shot of SM-33 where he starts as a puppet, turns and walks away using a seamless handoff from puppet to fully CG animation part way through the shot.Invisible VFX: from faceplates to falling childrenNot all of the effects in Skeleton Crew are big establishing shots or complex visual effects space sequences. Some of the most difficult were the ones viewers arent meant to notice.Take KBs visor, for instance: a piece of costume design that needed to shift positions on her face. The mechanical motion couldnt be practically achieved, so ILM animated it digitally. But that motion had secondary consequenceslike changing her hairstyle as the visor moved, requiring CG hair replacement. Then there were the safety concerns: the visors mesh obscured vision in dark scenes, so it was sometimes omitted entirely and replaced digitally. It was clearly unsafe to have child actors walking around complex dark sets with restricted vision.Similarly, scenes involving stunts or hazardous terrain often relied on digital doubles. For example, when the kids are ejected from garbage tubes onto a beach, that fall was entirely CGno safe or practical way to shoot it live, Knoll commented. In many cases, ILM used a combination of adult stunt doubles and CG, depending on the shot and risk level.The volume and the value of real sunlightSkeletal Crew also made extensive use of ILMs StageCraft volume. But Knoll is quick to point out: its not a blanket solution. For him, its a tool best used when it makes creative and logistical sense. The real benefit comes in longer scenes, where the ability to amortize the upfront content build over many pages of dialogue outweighs the cost of per-shot VFX.And yet, despite the advances in LED volumes, Knoll remains a staunch advocate for real sunlight when it comes to outdoor scenes. Bad daytime exteriors on a soundstage, he says, are the bane of my existence. He comes armed with a library of examplesgood and badto help DPs and production designers understand the visual trade-offs. With the right planning, he says, everyone can align early to avoid the common pitfalls. Controlled chaos: simulated destruction and stylized spaceOf course, Skeleton Crew still has its share of large-scale spectacle. From tug-of-war sequences between ships and garbage munchers, to debris-littered space battles, Knolls team tackled destruction scenes by starting with animation to define story intent, and then layering simulations to support and enhance the motion.And in space, visual stylization remains key. The lighting philosophy draws from the original trilogya willingness to place mysterious bounce cards in the void for the sake of sculpted forms and cinematic readability. Youre not trying to replicate NASA footage, Knoll explains. Youre trying to make something beautiful and clear. A playbook for better VFXKnoll keeps a mental list of top production pitfalls, and he runs through them with every new team. From improperly lit interiors with mismatched window comps, to awkward soundstage exteriors, to vehicle shots with static lightinghes seen the same mistakes repeat across the industry.Knoll has compiled a personal playbook of common VFX pitfalls, which he shares with production teams early on and he shared with fxguide. His Top 5Pitfalls for VFX includes:Daytime exteriors on a soundstage.Daytime interiors with blown-out window blue screens.Static lighting on moving vehicles.Poorly designed shots with no visual solution.Imbalanced composites that simply need regrading.Most of what goes wrong on VFX shows, he says, falls into one of those buckets.But his goal isnt just to avoid problems; its to empower productions to get it right from the start, and that ethos runs through every frame of Skeleton Crew. Its a show where high-end visual effects serve a heartfelt, youthful adventureand where the seamless blend of puppetry, miniatures, CG, and practical lighting creates a galaxy that feels every bit as lived-in and magical as the Star Wars of our childhoods that inspired so many of us to enter Visual Effects.

The successful Netflix miniseries, Senna, explores the extraordinary life of Brazilian racing legend Ayrton Senna da Silva, who captured the Formula One World Drivers Championship three times. Starring Gabriel Leone, Kaya Scodelario, Matt Mella, Patrick Kennedy, Arnaud Viard, Steven Mackintosh, Camila Mrdila, and Marco Ricca, the show brings Sennas captivating story to life.Visual effects for the series were crafted by Scanline VFX, with teams working collaboratively across their facilities in Vancouver, Seoul, Montreal, and Los Angeles. Production VFX Supervisors Craig Wentworth and Marcelo Siqueira oversaw the ambitious project, delivering the powerful visuals that vividly recreate Sennas iconic racing moments.Amid a challenging time for the visual effects industry and significant shifts within Scanline itself, the quality of work on Senna highlights the studios dedication and continued excellence. This miniseries showcases the kind of technical artistry and storytelling prowess that Scanline has been known for since its founding in 1989 by Stephan Trojansky in Munich.For decades, Scanline VFX has led the industry, particularly in complex fluid simulations, notably through the groundbreaking development of their proprietary software, Flowline. Their expertise in water simulations propelled them onto the global stage, as the go-to vendor for large-scale water sims, culminating in a Scientific and Technical Achievement Academy Award for Flowline in 2008.Today, with Formula One enjoying unprecedented popularity, driven by the success of Netflixs Drive to Survive and the excitement surrounding the start of the 2025 season from Melbourne to Shanghai, the release of Senna the series has proven popular, and it serves as a compelling tribute to Ayrton Sennas legacy and a testament to the artistry and innovation of the shows visual effects artists.

Rob Legato, the legendary VFX supervisor behind groundbreaking films like Titanic, Hugo, and The Jungle Book, has officially joined Stability AI as Chief Pipeline Architect. Known for his pioneering work in virtual cinematography and immersive storytelling, Legatos move marks a significant step in the evolving relationship between artificial intelligence and visual effects. At Stability AI, as he explains in this weeks fxpodcast, he reunites with filmmaker and friend James Cameron, a key board member of the company, to explore new frontiers in generative AI-driven film production pipelines.Throughout his career, Legato has consistently pushed the boundaries of filmmaking technology, from developing the virtual cinematography pipeline for Avatar to revolutionizing digital production workflows in The Lion King and Hugo. As AI-powered tools like Stability AIs Stable Diffusion gain traction in creative industries, Legato sees a unique opportunity to leverage these advancements to enhance storytelling rather than replace traditional artistry. In an exclusive conversation with fxguide, he shares his perspective on AIs role in filmmaking, its ethical implications, and how it can empower artists to achieve unprecedented creative storytelling.With Stability AIs leadership teamincluding CEO Prem Akkaraju, former Weta Digital head; CTO Hanno Basse, ex-20th Century Fox CTO; and executive chair Sean Parker (Napster) Legato is joining a company at the forefront of AI innovation. As the VFX industry grapples with rapid technological shifts, his expertise could help shape a new, AI-augmented workflow that balances automation with the artistry that defines a new age in VFX and cinema in general. In this interview, Legato discusses his ambitions at Stability AI, his take on the future of VFX, and why he believes the fusion of AI and filmmaking is an evolutionnot a replacementof creative storytelling.Note: John Montgomery is on holidays this week and he will be back on the show next week

If you check social media right now, youll find a lot of discussion surrounding Apple Intelligence. At the same time, Apple has launched a new lineup of iPads, MacBook Air models, and the latest Mac Studios. While many YouTubers and influencers have expressed disappointment with Apples approach to AI, particularly the implementation of their Apple Intelligence strategy, the company has simultaneously released one of the most powerful machines ever: the M3 Ultra Mac Studio, which is brilliant for AI.Weve been using the new M3 Ultra since its release, and for artists and TDs working doing AI in M&E , this machine is exceptionally attractive. Our M3 Ultra is far from inexpensive, but with 512GB of RAM and 12TB of storage, it is, without question, a beast when it comes to localized AI, machine learning, LLM applications, and image processing. Weve specifically been putting it through its paces with Topaz Video AI 6, which runs natively on the M3 Ultra Mac Studio.360 to 4K in Topaz Vdeio AI 6. (click to enlarge)The question that naturally follows is: why do you need this much power on a desktop? Topaz AI 6 provides a perfect answer. Unlike many AI applications, this software is not cloud-basedthough Topaz does have an early cloud prototype called the Starlight Project. For some people in production, cloud computing is a viable option, but there are compelling reasons to keep processing local. Three primary factors make local AI processing beneficial: security, speed of upload, and speed of processing. While cloud computing is an alternative for those without high-performance machines, our intense work over the past week left no doubt that in a professional environment, the M3 Ultra is an outstanding option.Security. Security concerns around AI in VFX are significant, as many clients fear that AI or machine learning tools could absorb proprietary data into cloud-based models, thereby compromising intellectual property. While this concern is often unfoundedmost AI models, including ChatGPT, do not learn from user inputs once they are built, but the client perception remains. As some great colleagues of mine recently posted, AI systems like ChatGPT are pre-trained, meaning they dont continuously learn from user interactions; instead, they operate within the confines of their initial training data. Nonetheless, some clients are adamant about avoiding AI tools altogether. With local processing, security is far easier to guarantee, giving professionals a level of control that cloud solutions struggle to match.Speed of upload. While many users have access to fast internet, uploading large filesparticularly in a remote workflowcomes at a cost. This challenge is especially pronounced for VFX professionals working with massive DPX or EXR files. In our situation, where we are focused on upscaling footage, the issue was not a case of uploading a few live action plates elements and processing them over hours, but rather dealing with vast amounts of material being repurposed. This significantly exasperates the upload problem, reinforcing the advantages of local processing.Speed of processing. This is where the M3 Ultra truly excels. With its killer M3 Ultra chip, fast RAM and high-speed storage, it processes massive datasets at an incredible rate. Rather than relying solely on benchmarks, we focus on real-world scenarios. We worked on a range of production assets for this story, some decades old and stored only in 360p resolution, others more recent, at 2K res. Our primary test involved upscaling to 4K, as it provided a meaningful balance between quality and computational demands (Topaz can scale to 8K). One specific scenario involved integrating old green screen footage with newly shot 4K material. Additionally, we experimented with extreme upscaling, pushing very low-resolution footage (360P) to 4K, to evaluate failure points and we also compared the fully released Topaz AI 6 with Topazs prototype cloud-based Project Starlight AI.Rather than discuss specifciation and the data rates of the M3 Ultra Mac Studio we explored what we can do with it, after all it was Apple who sold the original ipod as 1000 songs in your pocket, and not iPod with 5GB Hard drive.Stand alone upresing:Before diving into the green screen examples below, we first examined some traditional upscaling work performed using Topaz AI 6. In each case, the upscaling was applied to a completed shot, with clear before-and-after comparisons to showcase the improvements. Regardless of the hardware running Topaz AI 6, the results are impressive, demonstrating just how far machine learning has advanced as a powerful post-production tool.The combination of Topaz AI 6 and the M3 Ultra particularly excels when handling multiple shots. While cloud-based solutions may be viable for a single, isolated shot, the speed and efficiency of a high-performance local Mac solution are as impressive as the visual enhancements themselves.Topaz AI 6 is far from a one-click tool; it provides the flexibility to experiment with various AI models and fine-tune parameters such as motion blur, color space, and focus. The M3 Ultra tackles these complex AI-driven tasks with exceptional speed, enabling users to iterate and refine their settings efficiently. The ability to quickly generate and manipulate 5-second previews is crucial for making real-world adjustments, and in our experience, the M3 Ultra is the fastest system we have used to handle this insanely computationally intensive process.Still from a clip 1280 720 (Left) to 3840x 2160 : 4K (Right) click for larger version. High frequency details in the background and depth of field defocus are both handled extremely well.Clearly there are important issues such as providence, copyright and artist rights in any machine learning pipeline. However, upres-ing such as this is not about replacing jobs, nor dramatically removing the creative craft of the VFX. It is however all about providing incredible results that just a few years ago would have been impossible. Some of these processed shots are simply unbelievably good.The software also does SDR to HDR inverse tone mapping . It converts Rec 709, BT. 1886 (Standard Display Gamma Response) to BT. 2020, Wide Color Gamut for 4K and 8K, the color standard designed for ultra-high-definition (UHD) video.There are in some artefacts, especially on very large resolution changes, but in addition to upres-ing the same Topaz software can be used for slow-mo, noise reduction, grain removal and we bought our copy for only $299, but you can sometimes get discounts such as during Black Friday/Cyber Monday.(L) 360P upres to 4K (R). Originally shot high frame rate on a Red Epic. Click to expandOriginal Shot Slow motion: (L) 960 540 to 3840x 2160: 4K (R). Click to expandNuke: GreenScreenFor all the greenscreen comparsions we used a standard Nuke Comp setup to pull the key and examine the matte channels. Naturally, a skilled Nuke compositor could improve on the key or build on what we have done here, but the matte images below are presented as indictative rather than best of class compositing. And on the whole, they are sensible key / matte outputs (more on the Nuke setup below).Left: compressed H264 low res footage: vs. Right 4K upres . Click to expand.Greenscreen: 360p to 4KA Nearly Impossible UpscaleWe selected two sources, one being an archival MP4 clip in 360p, originally shot years ago in Las Vegas for NAB. Longtime fxguide readers may remember our infamous fxguide hangover video, (proof that what happens in Vegas doesnt always stay in Vegas). The footage had every issue imaginable: heavy compression, low resolution, and only 8-bit depth. There is no way that any reasonable imagery should be possible from such a huge leap in resolution. However, in real-world productions, sometimes archival footage is all thats available.We ran the clip through both Topaz AI 6 and the Starlight cloud tool. The processing times varied drastically between the two pipelines. The new diffussion model Starlight solution, though remarkable with its new AI-based approach, required over 50 minutes (50m 45s) to upscale just 10 seconds of footage to 2K. Meanwhile, on the Mac Studio the local 4K upscale with Topaz AI 6, (despite using a different algorithm), ran vastly faster at around 10 frames per second, (under 30 seconds for the same clip, (at higher 4K not 2K resolution!)In viewing the mattes below, the results are remarkably sharp and, most importantly, temporally stable. The stability of the algorithms outputs across successive frames is vital to ensuring that edges do not exhibit unwanted fluctuations or boiling in a composite. While the inferred hair detail is impressive, certain elementssuch as the comb in the hairstylists hands, can sometimes be lost as the program attempts to resolve motion-blurred objects.Source: Original material comped in Nuke, matte below is provided as reference.Note the source was heavily compressed 960540 H264.Special thanks to fxguidetvs Angie and Chris who appear in this clip.https://www.fxguide.com/wp-content/uploads/2025/03/Angie_960x540_comp.mp4https://www.fxguide.com/wp-content/uploads/2025/03/Angie-960x540-matte.mp4Starlight (cloud based): Original Upres-ed to HD and comped in Nuke, matte below is provided as reference.https://www.fxguide.com/wp-content/uploads/2025/03/Angie_1920x1080_comp.mp4https://www.fxguide.com/wp-content/uploads/2025/03/Angie-1920x1080-matte.mp44K Topaz AI 6 : Original Upres-ed to 4K, again comped in Nukehttps://www.fxguide.com/wp-content/uploads/2025/03/Angie_3840x2160_comp.mp4https://www.fxguide.com/wp-content/uploads/2025/03/Angie-3840x2160-matte.mp4Project Starlight leverages an AI diffusion model for video to recreate expected, missing details during upscaling, resulting in high-resolution videos that are rich with detail. The feature also operates without artifacts such as incorrect object motions, a temporal error that can occur when AI doesnt create realistic output.Interestingly, in our work, the visual results favored Starlight in most cases. Since this process relies on AI-driven image generation, some hallucinations occurred, including an instance where Topaz AI 6 mistakenly rendered part of a persons hand as an additional face. On the other hand, Topaz AI 6 was stronger in handling scene transitionsour green screen footage, extracted from an edit, showed some flickering artifacts in the Starlight version, particularly at the beginning and end of the clip.1:1 scale of the low res / compressed source to the up-res 4K. Which is an incredible jump. Note the trouble resolving the logo and the face hallucination in the hand. Click for large version.Greenscreen: Production 2K to 4KFor a more controlled and sensible production example, we used professionally shot green screen footage originally captured in RAW .R3D on an EPIC camera. However, we only had access to the exported transcoded 2K files rather than the original RAW .r3d data. This scenario mirrors real-world challenges where VFX artists must integrate older footage with modern 4K backgrounds. Given the limitations, upscaling the foreground is the only viable solution. Topaz Video AI 6 supports a range of file formats, including .png, .tif, .jpg, .dpx, and .exr. However, it processes EXR files by converting them to temporary 16-bit .tiff images, meaning that 32-bit EXRs do not retain full color information. For our test, we loaded the green screen shot as a sequence of DPX files and upscaled it to 4K.As seen below, the program excels at processing faces and people in general. Hair appears sharper and more consistent, and the results avoid traditional upscaling artifacts such as ringing and excessive edge sharpening, which are common in basic kernel-based sharpening algorithms.One of the challenges of upscaling is preserving skin texture, which can often become flattened or blurred. However, in this case, pore details are enhanced in a natural and believable way, making the results highly usable. While Nuke offers internal scaling options for any footage, Topaz AI 6 appears to deliver a superior result.Source (2K):https://www.fxguide.com/wp-content/uploads/2025/03/Original2KComp.mp4https://www.fxguide.com/wp-content/uploads/2025/03/Original2KMatte.mp44K comp:https://www.fxguide.com/wp-content/uploads/2025/03/UpRes4KComp.mp4https://www.fxguide.com/wp-content/uploads/2025/03/UpRes4KMatte.mp4Nuke (using Cattery AI)The key for this main Greenscreen shot used MODNET which is a Cattery node for roughly segmenting the character out of the green screen, then by shrinking and expanding the matte to get an inner core matter overlayed onto of the outer soft edge (hair) matte, to feed into ViMatte, which another Cattery node for creating the overall matte. Then the matte is normalised to the value between 0 and 1. The matte is then copied to the dispelled plate.The background is simple CG element over a BG plate. The CG element has depth map generated from another Cattery node called DepthAnything, the depth map was used for defocusing the CG element. Grain also added to the CG element.Then FG was graded and multiplied, comped over the BG. BG was also graded through the FG matte to bring some more hair detail back. Both 2K comp and 4K comp were using the same setup, but with some small tweaks.Our Nuke Comp setupM3 UltraThe M3 Ultra is built for extreme performance, handling the most demanding workflows that leverage high CPU and GPU core counts alongside unified memory. If you are just surfing the Web this is not for you. The M3 Ultra is built by Apple for video editors, 3D & VFX artists, and AI researchers. We have a Mac Studio with a M3 Ultra, 32-core CPU, an 80-core GPU, 512GB of unified memory with up to 819GB/s bandwidth, and 12TB of ultra-fast internal storageenough for over 12 hours of 8K ProRes footage. On paper, the M3 Ultra delivers 50% more performance than any previous Ultra chip, with 8 efficiency cores pushing CPU speeds 80% faster than the M1 Ultra, which weve used extensively on our prior four AI-driven film projects. Ultimately, the M3 Ultra Mac Studio is an undeniable powerhouse for professionals working with AI, VFX, and machine learning applications. While cloud-based AI services like Project Starlight have their place, the performance, security, and reliability of local processing make a compelling argument for investing in high-end hardware. While unconfirmed, it is hoped that Starlight will one day also be available as a download implementation able to run locally on high-end hardware. It is currently free to test on the cloud.

Exploring the Potential of Neural Rendering in Visual EffectsNeural Radiance Fields (NeRFs) and Gaussian Splatting are starting to change the way visual effects artists capture, render, and integrate photorealistic scenes, especially environments. In this fxpodcast, Sam Hodge, a machine learning software engineer currently at the Australian Institute for Machine Learning (AIML), University of Adelaide, discusses these emerging techniques and their growing role in virtual production, previsualization, and postvisualization.From Photogrammetry to Neural Radiance FieldsNeRFs offer a major evolution from traditional photogrammetry and LiDAR scanning. While photogrammetry reconstructs static 3D models with baked-in lighting, NeRFs allow for view-dependent rendering, meaning elements like specular highlights and transparency shift naturally based on the cameras perspective. This enables virtual cameras to move through a scene with realistic light transport, a key benefit for VFX workflows.The scene Sam discusses and training in NeRF StudioNeRFs in Production: Strengths and ChallengesNeRFs capture complex materials and lighting conditions with an unprecedented level of realism. However, rendering them remains computationally intensive, with each frame requiring billions of calculations per pixel. This challenge makes real-time applications difficult. To address this limitation, Gaussian Splatting (GS) has emerged as a faster alternative, trading some accuracy for major speed gains.Both NeRFs and GS are not quite ready for high end tentpole final pixel VFX pipelines, but with enormous amounts of research being published on both, it is not unreasonable to expect this to change soon. Certainly they do have a role in the wider range of AI and ML tools that are appearing and fore projects aiming for non-theatrical exhibition.Gaussian Splatting: A Faster AlternativeGaussian Splatting reconstructs 3D environments faster than NeRFs while maintaining photorealistic quality. Instead of relying on polygonal meshes, it uses elliptical points that blend together to create smooth, volumetric visuals. While it does not achieve the same level of fine detail as NeRFs, they can run in real-time, making it ideal for virtual production, game engines, and immersive AR/VR experiences.Dynamic Scenes and 4D Gaussian SplattingNeRFs traditionally struggle with moving objects, but 4D Gaussian Splatting processes time-based data, allowing for the volumetric reconstruction of dynamic performances. This makes it possible to capture live-action events, such as a tennis match or a stage performance, and view them from infinite angles. As a result, 4D Gaussian Splatting opens new possibilities for immersive media, volumetric filmmaking, and interactive experiences.Integrating Neural Rendering into VFX PipelinesVFX professionals continue exploring ways to integrate these technologies into existing pipelines. NeRFs and Gaussian Splatting do not inherently produce polygonal meshes. In the case of NeRFs they live inside a neural network, for GS, they can be thought of as a point cloud.While not immediately providing polygon solutions, they so prove valuable opportunities for: Previsualization and postvisualization, creating photorealistic environments and testing camera movements. Virtual production, providing interactive, high-fidelity backdrops on LED volumes. Location scouting, enabling filmmakers to explore digital representations of real-world locations. Performance capture and digital human references, offering new ways to train AI-driven facial and motion models.A New Era for Machine Learning in VFXThis weeks fxpodcast discussion also highlights how machine learning is reshaping the industry, particularly in generating high-quality synthetic training data. By using NeRFs and Gaussian Splatting to capture real-world actors, environments, and materials, artists can train AI models without relying on scraped internet content. This approach ensures ethical and controlled data acquisition while improving AI-based workflows.A Tool, Not a FadNeRFs and Gaussian Splatting are not passing trends. As these technologies continue to evolve, they offer real advantages for environment creation, camera planning, and immersive media. While the industry is still refining their applications, they already prove their value in production.For a deeper look at these cutting-edge technologies, listen to the full fxpodcast with Sam Hodge.https://www.fxguide.com/wp-content/uploads/2025/03/Apple_NeRF.mp4Here are the data files that Sam and Mike discuss in the podcast:https://r2.fxguide.com/articles/2025-02/prague_video_filtered.ziphttps://r2.fxguide.com/articles/2025-02/PragueInstallerImage.dmg.zipnote: you can also load the project into NeRF Studio as we have above.

Our industry is facing a very serious time. The collapse of Technicolor and its flagship VFX house MPC is a sobering reminder of the instability plaguing the visual effects industry. While external factors such as the post-COVID slowdown, the impact of industry strikes, and cash flow challenges were cited as contributing factors, many insiders also argue that years of financial mismanagement may have played a significant role. Technicolor had already been struggling, having filed for bankruptcy protection in 2020 and undergone multiple restructurings. Despite attempts to consolidate its brands and pivot to new strategies, the company failed to secure long-term financial stability.The sudden impact of MPC, a major player responsible for high-profile projects such as Mufasa: The Lion King, has left thousands of artists without work and disrupted ongoing film productions, highlighting the precarious nature of employment in VFX. This first surfaced when Technicolor notified its U.S. employees last week that it would be required to cease our U.S. operations, including studios The Mill, MPC, Mikros Animation, and Technicolor Games. Companies such as The Mill have been shining lights of VFX mastery for years and are incredibly well regarded in the industry.Beyond Technicolors specific challenges, the broader VFX industry continues to grapple with systemic issues, including cost-cutting pressures, exploitative working conditions, and an unsustainable business model. VFX houses often operate on razor-thin margins, competing in a race to the bottom due to studios demand for cheaper and faster work. This results in a cycle of overwork, burnout, and, in many cases, eventual bankruptcy, as seen with Rhythm & Hues in 2013 and now at Technicolor. The reliance on tax incentives and outsourcing further complicates matters, making VFX work highly unstable. With major vendors collapsing and industry workers facing continued uncertainty, many are calling for structural changes, including better contracts, collective bargaining, and a more sustainable production pipeline. Without meaningful reform, the industry risks seeing more historic names disappear and countless skilled artists move to other fields.Last year, Quebecs animation industry was decimated, following the strikes in Hollywood and Quebecs tax credit reduction. Over half of all animation and VFX jobs in the Canadian province, including in the production hub of Montreal, have been lost since January 1, 2023, according to the Quebec Film and Television Council (QFTC). Even after this weeks episode was recorded, today Walt Disney Animation Studios has laid off staff from its Vancouver studio as a result of a shift in business strategy from a focus on theatrical features complemented by short-form streaming content, a Disney spokesperson is reported saying, This means the studio is no longer making long-form content for Disney+. It seems each day brings more bad news.Scott RossScott RossScott Ross was a key manager at George Lucas companies in the 80s and in 90s he co-founded Digital Domain, along with James Cameron and Stan Winston.He has a new book out UPSTART: The Digital Film Revolution Managing the UnManageable. In this special episode, we spoke to Ross to gain a different perspective on the massive structural changes in VFX and the company failures rocking our industry.In the 1980s, Ross was general manager of ILM and under his leadership, ILM won five Academy Awards for Best Visual Effects (Who Framed Roger Rabbit, Innerspace, Terminator 2: Judgment Day, The Abyss, Death Becomes Her). The company re-organized in 1991 and Ross was named senior vice president of the LucasArts Entertainment Company, which comprised Skywalker Sound, LucasArts Commercial Productions, LucasArts Attractions, EditDroid/SoundDroid and ILM.Under Ross direction, from 1993 to 2006, Digital Domain garnered two Academy Awards and three nominations, receiving its first Oscar in 1997 for the ground-breaking visual effects in Titanic. That was followed by a second Oscar for What Dreams May Come. Digital Domain received additional nominations forTrue Lies,Apollo 13andI, Robot and won three Scientific and Technical Academy Awards for its proprietary software, including the birth of Nuke (now Foundry).* The highlight image for this fxpodcast story is the Pirate flag that flew once over DD headquarters in Vencie California.Dont forget to subscribe to both the VFXShow and the fxpodcast to get both of our most popular podcasts.This week in space, our lineup is:Matt Wallin * @mattwallin www.mattwallin.com.Follow Matt on Mastodon: @[emailprotected]Mike Seymour @mikeseymour. www.fxguide.com. + @mikeseymourWith special guest, Scott Ross.(Jason Diamond was on location filming this week but he will be back next week).Special thanks to Matt Wallin for the editing & production of the show with help from Jim Shen.

Scott Derricksons The Gorge is a gripping blend of sci-fi, action, and romance, grounded by an intense, isolated setting that plays a crucial role in the story. Bringing this unique environment to life was a significant challenge, one taken on by two principal visual effects houses: DNEG and Framestore. We spoke with two of the films VFX supervisors from DNEG, Anelia Asparuhova and Sebastian Von Overheidt, to explore the complexity of constructing The Gorges visually arresting world. Crafting The Gorge: A Character in ItselfThe gorge isnt just a backdrop, says Asparuhova. Its almost like a character in the film. The secluded, seemingly impenetrable landscape serves as both a prison and a battleground for the protagonists, Levi (Miles Teller) and Drasa (Anya Taylor-Joy), who are stationed on opposite sides.The films production team had a general concept of the gorges design early on, but it was up to DNEG to bring it to life in a way that felt both realistic and visually striking. We had a previous model based on some scans from Norway, Asparuhova explains. Theres a website where you can download the entire country as a CG scan. We took inspiration from Norways gorges but wanted a more Central European look, incorporating references from Greece and Bulgaria.To ensure scientific credibility, the team even consulted geologists. We wanted to make sure that every rock formation, tree, and feature made sense geologically, adds Von Overheidt. Even though the gorge isnt real, we wanted it to feel real. Making the Gorge InescapableThe gorges geography had to support the films narrative constraints. Why couldnt the characters simply walk around it? Why was it so impossible to escape? We had an explanation, Asparuhova says. Thats why we placed a massive waterfall on one side and a sheer rock wall on the other. These choices not only reinforced the narrative but also posed technical challenges. One of the biggest was conveying scale. When you start building environments in CG, they can often feel miniature, Asparuhova points out. We had to add layers of detail, especially fog, depth haze, and we even added some CG birds (an age old VFX trick!), to emphasize the scale. Photorealistic Lighting and Optical DepthA key element in grounding The Gorge in reality was achieving the right depth of field and optical qualities. Even today, I see car shots where the depth of focus outside the window feels off, notes Von Overheidt, a former compositor. Its something you instinctively feel as wrong, even if you cant articulate why.Von Overheidts experience played a crucial role in nailing these subtle but vital elements. We analyzed reference photography, carefully studied bokeh shapes, and matched depth-of-field characteristics to real lenses, he explains. Different cameras and lenses have distinct looks, and we wanted to maintain that authenticity. Towers, Zip Lines, and Drone BattlesThough The Gorge relied on practical sets for certain key locations, much of its environment was CG-enhanced or fully digital. The production built partial sections of the towers, including their bases and tops, but the midsections were entirely CG. We had to seamlessly integrate practical elements with digital extensions, Asparuhova explains. The films action sequences required extensive VFX work. We handled the zip line sequence, the skydiving scenes, and the quadcopter chase through the forest, Von Overheidt says. Even in shots where the actors were filmed in real locations, we often had to extend the environment into the distance to maintain continuity. Drones played a major role in the film, serving both as surveillance tools and deadly weapons. I handled the smaller drones, says Asparuhova, while Seb worked on the more aggressive, heavily armed ones. Von Overheidt adds, The art department provided a model, but we beefed it up, making it look more tactical, with larger weapons and a more menacing silhouette. The Climactic Explosion: Destroying the GorgeThe film culminates in a devastating nuclear explosion, a sequence that required intricate effects work. We looked at real nuclear test footage, Asparuhova reveals. Its eerie, but incredibly useful reference material.One of the biggest challenges was adapting real-world nuclear explosion dynamics to the gorges enclosed space. In real tests, the shockwave expands outward across a flat surface, she explains. But our explosion was hundreds of meters below the ground, contained by the gorge walls.This unique setup influenced how the shockwave behaved. Instead of purely radiating outward, it funneled up and out, she says. Thats why you see that distinctive lifting effect at the edges.Von Overheidt highlights the importance of layers in achieving realism. We had pre-shockwave smoke, then the destructive shockwave itself, which flattens the trees and crumbles the towers, and then the big blast, he describes. It wasnt just one big explosionit was a sequence of events.Seamless Digital Doubles and Stunt TransitionsOne of the most demanding character effects was Drasas parachute jump into the gorge. The beginning of her run was practical, but the jump itself transitioned into a full-CG double, Von Overheidt says. It had to be seamlessmatching costume folds, hair sim, everything.Unlike purely technical challenges, this was about maintaining the illusion of physicality. Ive worked on other free-fall sequences before, like Uncharted, he adds. Getting the acceleration and terminal velocity to feel right was crucial. A Cohesive VisionDespite the scope and complexity of the VFX, the films visual style remained consistent. For the most part, the creative vision was locked in early, says Asparuhova. There were minor reshoots, but nothing that drastically changed the edit. Von Overheidt agrees. We had a clear roadmap, which helped keep things cohesive across our teams in North America and Europe.Ultimately, The Gorge showcases the power of VFX in storytelling, not just as a means of spectacle but as a way to shape the world in which characters struggle and connect. Whether through vast landscapes, heart-pounding action, or intimate lighting nuances, the work ensures that The Gorge feels as immersive as it is thrilling.

BEST VISUAL EFFECTSDUNE: PART TWOPaul Lambert, Stephen James, Rhys Salcombe and Gerd Nefzer won for Dune 2.Dune: Part Two fxpodcast Visual Effects Supervisor Paul LambertANIMATED FEATURE FILMFLOWThe visionary masterpiece from Latvia, won best Animated Feature.ANIMATED SHORT FILMIn the Shadow of the Cypress, Shirin Sohani and Hossein MolayemiCinematographyLol Crawley won for The Brutalist

Ramsey Avery is the Production Designer of Marvels latest film, Captain America: Brave New World. In this weeks fxpodcast, we speak to him about the films challengesand his perspective on the relationship between production design and visual effects.In Captain America: Brave New World, Sam finds himself involved in an international incident after meeting with President Thaddeus Ross. He must discover the reason behind a nefarious global plot before the true mastermind has the entire world seeing red.Red Hulk/President Thaddeus Ross (Harrison Ford) in Marvel Studios CAPTAIN AMERICA: BRAVE NEW WORLD. Photo courtesy of Marvel Studios. 2024 MARVEL.Marvel Studios Captain America: Brave New World stars Anthony Mackie, Danny Ramirez, Shira Haas, Carl Lumbly, Xosha Roquemore, and Harrison Ford. The film is directed by Julius Onah and produced by Kevin Feige and Nate Moore.Ramsey Avery, the Production Designer of Marvels Captain America: Brave New World.Ramseys past credits include The Lord of the Rings: The Rings of Power, Guardians of the Galaxy Vol 2., Tomorrowland, and earlier in his career Minority Reportand A.I. Artificial Intelligence. His vast experience allows him to implement the newest digital tools and collaborate with VFX to immerse the audience into the worlds he is creating. In this fxpodcast, he discusses the relationship between Production Design and VFX, which is crucial as technology plays a greater and greater role in filmmaking. He discusses in detail how digital design tools helped build the crucial sets in Captain America: Brave New World. Ramsey also shares here the behind-the-scenes images of how he was mindful of making VFX team jobs easier on this film by sometimes building more of a set to save them time and money and thinking about post-team in design.ScreenshotAt the end of Avengers: Endgame, Steve Rogers passed on his vibranium shield to Sam Wilson, who had stood beside the Avengers as the winged Falcon. But the decision to take on the mantle of Captain America was more complex for Wilson, and his journey from Falcon to Captain America was explored in Marvel Studios The Falcon and The Winter Soldier series for Disney+. This was naturally the jumping off point for the film both in terms of plot and visuals.(L-R): Director Julius Onah, Xosha Roquemore, and Anthony Mackie behind the scenes of Marvel Studios CAPTAIN AMERICA: BRAVE NEW WORLD. Photo by Eli Ad. 2024 MARVEL.This return to the Captain America franchise is also a return to the tone of Captain America: The Winter Soldier, meaning a more grounded, more geopolitical landscape punctuated with issues that feel relevant and timely. Says Nate Moore, We have a hero who doesnt have superpowers but is very well-versed in the political and military landscapes, so this film puts Sam squarely back into the genre of the political thriller.Captain America/Sam Wilson (Anthony Mackie)Principal photography on Captain America: Brave New World began in Spring 2023 with the director tasking his brain trust of creatives, including cinematographer Kramer Morgenthau (Creed III) and production designer Ramsey Avery, working with visual efects supervisors Bill Westenhofer (Life of Pi) and Alessandro Ongaro (The Adam Project) to blaze a new path for Captain Americas next chapter.Production DesignConcept Art from Averys teamConcept Art from Averys teamColour PaletteCapturing it all on camera in a compelling way would be essential to realizing Onahsvision. Leading the charge was award-winning director of photography Kramer Morgenthau, known for his innovative camera work and dynamic lighting design. We wanted to achieve a look that was as close as humanly possible to shooting photochemical film but with digital cameras. So, in prep we shot extensive tests and dug deeply into color science and vintage anamorphic lenses to achieve that look, explains Morgenthau. We created a set of rules around camera movement, color, composition and texture. The goal was for the film to pay homage to some of the great 8 paranoid thrillers of the 1970s but also have the visual space for the extensive action and spectacle that Marvel Studios films achieve on the highest level.Mood board showing the colour palettes for the various scenes.Below is more of the concept art, combines with the colour palette from the Production Department.Taking full advantage of the versatile environments and topography in and around Atlanta, Georgia, which was home base for the production, the filmmakers looked to veteran production designer Ramsey Avery to establish the multi-layered visual landscape.Left: Director Julius Onahand Production Designer Ramsey Avery on setAverys first conversations with the director yielded a focused, more intentional and relatable sense of realism for Captain America: Brave New World to further the materials tone and narrative and allow for a transition away from the visual vocabulary thats been a mainstay of Phase 5 of the Marvel Cinematic Universe. For Brave New World, in particular, Julius [Onah] wanted the aesthetic to be very specific and feel like it was something that could be happening now within the current space, says Avery. He also wanted to veer away from those elements that can sometimes take an audience out of the storytelling. It really was important to Julius and Kevin [Feige] that this story felt of the moment and mimicked the characters as they move through a very real and honest world.WashingtonWhile the films settings are far-reaching, the majority of the productions film schedule was completed at Trilith Studios, with cast and crew traveling to Washington, D.C. to film exterior scenes for a week amidst iconic landmarks like the White House, the Capitol Building and Pershing Park. Practical trees were then extended digitally by VFXWorking closely with the productions location team overseen by Ilt Jones (Black Panther: Wakanda Forever), Avery, set decorator Rosemary Brandenburg, construction coordinator John Hoskins and their respective teams of talented crafts people, transformed buildings, streetscapes and other locations throughout their home production city of Atlanta to mimic the films diverse settings in every way.The practically built Rose Garden setThe practically built Rose Garden setsThe Tyler Perry Studios White House SetAmong the sets practically built were the White House Bunker Situation Room, Camp Echo, the Oval Ofice and the White House Rose Garden and Hains Point exterior sets. As Avery discusses in the fxpodcast, in Atlanta, Tyler Perry Studios has one of the largest production facilities in the country, showcases forty buildings including a 3/4 scale real physical built copy of the White House.Prison Set /Lab SetIn Captain America: Brave New World, the production design and VFX teams collaborated closely to create an extensive range of environments, seamlessly integrating practical sets with digital extensions. One of the films most striking sets is the prison set, at hidden black site in West Virginia called Camp Echo One, which reveals the secret lab of Dr. Samuel Sterns. This showcased the scale and complexity of the physical builds required for the film, but again linked to live action locations near principal photography, as Avery reveals in the fxpodcast.With the film embracing a more grounded tone, the production design was meticulously crafted to maintain a cohesive cinematic language. This was reinforced by a carefully structured color palette that threaded through both the physical and digital elements, ensuring visual continuity. The integration of in-camera set pieces with VFX-driven expansions highlights the balance between tangible world-building and digital artistry, a hallmark of Marvels evolving cinematic approach.Captain America/Sam Wilson (Anthony Mackie) in Marvel Studios CAPTAIN AMERICA: BRAVE NEW WORLD . Photo courtesy of Marvel Studios. 2024 MARVEL.Captain America: Brave New World debuted on February 11, 2025, with a high-profile premiere at the TCL Chinese Theatre in Hollywood before its nationwide release on February 14 as part of Phase Five of the Marvel Cinematic Universe. The film has securing the position as the third-highest-grossing film of 2025 so far.

GenAIChatGPT has undeniably been the poster child for the generative AI (GenAI) revolution, capturing both headlines and imaginations. But as AI-powered tools continue to push the boundaries of creative content generation, its clear that GenAIs impact extends far beyond chatbots. This week, the Visual Effects Society (VES) is hosting a timely panel discussion exploring GenAIs role in the VFX industry, featuring a roster of experts with hands-on experience at the cutting edge of AI-driven artistry. Among them is visual effects supervisor Jim Geduldick, a longtime friend of fxguide and a recognized pioneer in the intersection of virtual production, machine learning, and computer vision within visual effects and filmmaking.Jim Geuldick, VFX Sup, Virutal Production expert and FilmmakerGeduldicks career spans decades of creative problem-solving, from real-time rendering to LED volumes, making him an ideal candidate to demystify the impact of AI in visual effects. With AIs rapid evolution, panel discussions like this are becoming increasingly critical. AI may not yet have a digital consciousness or a theory of mind popular in sci-fi movies, but it is getting closer to helping VFX artists create those movies.Joining Geduldick on the VES panel are other prominent voices in the space, including avant-garde AI artist Minta Carlson, concept artist and digital sculptor Martin Nebelong (who has worked extensively with AI tools such as OpenAIs SORA), and creative technologist Don Allen Stevenson III. The discussion promises to examine AIs influence from multiple perspectivestechnical, artistic, and cultural.We sat down with Jim Geduldick to preview the panel, and he emphasized the need to distinguish between GenAI and AI as a whole. A lot of what we do now is just educating clients, studios, and labels, he said. So much of the discourse around AI in VFX gets lumped into good, bad, or uglywith people assuming its just tools like Runway ML or SORA. But in reality, were talking about a range of technologies, from machine learning to computer vision, that have been foundational to VFX for years.The need for education around these technologies is not new. AI represents just the latest in a series of technological shifts that have required industry-wide adaptation. AI is already woven into the fabric of VFXoften in ways that go unnoticed. The misconception that AI is only about generative tools is one of the biggest hurdles, Geduldick explained. AI is in render denoising, deep compositing, and countless other aspects of production, yet the public doesnt realise how much were already relying on it.One of the most persistent misconceptions is the belief that using an AI model inherently contributes to its training data, which is not the case. Training Data is used to make the model, but to run the model doesnt have to contribute to the model. Naturally, many in our industry remain concerned about copyright issues, fearing that running an AI model on local project automatically integrates that data into a global dataset. People freak out over copyright issues, assuming that running an AI model on local data means that data is automatically being added to a massive public dataset, Geduldick said. But training data can be air-gapped. Studios can keep their AI tools completely self-contained and secure, just as they do with cloud computing.Beyond legal and ethical considerations, Geduldicks focus at the VES panel will be on AIs practical applications in VFX. His discussion will explore how AI is already enhancing production pipelines today. For example, the way we approach site scans and data wrangling has changed with AI-assisted depth capture, he said. Were integrating LIDAR scans with machine learning to automate tedious tasks, allowing artists to focus on creative work.A particularly promising area of AI-driven innovation is the use of Neural Radiance Fields (NeRFs) and Gaussian splats for location and set surveying. Geduldick has been actively involved in this space, contributing to early research with NVIDIA. Were getting closer to a state of maturity where NeRFs and splats can be viable for production, he noted. That said, we still face challengesocclusion errors, data quality issues, and the need for additional processing to make these formats truly production-ready.Another major focus for Geduldick is the role of AI in digital doubles. Several of his recent projects have required the creation of digital doubles for actors who are no longer living. One thing that Ive come across, especially this last year, was having to do a lot more doubles with people that have passed on, he said. The challenge is that if we dont have a person that we can scan today, we need to find someone with similar facial structure to make it believable. AI can really work well using techniques such as DeepFakes.The quality of training data remains a key factor in AI-generated assets, and Geduldick emphasized the increasing importance of synthetic data in addressing these challenges. AI-generated training datasets can be incredibly useful for avoiding copyright issues and ensuring data quality, he noted. Yet, its a topic that often gets overlooked in these discussions.The VES panel is scheduled for Thursday, February 20th, beginning at 11:00 AM PST. Given the high level of interest, the session is expected to extend beyond its allotted time to accommodate audience questions.With AI in VFX becoming a highly debated topic, this discussion aims to offer clarity and practical insights rather than speculative hype. Geduldicks focus will be on real-world applications and current production pipelines, reinforcing the idea that AI is not a replacement for artists but a tool that, when used effectively, enhances the creative process. AI is a tool, not a magic button, he said. Its about finding ways to use it effectively, not replacing the artistry that makes visual effects so compelling. In a rapidly evolving industry, such discussions are essential to ensuring that AI is leveraged in ways that support and elevate visual storytelling.The panel is on this week, Thursday, February 20, 2025 at 11:00AM (PST), (which is 1:00PM (CST), 2:00PM (EST), 7:00PM (GMT), 8:00PM (CET), Friday, February 21, 2025 at 12:30AM (IST), 6:00AM (AEST), 8:00AM (NZST))

This week, we have a double ep (of sorts). We discuss the 2025 Oscar nominations, plus we do a (short) review of Alien: Romulus, the 2024 science fiction horror film directed by Fede lvarez and written by lvarez and Rodo Sayagues.We start with the team discussing the nominations for the Oscars in 2025, which are:ALIEN: ROMULUS: Eric Barba, Nelson Sepulveda-Fauser, Daniel Macarin and Shane MahanBETTER MAN: Luke Millar, David Clayton, Keith Herft and Peter StubbsDUNE: PART TWO: Paul Lambert, Stephen James, Rhys Salcombe and Gerd NefzerKINGDOM OF THE PLANET OF THE APES: Erik Winquist, Stephen Unterfranz, Paul Story and Rodney BurkeWICKED: Pablo Helman, Jonathan Fawkner, David Shirk and Paul CorbouldIn the second half of the show, we catch up on discussing Alien: Romulus, which we have not previously managed to review.Alien: Romulus follows Rain Carradine, an orphaned colonist at the struggling Jacksons Star settlement on the dark planet LV-410. After discovering that Weyland-Yutani has forcibly extended her work contract, she plans an escape with her friends and adopted brother Andy, a malfunctioning android. They commandeer a hauler to reach Renaissance, an abandoned Weyland-Yutani station, intending to steal cryostasis equipment for their journey to an independent planet. However, their mission takes a deadly turn when they accidentally release facehugger parasites.In a desperate attempt to regain control, Rain upgrades Andy with a security chip, only for him to become loyal to Weyland-Yutani. As the stations dark history is revealedincluding past experiments on a xenomorph recovered from the Nostromos wreckagethe group realizes they are trapped with a growing xenomorph threat. As the station hurtles toward destruction, the survivors face a harrowing fight against the creatures.Dont forget to subscribe to both the VFXShow and the fxpodcast to get both of our most popular podcasts.This week in space, our lineup is:Matt Wallin * @mattwallin www.mattwallin.com.Follow Matt on Mastodon: @[emailprotected]Jason Diamond @jasondiamond www.thediamondbros.comMike Seymour @mikeseymour. www.fxguide.com. + @mikeseymourSpecial thanks to Matt Wallin for the editing & production of the show with help from Jim Shen.

14 scientific and technical achievements to be honored with academy awardsThe Academy of Motion Picture Arts and Sciences announced 14 scientific and technical achievements, represented by 37 individual award recipients, will be honored at its annual Scientific and Technical Awards ceremony, which has been rescheduled to Tuesday, April 29, 2025, at the Academy Museum of Motion Pictures.Achievements receiving Scientific and Technical Awards must demonstrate a proven record of contributing significant value to the process of making motion pictures. In addition, an Academy Award of Merit (an Oscar statuette) will be presented at the ceremony to collectively recognize all the individuals who have developed and supported captioning technology, whether open or closed, for film. The statuette will reside at the Academy Museum of Motion Pictures.As part of the Academys mission to celebrate artistry and innovation in filmmaking, we are honored to recognize the exceptional contributions of this years Scientific and Technical Awards recipients. Their work has powerfully driven advancements in our industry, said Academy CEO Bill Kramer and Academy President Janet Yang. Also, we are deeply honored to present the Academy Award of Merit to the individuals who created and supported the development of captioning for films. This is an essential technology that plays a vital role in making the cinematic experience accessible to all.Each year, our international committee of industry professionals conducts thorough evaluations of the innovation and impact of technologies developed for the motion picture industry, said Darin Grant and Raymond Yeung, co-chairs of the Academys Scientific and Technical Awards Committee. This years awards encompass a wide range of film production advancements, from fire stunt safety, stabilized hand-held camera operation, and animation to post-production innovations in dialogue capture and CG imagery rendering systems. These vital technologies have expanded the visual possibilities of cinema, creating new and compelling experiences for moviegoers.The Academy Awards for scientific and technical achievements are:TECHNICAL ACHIEVEMENT AWARDS (ACADEMY CERTIFICATES)To Essex Edwards, James Jacobs, Jernej Barbic, Crawford Doran and Andrew van Straten for the design and development of Ziva VFX.Ziva VFX is a system for constructing and simulating muscles, fat, fascia, and skin for digital characters. An artist-friendly interface that emphasizes easily understood physical metaphors, coupled with a robust, physically accurate solver, has enabled a broad range of studios to bring visually rich creatures to life.To Javor Kalojanov and Kimball Thurston for the creation of Wt FXs ML Denoiser.This denoiser prioritizes temporal filtering using innovative optical flow techniques to preserve crucial details. Novel training strategies allow its machine learning algorithms to denoise computer-generated imagery to the most exacting standards.To Neeme Vaino for the development of Fireskin360 Naked Burn Gel.This widely available gel allows longer targeted burns directly on the skin, broadening the range of fire stunts performed across the industry.To Dustin Brooks and Colin Decker for the development of naked burn gel.Fire for Hires gel first publicly demonstrated a naked burn, where fire appears directly on the skin, enabling a new form of safe fire stunts in motion pictures.To Attila T. fra for the creation of Intel Open Image Denoise, and to Timo Aila for his pioneering work at NVIDIA applying U-Nets to denoising.Open Image Denoise is an open-source library that provides an elegant API and runs on diverse hardware, leading to broad industry adoption. Its core technology is provided by the widely adopted U-Net architecture that improves efficiency and preserves detail, raising the quality of CG imagery across the industry.To Mark Noel for adapting and enhancing the safety and reliability of transportable six-degrees-of-freedom motion base technology for motion picture use.The NACMO series of modular motion bases enables filmmakers to dynamically control simulated actions, providing precise movements, enhancing special effects, and enriching the visual experience for audiences worldwide.To Su Tie for the development of the sensor analysis and stabilization software, to Bei Shimen for the electrical engineering, and to Zhao Yanchong for the mechanical design and engineering of the Ronin 2 gimbal system.Utilizing three-axis stabilization through multiple sensors, the DJI Ronin 2 has achieved broad adoption. It is controllable from a diverse set of input devices, enabling filmmakers to create complex, dynamic camera moves.To Tabb Firchau for the conception and development, to John Ellison and Steve Webb for the attitude control system, to David Bloomfield for the motor design, and to Shane Colton for the motor driver system design of the Mvi gimbals.Freefly Systems introduction of handheld stabilized gimbals provides single-person or collaborative remote camera operation with various controllers, enabling previously difficult shots without dolly or crane-supported stabilized heads.SCIENTIFIC AND ENGINEERING AWARDS (ACADEMY PLAQUES)To Jayson Dumenigo for the development of the Action Factory Hydrogels.Action Factory hydrogels are engineered to allow longer burns at higher temperatures with quick turnaround times, increasing the safety and efficiency of fire stunt performances.To Thijs Vogels, Fabrice Rousselle, David Adler, Gerhard Rthlin and Mark Meyer for the creation of Disneys ML Denoiser.This sophisticated machine learning denoiser features a ground-breaking kernel-predicting convolutional network and temporal stability. It has been adopted far beyond its original domain of animation and is an essential tool for creating computer-generated imagery in feature films.To Nir Averbuch, Yair Chuchem and Dan Raviv for the concept, design and development of the Auto Align Post 2.Sound Radixs Auto Align Post 2 allows the seamless blending of multiple moving microphones during film post-production, eliminating phase distortion, saving significant time over manual alignment methods and raising the reproduction quality of dialogue recorded on set.To Curt Schaller for the concept, design and development of the Trinity 2 system, and to Dr. Roman Foltyn for the software and hardware design of its motorized stabilized head.The ARRI Trinity 2 is a body-worn system that combines a traditional inertial camera stabilization system with electronic gimbal technology, allowing unprecedented freedom of camera movement for acquiring shots with multiple transitions that are otherwise unobtainable.To Steve Wagner for the initial concept and software, to Garrett Brown for the design, and to Jerry Holway and Robert Orf for the engineering of the Steadicam Volt stabilization system.The Tiffen Steadicam Volt revolutionizes inertial stabilization with its advanced two-axis motorized design, creating artificial inertia and simulated friction while providing adjustable tactile feedback. Different modes allow the operator to alter the physical feel of the rig. The Volt empowers filmmakers to achieve dynamic shots with more complex camera movement while maintaining a stable roll axis.To Dave Freeth for the design, engineering and development of the hand-held Stabileye three-axis motorized camera stabilization system.The compact size and live adjustment of operating parameters of these devices facilitate subtle and dynamic camera moves closer to actors, and in tighter quarters than previously possible. Its low latency allows for instinctive operation whether controlled by a single operator or remotely.

Actor-writer-comedians Rachel Sennott and Bowen Yang announced the 97th Oscars nominations today (January 23) at the Academys Samuel Goldwyn Theatre. Active members of the Academy are eligible to vote for the winners in all 23 categories beginning Tuesday, February 11, through Tuesday, February 18. The 97th Oscars will be held on Sunday, March 2, 2025, at the Dolby Theatre at Ovation Hollywood.Emilia Perz leads with 13 nominations overall, Wicked and The Brutalist follow with 10 each.VISUAL EFFECTS NOMINEESALIEN: ROMULUSEric Barba, Nelson Sepulveda-Fauser, Daniel Macarin and Shane MahanNelson Sepulveda-Fauser, ILM: Working on Alien: Romulus with Fede lvarez, a director with such a bold and compelling vision, was an absolute pleasure. I am incredibly proud of the beautiful imagery the ILM Sydney and San Francisco teams brought to the screen. Bringing this project to life has been nothing short of extraordinary.We are incredibly proud to have our teams work on the third act of Alien: Romulus recognized by the Academy., commented Daniel Macarin, Wt FXs VFX Supervisor onAlien: Romulus. We worked closely with director Fede lvarez to build on the franchises history and bring audiences closer to the rings of a planet than ever before. We hope this nomination inspires the next generation of VFX artists and sci-fi space film fans.BETTER MANLuke Millar, David Clayton, Keith Herft and Peter StubbsLuke Millar, VFX Supervisor forBetter Mansays, We are extremely honoured thatBetter Man is nominated for Best Visual Effects at the 2025 Academy Awards. The film represents an insane amount of work and talent from the artists, production and support staff here at Wt FX and we are humbled that these efforts have been recognised by our peers. It was truly such a fantastic project to be a part of, and the work is something that I will always be incredibly proud of.fxpodcast: Better Man with Wt FXDUNE: PART TWOPaul Lambert, Stephen James, Rhys Salcombe and Gerd NefzerDune: Part Two fxpodcast Visual Effects Supervisor Paul LambertKINGDOM OF THE PLANET OF THE APESErik Winquist, Stephen Unterfranz, Paul Story and Rodney BurkeWe were thrilled to wake up to the good news this morning. It is an honour getting to represent the more than a thousand artists, developers, production, and support crew who worked their magic for over a year on Kingdom, remarked Erik Winquist, VFX Supervisor onKingdom of the Planet of the Apes . Collaborating with Wes Ball & 20th Century on this was a delight, and its so satisfying to see our work recognised by the Academy. Were looking forward to celebrating this past year of cinema on March 3rd.fxpodcast #369: Kingdom Of the Planet of Apes with Director Wes Ball and VFX Supervisor Erik WinquistWICKEDPablo Helman, Jonathan Fawkner, David Shirk and Paul CorbouldWhat an incredible experience to be a part of Wicked, and an honor to be nominated! It was a real team effort, and now the celebration starts! exclaims VFX Sup. Pablo Helman. Im so excited for our nomination and honored to be part of such an amazing team! adds ILMs David Shirk. I was frequently awed by the artistry and passion of the crew. Its an incredible thrill to see our contribution recognized for a film that is so emotional, optimistic and has connected so strongly with audiences.Fiona Walkinshaw, Framestores CEO, Film & Episodic, commented: Having our filmmaking peers and partners recognise the craft, creativity and innovation of our team like this is an amazing way to start the year. Jonathan and his team really pulled out all the stops when it came to conjuring the magic of Shiz University, so a huge congratulations to every single artist, producer and technologist who helped breathe life into Wicked and craft the films gravity-defying VFX.Pablo Helman breaks down WickedANIMATED FEATURE FILM NOMINEESFLOWINSIDE OUT 2MEMOIR OF A SNAILWALLACE & GROMIT: VENGEANCE MOST FOWLTHE WILD ROBOTANIMATED SHORT FILM NOMINEESBEAUTIFUL MENNicolas Keppens and Brecht Van ElslandeIN THE SHADOW OF THE CYPRESSShirin Sohani and Hossein MolayemiMAGIC CANDIESDaisuke Nishio and Takashi WashioWANDER TO WONDERNina Gantz and Stienette BosklopperYUCK!Loc Espuche and Juliette MarquetCinematography NomineesThe BrutalistLol CrawleyDune: Part TwoGreig FraserEmilia PrezPaul GuilhaumeMariaEd LachmanNosferatuJarin BlaschkeProduction Design NomineesThe BrutalistJudy Becker; Set Decoration: Patricia CucciaConclaveSuzie Davies; Set Decoration: Cynthia SleiterDune: Part TwoPatrice Vermette; Set Decoration: Shane VieauNosferatuCraig Lathrop; Set Decoration: Beatrice BrentnerovWickedNathan Crowley; Set Decoration: Lee Sandales

Silo 2Season 2 of Silo on Apple TV+ is set to deepen the intrigue of the underground dystopian world that captivated audiences in its first run. Based on Hugh Howeys based Silotrilogy of novels (Wool,Shift, andDust).Silo has become a flagship show for Apple+, combining compelling visual storytelling with stunning visual effects. The first season introduced audiences to the titular Siloa massive, self-contained underground community where humanity survives after an apocalyptic event. With secrets layered at every level of the structure, the series is as much about the physical environment as it is about the psychological impact of isolation and control.The cinematography in Silo is a critical element in establishing its unique tone. By leveraging tight, claustrophobic framing and dim, moody lighting, the series underscores the oppressive environment of the Silo while reflecting the characters psychological confinement. Alternately, moments of expansive compositions and dynamic camera movement are used to highlight rare glimpses of freedom or rebellion, creating a visual rhythm that mirrors the emotional beats of the story. This meticulous approach elevates the storytelling, ensuring every shot contributes to the immersive and unsettling atmosphere. In this weeks fxpodcast we breakdown the series with one of the shows principle Directors of Photography, Ed Moore, BSC. As with most tentpole high budget series, a set of crews alturnate per episode, Ed Moore and Director Amber Templemore worked on multiple episodes especially in the later half of season 2. In Silo 2, the production design and visual effects work hand-in-hand to create a tangible, oppressive environment. The shows commitment to realism is apparent in every frame, with CG work often invisible but essential to the storys immersive quality. The lead visual effects were by ILM, as Ed Moore discusses in the podcast, while the set was vast, ILM had the task of working closely with the DOPs to extend the set and integrate the visuals. Season 2 promises to expanded the visual and narrative elements of the show, delving deeper into the mysteries of the Silos origins and the larger world outside. The challenge for the creative teams was to balance the shows grounded aesthetic with the need to broaden the visual scope of the show, showing more of the post-apocalyptic landscape beyond the Silos walls.From a technical perspective, Silo stands out for its restrained yet precise use of visual effects combined with dark and complex visual plate photography. An example is the opening shot of Season 2s 5th episode. As Ed Moore discusses in the fxpodcast, the shot was a remarkable combination of a very cleverly designed and executed live action camera move with ILM providing extensive set extension. Ed posted the following clip on Instagram showing the behind the scenes camera department engineering and execution.View this post on InstagramA post shared by Ed Moore BSC (@edmooredop)Ed Moore has provided a set of his own personal black and white photography behind the scenes of season 2. Below is a featurette showing the complex filming sets and extensive production design.

Chris Bridges, is the SFX visionary behind Gaslight FX Studio, a powerhouse in the world of prosthetic makeup and special effects. With nearly 30 years of experience, Chris has carved a niche in the industry, seamlessly blending artistry with cutting-edge technology.As the Head of Department for Prosthetics on Star Trek: Strange New Worlds, and a proud Emmy winner, Chriss expertise is sought after by filmmakers looking to elevate their storytelling through innovative special effects.Gaslight FX Studio recently collaborated on the gripping horror/drama Heretic, which premiered at TIFF and was released last Nov. This project not only showcased Chriss exceptional talent but also exemplifies his commitment to storytelling. The studio crafted a variety of intricate makeup effects, from the hauntingly emaciated look of the Prophets to the striking prosthetic arm gag featuring Hugh Grant.As you can hear in this weeks fxpodcast, what sets Gaslight FX apart is its meticulous approach. Chris and his team conducted an in-depth breakdown of the script, aligning closely with the directors to ensure that every effect served to enhance the films narrative. The prosthetics were designed not merely for shock value but to immerse audiences in the psychological horror of confinement and starvation.Fans eagerly anticipate the release of Season 3 of Star Trek: Strange New Worlds in early 2025, with a fourth season already ordered. Download and listen to our fxpodcast on Gaslight FX Studios and the brilliant work of Chris Bridges, whereever you listen to podcasts.

The EE British Academy Film Awards (BAFTAs) are prestigious annual awards presented by the British Academy of Film and Television Arts to honor outstanding achievements in the film industry. Recognized as one of the most significant film awards globally, the BAFTAs celebrate excellence across a range of categories, including acting, directing, writing, cinematography, and production design. The awards were first established in 1947, and the ceremony takes place in London, attracting leading figures from the international film community. Often considered a precursor to the Oscars, the BAFTAs provide a strong indication of what the VFX and animation community believe have made substantial contributions to the art form.Special Visual Effects NomineesBetter ManLuke Millar, David Clayton, Keith Herft, Peter StubbsOur fxpodcast with Director Michael Gracey:Director Michael Gracey & making Better ManDune: Part TwoPaul Lambert, Stephen James, Gerd Nefzer, Rhys SalcombeOur fxpodcast with Visual Effects Supervisor Paul Lambert:Dune: Part Two fxpodcast Visual Effects Supervisor Paul LambertGladiator IIMark Bakowski, Neil Corbould, Nikki Penny, Pietro PontiOur fxguide story with Overall Production VFX Supervisor: Mark BakowskiGladiator II: Mark Bakowski Overall VFX Sup. and RidleygramsKingdom of the Planet of the Apes Erik Winquist, Rodney Burke, Paul Story, Stephen UnterfranzOur fxpodcast with Director Wes Ball and VFX Supervisor Erik Winquist:fxpodcast #369: Kingdom Of the Planet of Apes with Director Wes Ball and VFX Supervisor Erik WinquistWickedPablo Helman, Paul Corbould, Jonathan Fawkner, Anthony SmithOur fxpodcast with renowned visual effects supervisor Pablo Helman:Pablo Helman breaks down WickedAnimated FilmFlowGints Siibalodis, Matss KaaInside Out 2 Kelsey Mann, Mark NielsenWallace and Gromit: Vengeance Most FowlNick Park, Merlin Crossingham, Richard BeekThe Wild RobotChris Sanders, Jeff HermannThe awards ceremony will take place on 16 February 2025 at the Royal Festival Hall in London. In addition to the awards, BAFTA is an independent arts charit, supporting the arts.

OUTSTANDING VISUAL EFFECTS IN A PHOTOREAL FEATUREBetter ManLuke MillarAndy TaylorDavid ClaytonKeith HerftPeter StubbsDune: Part TwoPaul LambertBrice ParkerStephen JamesRhys SalcombeGerd NefzerKingdom of the Planet of the ApesErik WinquistJulia NeighlyPaul StoryDanielle ImmermanRodney BurkeMufasa: The Lion KingAdam ValdezBarry St. JohnAudrey FerraraDaniel FotheringhamTwistersBen SnowMark SoperFlorian WitzelSusan GreenhowScott FisherOUTSTANDING SUPPORTING VISUAL EFFECTS IN A PHOTOREAL FEATUREBlitzAndrew WhitehurstSona PakTheo DemirisVincent PoitrasHayley WilliamsCivil WarDavid SimpsonMichelle RoseFreddy SalazarChris ZehJ.D. SchwalmHorizon: An American Saga Chapter 1Jason NeeseArmen FetulagianJamie NeeseJ.P. JaramilloNosferatuAngela BarsonLisa RenneyDavid ScottDave CookPavel SgnerYoung Woman and the SeaRichard BriscoeCarrie RishelJeremy RobertStphane DittooIvo JivkovOUTSTANDING VISUAL EFFECTS IN AN ANIMATED FEATUREInside Out 2Kelsey MannMark NielsenSudeep RangaswamyBill WatralMoana 2Carlos CabralTucker GilmoreIan GoodingGabriela HernandezThe Wild RobotChris SandersJeff HermannJeff BudsbergJacob Hjort JensenTransformers OneFrazer ChurchillFiona ChiltonJosh CooleyStephen KingUltraman: RisingHayden JonesSean M. MurphyShannon TindleMathieu VigOUTSTANDING VISUAL EFFECTS IN A PHOTOREAL EPISODEFallout; The HeadJay WorthAndrea KnollGrant EverettJoao SitaDevin MaggioHouse of the Dragon; Season 2; The Red Dragon and the GoldDai EinarssonTom HortonSven MartinWayne StablesMike DawsonShgun; AnjinMichael CliettMelody MeadPhilip EngstrmEd BruceCameron WaldbauerStar Wars: Skeleton Crew; Episode 5John KnollPablo MollesJhon AlvaradoJeff CapogrecoThe Lord of The Rings: The Rings of Power; Season 2; EldestJason SmithTim KeeneAnn PodloznyAra KhanikianRyan ConderOUTSTANDING SUPPORTING VISUAL EFFECTS IN A PHOTOREAL EPISODEExpats: HomeRobert BockGlorivette SomozaCharles LabbTim EmeisLady in the Lake; It Has to Do With the Search for the MarvelousJay WorthEddie BoninJoe WehmeyerEric Levin-HatzMike MyersMasters of the Air; Part Three; The Regensburg-Schweinfurt MissionStephen RosenbaumBruce FranklinXavier Matia BernasconiDavid AndrewsNeil CorbouldThe Penguin; BlissJohnny HanMichelle RoseGoran PavlesEd BruceDevin MaggioThe Tattooist of Auschwitz; PilotSimon GilesAlan ChurchDavid SchneiderJames HattsmithOUTSTANDING VISUAL EFFECTS IN A REAL-TIME PROJECT[REDACTED]Fabio SilvaMatthew ShermanCaleb EssexBob KopinskyDestiny 2: The Final ShapeDave SamuelBen FabricEric GreenliefGlenn GambleStar Wars OutlawsStephen HawesLionel Le DainBenedikt PodlesniggBogdan DraghiciWhat If? An Immersive StoryPatrick N.P. ConranShereif FattouhZain HomerJax LeeUntil DawnNicholas ChambersJack Hidde GlavimansAlex GaborOUTSTANDING VISUAL EFFECTS IN A COMMERCIALYouTube TV NFL Sunday Ticket: The Magic of SundayChris BayolJeremy BrooksLane JollyJacob BergmanDisney; Holidays 2024Adam DroyHelen TangChristian Baker-SteeleDavid FleetVirgin Media; Walrus WhizzerSebastian CaldwellIan BerryBen CroninAlex GreyCoca-Cola; The HeroesGreg McKneallyAntonia VlastoRyan KnowlesFabrice FiteniSix Kings Slam; Call of the KingsRyan KnowlesJoe BillingtonDean RobinsonGeorge SavvasOUTSTANDING VISUAL EFFECTS IN A SPECIAL VENUE PROJECTD23; Real-Time RocketEvan GoldbergAlyssa FinleyJason BrenemanAlice TaylorThe Goldau Landslide ExperienceRoman KaelinGianluca RavioliFlorian BaumannMTV Video Music Awards; Slim Shady LiveJo PlaeteSara MustafaCameron JacksonAndries CourteauxTokyo DisneySea; Peter Pans Never Land AdventureMichael Sean FoleyKirk BodyfeltDarin HollingsBert KleinMaya VyasParis Olympics Opening Ceremony; RunBenjamin Le SterGilles De LusigmanGerome ViavantRomain TinturierOUTSTANDING CHARACTER IN A PHOTOREAL FEATUREBetter Man; Robbie WilliamsMilton RamirezAndrea MerloSeoungseok Charlie KimEteuati TemaKingdom of the Planet of the Apes; NoaRachael DunkAndrei CovalJohn SoreNiels Peter KaagaardKingdom of the Planet of the Apes; RakaSeoungseok Charlie KimGiorgio LafrattaTim TeramotoAidan MartinMufasa: The Lion King; TakaKlaus SkovboValentina RosselliEli De KoninckAmelie TalarmainOUTSTANDING CHARACTER IN AN ANIMATED FEATUREInside Out 2; AnxietyAlexander AlvaradoBrianne FranciscoAmanda WagnerBrenda Lin ZhangThe Wild Robot; RozFabio LigniniYukinori InagakiOwen DemersHyun HuhThelma The Unicorn; Vic DiamondGuillaume ArantesAdrien MonteroAnne-Claire LerouxGaspard RocheWallace & Gromit: Vengeance Most Fowl; GromitJo FentonAlison EvansAndy SymanowskiEmanuel NevadoOUTSTANDING CHARACTER IN AN EPISODE, COMMERCIAL, GAME CINEMATIC, OR REAL-TIME PROJECTSecret Level; Armored Core: Asset Management; Mech PilotZsolt VidaPter Krucsaignes VonaEnric Nebleza PaellaDiablo IV: Vessel of Hatred; NeyrelleChris BostjanickJames MaYeon-Ho LeeAtsushi IkarashiDisney; Holidays 2024; OctopusAlex DoylePhilippe MoineLewis PickstonAndrea LacedelliRonja the Robbers Daughter; Vildvittran the Queen HarpyNicklas AnderssonDavid AllanGustav hrenNiklas WallnOUTSTANDING ENVIRONMENT IN A PHOTOREAL FEATURECivil War; Washington, D.C.Matthew ChandlerJames HarmerRobert MooreAdrien ZeppieriDune: Part Two; The Arrakeen BasinDaniel RheinDaniel Anton FernandezMarc James AustinChristopher AnciaumeGladiator II; RomeOliver KaneStefano FarciJohn SeruFrederick ValleeWicked; The Emerald CityAlan LamSteve BevinsDeepali NegiMiguel Sanchez Lpez-RuzOUTSTANDING ENVIRONMENT IN AN ANIMATED FEATUREKung Fu Panda 4; Juniper CityBenjamin LippertRyan PrestridgeSarah VawterPeter MaynezThe Wild Robot; The ForestJohn WakeHe Jung ParkWoojin ChoiShane GladingTransformers One; Iacon CityAlex PopescuGeoffrey LebretonRyan KirbyHussein NabeelWallace & Gromit: Vengeance Most Fowl; AqueductMatt PerryDave Alex RiddettMatt SandersHoward JonesOUTSTANDING ENVIRONMENT IN AN EPISODE, COMMERCIAL, GAME CINEMATIC, OR REAL-TIME PROJECTDune: Prophecy; Pilot; The Imperial PalaceScott CoatesSam BesseauVincent lHeureuxLourenco AbreuDune: Prophecy; Two Wolves; Zimia SpaceportNils WeisbrodDavid AnastacioRene BorstRuben ValenteShgun; OsakaManuel MartinezPhil HanniganKeith MaloneFrancesco CorvinoThe Lord of the Rings: The Rings of Power; Season 2; Doomed to Die; EregionYordan PetrovBertrand CabrolLea DesrozierKaran DhandhaOUTSTANDING CG CINEMATOGRAPHYBetter ManBlair BurkeShweta BhatnagarTim WalkerCraig YoungDune: Part Two; ArrakisGreig FraserXin Steve GuoSandra MurtaBen WiggsHouse of the Dragon; Season 2; The Red Dragon and the Gold; Battle at Rooks RestMatt PerrinJames ThompsonJacob DoehnerP.J. DillonKingdom of the Planet of the Apes ; Egg ClimbDennis YooAngelo PerrottaSamantha ErickstadMiae KangOUTSTANDING MODEL IN A PHOTOREAL OR ANIMATED PROJECTAlien: Romulus; Renaissance Space StationWaldemar BartkowiakTrevor WideMatt MiddletonBen ShearmanDeadpool & Wolverine; Ant-Man ArenaCarlos Flores GomezCorinne DyChris ByrnesGerald BlaiseDune: Part Two; The Harkonnen HarvesterAndrew HodgsonTimothy RussellErik LehmannLouie ChoGladiator II; The ColosseumOliver KaneMarnie PittsCharlotte FargierLaurie PriestOUTSTANDING EFFECTS SIMULATIONS IN A PHOTOREAL FEATUREDune: Part Two; Atomic Explosions and WormridingNicholas PapworthSandy la TourelleLisa NolanChristopher PhillipsKingdom of the Planet of the Apes; Burning Village, Rapids and FloodsAlex NowotnyClaude SchitterFrdric ValleurKevin KelmTwistersMatthew HangerJoakim ArnessonLaurent KermelZheng Yong OhVenom: The Last Dance; Water, Fire & Symbiote EffectsXavi Martin RamirezOscar DahlenHedi NamarYuri YangOUTSTANDING EFFECTS SIMULATIONS IN AN ANIMATED FEATUREKung Fu Panda 4Jinguang HuangZhao WangHamid ShahsavariJoshua LaBrotMoana 2Zoran StojanoskiJesse EricksonShamintha Kalamba ArachchiErin V. RamosThe Wild RobotDerek CheungMichael LosureDavid ChowNyoung KimUltraman: RisingGoncalo CabacaZheng Yong OhNicholas Yoon Joo KuangPraveen BoppanaOUTSTANDING EFFECTS SIMULATIONS IN AN EPISODE, COMMERCIAL, GAME CINEMATIC, OR REAL-TIME PROJECTAvatar: The Last Airbender; Legends; KoizillaIoan BoieriuDavid StopfordPer BalaySaysana RintharamyShgun; Broken to the Fist; LandslideDominic TiedekenHeinrich LweCharles GuertonTimmy LundinStar Wars: Skeleton Crew; Pilot; Spaceship Hillside TakeoffTravis HarkleroadXiaolong PengMarcella BrownMickael RiciottiThe Lord of the Rings: The Rings of Power; Season 2; Shadow and Flame; Balrog Fire and Collapsing CliffKoenraad HofmeesterMiguel Perez SenentMiguel Santana Da SilvaBilly CopleyThree Body Problem; Judgement DayYves DIncauGavin TemplerMartin ChabannesEloi Andaluz FullOUTSTANDING COMPOSITING & LIGHTING IN A FEATUREBetter ManMark McNichollGordon Spencer de HasethEva SnyderMarkus ReithofferDune: Part Two; Wormriding, Geidi Prime, and the Final BattleChristopher RickardFrancesco DellAnnaPaul ChapmanRyan WingKingdom of the Planet of the ApesJoerg BruemmerZachary BrakeTim WalkerKaustubh A. PatilThe Wild RobotSondra L. VerlanderBaptiste Van OpstalEszter OffertalerAustin CasaleOUTSTANDING COMPOSITING & LIGHTING IN AN EPISODEShgun; Broken to the Fist; LandslideBenjamin BernonDouglas RoshamnVictor KirschCharlie RaudStar Wars: Skeleton Crew; Episode 6; JawsRich GrandeTomas LefebvreIan DodmanRey ReynoldsThe Boys; Season 4; Life Among the SepticsTristan ZerafaMike StadnyckyjToshi KosakaRajeev BRThe Penguin; After HoursJonas StuckenbrockKaren ChangEugene BondarMiky GirnOUTSTANDING COMPOSITING & LIGHTING IN A COMMERCIALVirgin Media; Walrus WhizzerSebastian CaldwellAlex GreyKanishk ChouhanShubham MehtaCoca-Cola; The HeroesRyan KnowlesAlex GabucciJack PowellDan YarcigiCorcept; MarionetteYongchan KimArman MatinYoon BaeRajesh KaushikDisney; Holidays 2024Christian Baker-SteeleLuke WarpusPritesh KotianJack HarrisOUTSTANDING SPECIAL (PRACTICAL) EFFECTS IN A PHOTOREAL PROJECTBlitzHayley WilliamsDavid EvesAlex FreemanDavid WatsonConstellationMartin GoeresJohara RaukampLion David BogusLeon MarkThe Penguin; Safe GunsDevin MaggioJohnny HanCory CandrilliAlexandre ProdhommeEMERGING TECHNOLOGY AWARDDune: Part Two; Nuke CopyCatBen KentGuillaume GalesMairead GroganJohanna BarbierFuriosa: A Mad Max Saga; Artist-driven Machine Learning CharacterJohn BastianBen WardThomas RowntreeRobert BeveridgeHere; Neural Performance ToolsetJo PlaeteOriel FrigoTomas KoutskyMatteo Oliviero DancyMufasa: The Lion King; Real-Time Interactive Filmmaking, From Stage To PostCallum JamesJames HoodLloyd BishopBruno PedrinhaThe Penguin; Phase Synced Flash-Gun SystemJohnny HanJefferson HanJoseph MenafraMichael PynnOUTSTANDING VISUAL EFFECTS IN A STUDENT PROJECTDawn (entry from ESMA cole Suprieure Des Mtiers Artistiques)Noah MercierApolline RoyerLorys StoraMarie PradeillesStudent Accomplice (entry from Brigham Young University)Spencer BlanchardLisa BirdAnson SavageKiara SpencerPittura (entry from ARTFX Schools of Digital Arts)Lauriol AdamLassre TitouanVivenza RmiMarre HellosCourage (entry from Supinfocom Rubika)Salom CognonMargot JacquetNathan BaudryLise Delcroix

The much-anticipated sequel to Ridley Scotts iconic Gladiator, Gladiator II promised to transport audiences back to the grandeur of ancient Rome, balancing epic scale with emotional storytelling via superb VFX. At the heart of this ambitious endeavor is the visual effects team, led by Mark Bakowski, Overall VFX Supervisor from Industrial Light & Magic (ILM). With a legacy of crafting unforgettable cinematic worlds, ILM took on the monumental task of recreating the visceral authenticity and historical depth that made the original film so beloved. ILM was aided by Framestore, who was also a major contributor. Framestore delivered 136 carefully crafted shots, including the armoured rhino,12 bloodthirsty baboons and a hauntingly stylized River Styx environment.The wildfires have torn through the Los Angeles area this week, and our hearts go out to everyone affected; the devastation has been horrendous. It has also led to numerous closures, cancellations and postponements including the Oscar Bakeoff nominations. The traditional VFX bakeoff was originally scheduled for Jan. 11th, but the event will now be done virtually. Additionally, the announcement of nominees for the 97th Academy Awards has been delayed 2 days until Jan. 19, with nominations voting extended to Jan. 14. As part of our week of Bakeoff coverage, we spoke to Mark Bakowski in fire-ravaged LA, prior to him flying back to northern California.RidleygramsRidleygrams are Ridley Scotts iconic hand-drawn storyboards, which he uses as a creative tool to visualize and communicate his vision for a film. These sketches are a hallmark of Scotts filmmaking process, reflecting his background in art and design. While not overly detailed, Ridleygrams capture the mood, composition, and framing of key scenes, offering a dynamic and impressionistic blueprint for the film.Ridleygrams from Ridleys Instagram accountAs any VFX supervisor will testify, one of the most distinctive aspects of working with Scott is his use of Ridleygrams. Ridleys sense of perspective and composition is incredible, said Bakowski. I actually just got a book from him about a week ago- a leather-bound book of all his Ridleygrams from the movie, they beautifully track his vision from concept to the final shots. Scotts approach is often spontaneous, drawing inspiration from the environment. Whats amazing is how spontaneous his creativity can be, he explains. Hell spot something on the way to Setmist on the hills in Malta, for exampleand doodle on top of that to say, This is our Rome shot. His Ridleygrams arent just planning tools; they are an extension of how he thinks visually.Scott often sketches these directly on set or during pre-production to guide the crew, especially the cinematographer, production designers, and VFX crew, to ensure everyone clearly understands his creative intent. Their simplicity and immediacy make them a practical and flexible tool for collaboration, helping bridge the gap between abstract concepts and tangible cinematic execution.Ridleys sketches naturally convey depth and perspective, and the director is deeply focused on layering contrast and composition in his imagery. Hell dress a scene with incredible attention to detaileven down to positioning stunt performers based on their look, and who has the most character.That depth-building extends through his multi-camera setups. Our job is to translate his vision into something that feels both epic and authentic, ensuring that every layer of the frame contributes to the illusion of a lived-in world.(Sidenote: There is an upcoming art & making of Gladiator II from @abramsbooks featuring Ridleygrams, to be published in March 2025.)Numidia AttackSet 16 years after the death of Marcus Aurelius, Ridley Scotts Gladiator II begins with an unforgettable naval assault on the city of Numidia. This sequence perfectly encapsulates the ambitious visual effects approach of the film. Shot in the arid desert of Morocco, the scene utilized the Jerusalem set from Scotts Kingdom of Heaven, repurposed and adapted to evoke the grandeur of Numidia. To create the illusion of a Roman fleet engaging in battle, two 150-foot-long practical ships were mounted on transporter rigs by the Special Effects (SFX) team, allowing for dynamic on-set movements. These ships were later completed digitally, with the surrounding ocean and dramatic skies crafted entirely in post-production. Smoke, fire, explosions, and a hail of arrows added layers of intensity, while Ridley Scotts ability to art direct the ocean ensured the sequence met his exacting vision.Final shot combining dry for wet, sky replacement and built on vast practical setsThe battle culminates in a striking scene where Lucius, the films hero, finds himself at the mythical River Styx. This sequence by Framestore, combined practical and digital elements seamlessly. A small beach set was constructed on a soundstage, complemented by digital environment extensions, including a mesmerizing liquid-metal mercury simulation for the rivers supernatural qualities. When Lucius awakens on a practical beach shot in Numidia, the wider and reverse angles relied on footage captured in Malta. These disparate locations were unified in post with digital dressing and seamless transitions between the varied environments.ColosseumRome itself became a character in the film, its monumental architecture and vibrant streets brought to life through a combination of practical sets and digital augmentation. The lower sections of the Roman sets were built practically in Malta, while expansive vistas and upper architectural elements were added digitally by ILM. Despite the grandeur of the Roman scenes, extras on set never exceeded 500, necessitating extensive VFX crowd work. The Colosseum, a centerpiece of the original Gladiator, was revisited multiple times throughout the 1,130 visual effects shots in the new film, blending practical builds with complex digital enhancements to recreate its epic majesty. Ridley doesnt like to overcommit to a plan too far in advance, Bakowski explained. He thrives on flexibilityshooting with multiple cameras and finding the moment as it happens. For us, it meant being ready to pivot at any time. A prime example of this adaptability came during the sequence depicting a naval battle in the Coliseum. Initially planned as a mix of wet and dry shooting, the sequence was disrupted by the actors strike, leaving the team to complete it entirely dry on set. By working closely with the stunts team and leveraging post-production VFX, ILM seamlessly transformed the footage into a believable, high-stakes naval battle.As a result, this battle became one of the most technically demanding sequences in the Colosseum. Shot predominantly on dry land, it required extensive CG water, mast and sail extensions, and integration of long, uninterrupted takes captured from up to 12 cameras. The productions limited use of blue screens presented unique challenges, requiring heroic feats of paint, rotoscoping, and tracking to integrate the live-action footage with CG elements seamlessly. This approach had both advantages and drawbacksoffering more natural on-set lighting and interaction but demanding a Herculean effort from the paint and roto team.Ridley Scott has a natural sense of perspective and depth, comments Bakowski. He understands the depth of a scene. He often jokingly talks about how he invented smoke in movies in terms of depth layering and so on. As the Director loves to build contrast and composition in the way he constructs his images, he will individually dress to camera each of his multiple cameras when shooting. Often hell shoot with eight cameras as a regular thing, maybe 10, or 12. He will dress each camera by the foreground .. saying Okay, I want that stunt man whos got the bigger muscles, that guy has got the nice big nose, hes got character, et cetera, and hell build his scene back, in depth, into the frame. CreaturesIn addition to large-scale environments, the film also featured an array of CG creatures, from sharks and tigers to birds, horses, and even a rhino. One of the standout achievements was the creation of a full-sized white rhino rig, mounted on wheels and radio-controlled for practical interaction and lighting reference. VFX artists then replaced the rig with a fully digital rhino, whose detailed musculature, thick layers of fat, and sliding skin conveyed a sense of weight and momentum. Similarly, Ridley Scotts fascination with a nature documentary featuring a baboon with alopecia inspired the creation of a unique, digitally crafted baboon that became a pivotal character in the story.Final Army ConfrontationThe films climactic finale, set on the outskirts of Rome, showcased the VFX teams ability to unify diverse elements. Split between locations in Malta and the UK, the sequence involved digital extensions to blend the two settings, the addition of armies on both sides of the conflict, and a dramatic horse crash that required intricate CG work. As the culmination of the films 1,130 VFX shots, the finale exemplified the marriage of practical and digital techniques that defined Gladiator II. Through the collaboration of Ridley Scott, Mark Bakowski, and the VFX teams, the film not only honored the legacy of its predecessor but also elevated the art of visual effects in historical epics.

Civil War takes audiences into a fractured America, exploring themes of division and unity against a reimagined Washington, D.C. The VFX approach focused on photorealism and narrative integration. Framestores David Simpson, as Production VFX Supervisor, collaborated closely with director Alex Garland, DOP Rob Hardy, and Production Designer Caty Maxey to achieve the films gritty, documentary-style aesthetic. The challenge went beyond the scale of the VFXit was about crafting a city that felt alive and in conflict. Framestores ability to push technical boundaries while preserving emotional depth makes Civil War a standout in this years VFX-driven films.Everything had to feel grounded and lived in, says Simpson. Anything remotely Hollywood was immediately kicked into touch, and we focused instead on news and documentary footage. It made the research and reference-gathering stage pretty heavy going at times, but the aim was to create a realistic and utterly unsanitized view of war unfolding. Framestores key aim was to augment and extend the real-life action while enhancing those aspects that would not be safe or practical to accomplish on set or out on location. The first rule was that, wherever possible, everything should be captured in camera, says Simpson.Framestore digitally build Washington DCThe visual effects for Civil War were a monumental achievement, delivered by a dedicated team of 175 artists at Framestore over the course of 406 days. The scope of their work was staggering, involving the meticulous digital recreation of Washington, D.C., for the films intricate and immersive storytelling.Washington DC: Street by streetGarland, Simpson and Hardy conducted recces of Washington DC to gauge the city and inform plans to find locations in Atlanta that might double for the US capital. With no suitable stand-ins found, partial sets were constructed and the VFX team were charged with building out the environments. In those scenes involving close-quarters clashes, youre seeing a blend of CG and practical sets, says Simpson. Everything above the ground floor of those buildings has been built in CG.The team brought to life 13 miles of the city, complete with 75 iconic landmarks, such as the Capitol and Washington Monument, to provide an authentic and recognizable backdrop. This ambitious endeavor required not only a deep understanding of the citys geography but also an exceptional level of detail to ensure the audience felt fully immersed in the environment. In addition to its landmarks, the digital cityscape included 887 miles of road, 3,736 buildings, and a host of smaller yet essential details. The artists modelled 64,191 street lamps, 1,160 traffic lights, and 17,851 trees to populate the urban environment, making it vibrant and believable. The interiors were just as meticulously crafted, with over half a million pieces of office furniture (519,066 to be precise) designed to add depth to the films narrative settings. This level of detail exemplifies Framestores commitment to crafting visual effects that serve the story while pushing the boundaries of what is possible in digital artistry. The sheer scale and precision of their work set a new benchmark in VFX, showcasing the power of technology and creativity to transport audiences into a meticulously crafted world. In keeping with the brief to create a living, breathing, immersive world for Civil Wars action, the Framestore team went into incredible detail for these environment builds. I was walking home through London one evening, and the citys sheer lack of uniformity struck me, says Simpson. You notice how the offices are lit differently, the fractional changes in design from road to road and individual architectural quirks that break up any given street scene. This is what we sought to tap into: the fractional changes in lighting, building out the interiors of the offices so they werent just hollow CG shells but dotted with desk clutter, pot plants and air conditioning units. Your eye doesnt necessarily register all this detail, but your mind does, and it heightens both the believability of the VFX work and the storytelling itself since you get a sense of the citys sudden, Mary Celeste-esque abandonment. War on the streetsThe success of these showcase moments was such that the VFX work expanded ambitiously outwards to the point where Framestore had effectively built a fully CG Washington DC. The city was then dotted with gunfire, digital crowds, flames and columns of smoke to highlight the skirmishes and clashes happening at points around the city. This work helped give a sense of scope and expanse, amplifying the story by highlighting how the drama extended far beyond what was happening to the films main cast. Rendering the whole city in CG also had some more practical creative benefits, as Simpson explains: building Washington ourselves meant we could achieve shots that simply wouldnt be possible or practical in real life, he says. The US Secret Service are obviously somewhat cagey about people flying helicopters close to the White House, for example if we wanted to do that, wed need an armed agent onboard, and theres no way we could have gotten as close as we did. Theres also the issue of the Lincoln Memorial, which, for practical and ethical reasons, we couldnt blow up!If the photoreal cityscapes and internal design of office blocks added to the worldbuilding, so, too, did the finer details. Everything was based on real-life footage, explains Simpson. We had de facto casting sessions for our explosions, using newsreels, citizen journalism and footage from weapons tests. We also needed to know what kind of damage these explosions would do, to streets, to buildings and, most harrowingly, to people. The aim was to strip away any sense of showiness, rendering the reality of war in all its stark, horrifying detail. Debuting at SXSW, Civil War was hailed as one of the years most startling and visceral films. Framestore was an early collaborator, identifying and deploying the best techniques, technologies and methodologies to achieve Director Alex Garlands distinctive and uncompromising vision and delivering some 1,000 VFX shots via its studios in London and Mumbai.

As part of our ongoing coverage of films in the lead-up to the Oscar Bake-off on January 11, we highlight the VFX of Barry Jenkins Lion King prequel Mufasa: The Lion King. MPC, a Technicolor Group company, has a long history of bringing to life unforgettable characters and crafting classic worlds, balancing animation with VFX. From The Jungle Book to Maleficent and The Lion King, MPCs has helped contribute to many new chapters in VFX and cinematic expression. This year, MPCs team brought Disneys African savannah to life in Mufasa: The Lion King. The film was directed by Barry Jenkins, the Production VFX Supervisor was Adam Valdez, and Animation Supervisor was Daniel Fotheringham. MPCs VFX Supervisor was Audrey Ferrara, and VFX Producer was Georgie Duncan. A team of over 1,700 artists, production crew, and technologists at MPC crafted the VFX for Mufasa: The Lion King. To create a blueprint for our final animation our motion capture shoot involved multiple performers playing Mufasa, Sarabi, Taka, Rafiki and even Zazu says Production VFX Supervisor Adam Valdez. They wore motion capture suits, and through a process we call QuadCap, their movements were mapped onto digital lion characters. This technology aligned the performers head and spine movements to the lions head and neck, their legs to the lions front legs, and simulated the lions back legs and hips to follow. Barry could then watch a live feed of the lions on screen through Unreal Engine, allowing him to give real-time performance and camera notes to the actors and DP. Within Unreal Engine, a total of 12680 on-stage takes were shot using the VCam and Motion Capture systems, all of which produced both a recorded and rendered artifact. If you were to play all captured takes one after the other, it would take just under 200 hours, or just over 8 days, to watch them all. A total of 7399 live motion capture and Quad Cap performances were captured throughout the shoot.We added facial expressions and lip sync to enhance characters performances. says Animation Supervisor Dan Fotheringham, then Barry could walk through the recorded sequence in VR making notes before we could wrap it up to be shot virtually. Performances with complex animal mechanics, like fighting or leaping were then integrated into the Quadcap performances and into the virtual sets, creating a complete master scene that Barry and James could shoot from any angle. This innovative blending of live-action filmmaking techniques and visual effects became a defining feature of the entire production. Building Africas Wild MajestyTo authentically recreate the African savannah, MPCs Environment team embarked on scouting trips across the continent, gathering invaluable references for the films flora, fauna, and landscapes. Armed with photogrammetry scans and painstaking hand-sculpting techniques, the team meticulously built the world of Mufasa, crafting plains, canyons, and forests down to the finest detail, including individual rocks and blades of grass.A crucial step in the process was optimizing the rendering of the vast environments. To handle the scale of these huge environments, the team had to develop new tools to increase efficiency. The landscapes became integral to telling Mufasas journey, serving as much a geographic as a spiritual backdrop. The result is a sprawling digital recreation of Africa spanning 107 square milesthe size of Salt Lake City, Utah. Custom scattering tools were used to populate rivers, trees, and plants in ways that mimicked the complexity of natural ecosystems. These breathtaking environments serve as both a stage and a character, guiding Mufasa on his epic journey. Breathing Life Into the Animal KingdomMPCs acclaimed Character Lab took the lead in bringing over 118 unique animals to life, including beloved characters like Mufasa, Scar, Pumbaa, Timon, and Rafiki. Each character was constructed from the ground up, beginning with an anatomically accurate bone and muscle structure. From there, the team used their proprietary grooming system, Loma, to create lifelike fur with unparalleled detail and realism.The challenge with fur is not just making it look realistic, but ensuring it moves and reacts naturally, says MPCs Character Supervisor. This was achieved through a combination of advanced simulation techniques and meticulous fine-tuning. Each lion had over 30,000,000 hairs to achieve the realistic look of fur. Mufasas mane alone had 16,995,454 hair curves. Mufasa has 600,000 hairs on his ears, 6.2 million hairs on his legs, and 9 million hairs covering the middle portion of his body. Simulating realistic lion manes for the assembled loins required 40,000 80,000 dynamic curves per character, with custom presets for different weather and physical conditions. Long shots took up to a week per iteration, with final fur caches exceeding 800 GB.To capture the emotional subtleties of the characters, animators studied hours of real animal footage. Muscle movement, posture, and even subtle shifts in expression were analyzed and replicated to ensure authenticity. Animators often acted out expressions themselves, using their performances to infuse each character with genuine emotion. This hybrid of research and personal creativity resulted in characters that feel as lifelike and emotionally resonant as their real-world counterparts. This shot of Rafiki making a snow angel required simulating over 620 million snow particles. Dynamic Elements: Simulating Natures ForcesMPCs FX team brought the dynamic forces of nature into the mix, simulating wind, rain, snow, and fire to create a fully immersive world. The FX work was key to grounding the characters in their environment, says Ferrara. Whether it was the golden light filtering through the savannah or a storm rolling across the plains, every element was designed to integrate into the photoreal aesthetic. CG lighters and compositors worked meticulously to perfect the films lighting and mood, ensuring every shot radiated authenticity. Pushing Boundaries in Animation and VFXA team of up to 88 artists across London, Montreal, and Bengaluru brought to life 77 digital sets, including the iconic Pride Rock and new locations Mountains of the Moon and the Tree of Life. Artists built a library of 5,790 assets, including trees, plants, and grass species, which are all featured in the film. The storage requirements for the film reached 25 petabytes which is the equivalent storage of 5.6 million DVDs. Rendering the film in final quality took 150M hours. It would take a single computer 17,123 years to complete. The fully digital world brims with depth, vivid detail, and a cinematic scale that does justice to the legacy of the original film. From its sweeping landscapes to its intricately animated characters, MPCs work on Mufasa: The Lion King represents another achievement in visual 3D animated storytelling.

In this episode, we dive into the extraordinary VFX of Better Man.Also check out our interview with the films director: Michael GraceyDirector Michael Gracey & making Better Manand also our interview with the team at Wt FX.fxpodcast: Better Man with Wt FXDont forget to subscribe to both the VFXShow and the fxpodcast to get both of our most popular podcasts.This week in our Boy Band lineup is:Matt Wallin * @mattwallin www.mattwallin.com.Follow Matt on Mastodon: @[emailprotected]Jason Diamond @jasondiamond www.thediamondbros.comMike Seymour @mikeseymour. www.fxguide.com. + @mikeseymourSpecial thanks to Matt Wallin for the editing & production of the show with help from Jim Shen.

The merging of two iconic characters, Deadpool and Wolverine, into a single film created one of the most anticipated cinematic events in 2024. Fans of the X-Men universe were eager to see how the sardonic, irreverent Wade Wilson (Deadpool) would collideboth literally and metaphoricallywith Logans gruff, brooding Wolverine. Bringing this explosive dynamic to life required a complex level of artistry, and at the forefront of this task was the visual effects powerhouse Framestore.No strangers to either the MCU or the merc with the mouth, Framestores creatives brought skill, flair and high-octane action to this hotly-anticipated box office smash. Work included the ambitious oner in which Deadpool and Wolverine cut a bloody swathe through the rampaging Deadpool Corps; Cassandras skin-crawling telekinetic powers and CG augmentation to the beloved Dogpool. In addition to final VFX and animation, Framestore Pre-Production Services (FPS) delivered the entirety of the films previs work, led by Visualisation Supervisor Kaya Jabar.Framestore provided pre-production servicespreviz, on-set support, techviz, and postvizto final VFX. Overseen by VFX Supervisors Matt Twyford (Loki), Robert Allman, Arek Komorowski, and Joo Sita, the VFX team delivered 420 supremely complex shots, building on the groundwork laid by Framestores Pre-Production team (FPS), led by Senior Visualisation Supervisor Kaya Jabar. The FPS team was the films sole pre-production services collaborator, delivering 900+ shots. The VFX team contributed to several key sequences, including the brutally funny opening title and the gripping third act. This involved executing the cameo-filled Deadpool corp and Oner sequences and orchestrating the climactic destruction of the Time Ripper machine, animating Dogpools performance, creating dozens of digi-doubles, building an expansive urban environment, and delivering a plethora of VFX, ranging from a hand passing through Paradoxs head, gallons of blood simulations, plasma energy, and Framestores signature spaghettification FX. Deadpool & Wolverine was directed by Shawn Levy from a screenplay he wrote with Ryan Reynolds, Rhett Reese, Paul Wernick, and Zeb Wells. The Production Visual Effects Supervisor was Swen Gillbergand, and the Visual Effects Producer was Lisa Marra. As part of our ongoing coverage of films in the lead-up to the Oscar Bake-off on January 11, we spoke with Framestores London Visual Effects Supervisor Matt Twyford.In our fxguide breakdown, Matt Twyford dived into two of the films most standout VFX moments: the surreal fingers through the face sequence and the scene-stealing CGI enhancements for Peggy, the films ugliest-yet-most-adorable dog. Both moments showcased Framestores ability to merge technical precision with artistic flair, creating visuals that were not only technically complex but also deeply connected to the films story and characters.The Fingers Through the Face SequenceIn VFX shot that felt utterly unprecedented, the scene where Cassandras hand penetrates a characters face was a defining moment in Deadpool & Wolverine,. According to Framestores VFX Supervisor Matt Twyford, the sequence was always envisioned as a visceral, photorealistic effect.Our only reference was a single comic book frame, Twyford explained. It was just enough to give us the creative direction we neededfingers intersecting through the skin but not the bone, interacting with facial orifices like the mouth and eye sockets. The challenge was making this look completely real on a fully performing actor. The team began by building an ultra-high-resolution digital double of the actor using a Clear Angle scan rig, capturing every detail down to individual pores. The system has over a hundred lights instead of just a single flash, youve now got the controlled light direction, Twyford explains. So its a 180 frame different light angle, light burst, which allows you then to get all the normals and extract the normal mats from the skin down to poor level Twyford commented that it was very easy to work with Clear Angle Studios. Weve got a close link with them. They fed back to us, we fed back to them, but the quality of the material was stunning. Our first models were just absolutely amazing for the faces.But the real magic lay in animating the interaction between the hand and the facial skin. Framestore decided to move much of the skin distortion work from simulation into animation, allowing the team to preview results earlier in the production process and ensure client confidence.We didnt want to wait until the back end to show results, Twyford noted. By animating the skin distortion early on, we could present rough renders to the client quickly, gaining approval on the gross motion before adding finer details like tension maps and subsurface effects.The final result? A mesmerizing blend of realism and stylization, where skin stretched and reacted with unsettling believability. Subtle details, like hemoglobin redistribution based on skin tension, added to the illusion. It was a balance between anatomical accuracy and Marvel-esque visual logic, Twyford said. The goal was to make it visually stunning without breaking the audiences immersion.Peggy: The Scene-Stealing Dogpool CanineOn the lighter side of the film, Peggya real-life dog and proud titleholder of the UKs ugliest dogstole the show. Framestore worked extensively with Peggy on set, capturing her unique look and mannerisms, including her perpetually hanging tongue, to ensure authenticity in her digital double.Peggy performed brilliantly on set, Twyford said. She did the stunts, the jumps, she worked with blue screens and even handled pyro effects like a pro. She was fantastic. While 90% of Dogpool was live-action, for certain sequences, such as adding goggles and enhancing her expressions, the team relied on her digital counterpart. The VFX team designed and rendered Dogpools goggles late in production, adding a playful yet functional element to her character. Using Framestores proprietary renderer, Freak, they achieved realistic fur interactions and magnified reflections in the goggles, all while maintaining Peggys signature look. The goggle idea actually only came really quite late on, probably less than two months before delivery, he recalls. There was a little discussion about, lets magnify her eyes, lets have that slightly googly eyeglasses effect. And because we are using the physics-based render, we had to do that using the thickness of the glass and the refractive index, which actually proved to be, as you can imagine, very difficult to control, but it is all through the renderer. The goggles allowed us to amplify her personality, Twyford explained. Frmestore kept her eyes true to her natural appearance but gave them life with subtle animations, letting her emotionally connect with the audience in key moments. Crafting Iconic MomentsFor Framestore, Deadpool & Wolverine was a perfect platform to showcase the teams ability to blend creativity and cutting-edge technology. While the film was filled with massive set pieces and intricate effects, it was the smaller, character-driven momentslike Cassandras surreal power display and Peggys charming anticsthat stood out.As Twyford put it, What Framestore loves doing, what we love doing, is the different stuff. Thats what we put ourselves forward for. And because thats what our artists love, they all demand the tricky stuff and the hard stuff. In the end, it was difficult and hard and very complex, but it was also very Marvel!Framestore actually has four films shortlisted for the 2025 Best Visual Effects Oscar: Wicked, Civil War, Deadpool & Wolverine and Gladiator II. These films showcase everything from world-dominating fantasy, epic character animation, blockbuster superhero action and gritty, documentary-style realism, these projects highlight the breadth of Framestores creative and technological skills. Wicked, Deadpool & Wolverine, Civil War and Gladiator II all be presented at the bake-off stage on January 11, 2025. The five final nominations will be announced on January 17. Framestores upcoming slate of projects includesHow To Train Your Dragon, Wicked pt. 2, The Wheel Of Time s3, Bridget Jones: Mad About The Boy, The Gorge, F1 and Three Bags Full.

As part of our ongoing coverage of films in the lead-up to the Oscar Bake-off on January 11, 2025, we talk to Paul Lambert, the films Oscar-winning Visual Effects Supervisor, about the incredible epic masterpiece: Dune Part Two.Dune Part Two: Following the destruction of House Atreides by House Harkonnen, Paul Atreides unites with Chani and the Fremen while seeking revenge against the conspirators who destroyed his family. Facing a choice between the love of his life and the universes fate, he must prevent a terrible future only he can foresee.Director Denis Villeneuve with Timothe Chalamet on setDirector Denis Villeneuve with DOP Greig FraserDune Part Two was directed and produced by Denis Villeneuve, who co-wrote the screenplay with Jon Spaihts. Paul Lambert was the production VFX Supervisor and he joins the fxpodcast this week to discuss the film in depth.Director Denis Villeneuve with Rebecca Ferguson on setDNEG led the visual effects, along with several other companies such as RodeoFX, Territory Studio, Wylie Co. and ReDefine. Australian cinematographer Greig Fraser was the DOP. As Paul discusses in the fxpodcast, the film builds on the Dune Part One, which garnered ten nominations at the 94th Academy Awards, including Best Picture, and went on to win a leading six awards for Best Original Score, Best Sound, Best Cinematography, Best Production Design, Best Film Editing, and of course: Best Visual Effects.As we discuss, DOP Greig Fraser shot the grand fight that occurs early on in the film as black-and-white infrared. He used an Alexa LF camera that had been modified and then VFX matched to that.

In the second part of ourBetter Man coverage, we speak with Wt FXs VFX supervisor, Luke Millar and animation supervisor, Dave Clayton. This is part of our ongoing coverage of films in the lead-up to the Oscar Bake-off on January 11, 2025. The five final nominations will be announced on January 17.Original on set footageThe transition from on set to finalThe finished frameBetter Man is an independent film about the life of UK Rock star Robbie Williams. Wt was not only responsible for the incredible animation of Robbie as a monkey throughout the film, but as Director Michael Gracey explained in last weeks Part One fxpodcast, they were key to getting the film made and green kit in the first place.Creature pass with the digital groomRobbie Williams actual eyes were scanned and digitally combinedThe final render and comp. of the closing shot of the filmOne of the most complex scenes was the 500-person Regent St Rock DJ Dance sequence, which nearly did not happen, as the team explains in this episode of the fxpodcast.As shot on the actual streets of LondonDigital RobbieThe final shotPlus:listen to the fxpodcast to hear how Wt FXs VFX supervisor, Luke Millar ended up as a digital extra 767 times in the film!

Better Man is a 2024 bio-musical film co-written, produced and directed by Michael Gracey, based on the life of British pop singer Robbie Williams. We spoke with Michael to discuss the film, its complexity and challenges and how he approached this innovative and powerful independent film.In this epsiode we discus the Regent Street sequence, above is just the start of that sequence, and we have an even more detailed breakdown coming, later this week, when we will post our fxpodcast interview with Wt FXs VFX supervisor, Luke Millar and animation supervisor, Dave Clayton. Better Man is part of our VFX Bakeoff series in the lead up to the Oscar Nomination voting in January.

Dive behind the emerald curtain in our latest fxpodcast episode as we explore the VFX and making of WICKED (Part1). We talk with renowned visual effects supervisor Pablo Helman, whose groundbreaking work brings the enchanting world of Oz to life. From reimagining iconic characters to creating dazzling, immersive landscapes, Helman reveals the creative challenges and innovative techniques that transformed this beloved musical into a cinematic spectacle.Pablo was the visual effects supervisor. The lead visual effects house was ILM along with Framestore. In this episode, he discusses his approach and the complexity of doing a musical and gives an insight into the filmmaking process of director Jon M. Chu.

In this episode, we dive into the extraordinary visual effects of Universal Pictures Wicked, directed by Jon M. Chu. As a prequel to The Wizard of Oz, the film not only tells the origin story of Elphaba and Glindatwo witches whose lives take drastically different pathsbut also transports audiences to a vividly reimagined Oz.Join us as we discuss the VFX that brings Ozs animals, spellbinding magic, and the stunning world of Shiz University to life. We break down the challenges of creating the films effects for pivotal scenes, such as the gravity-defying flight sequences and the Wizards grand, mechanical illusions. Plus, we discuss how the visual effects team balanced fantastical elements with the emotional core of the story, ensuring the magic of Oz feels both epic and personal.In this VFXShow, we discuss and review the film, but later this week, we will also post our interview with Wickeds VFX supervisor, Pablo Helman.Dont forget to subscribe to both the VFXShow and the fxpodcast to get both of our most popular podcasts.This week in OZ:Matt Lion Wallin * @mattwallin www.mattwallin.com.Follow Matt on Mastodon: @[emailprotected]Jason Scarecrow Diamond @jasondiamond www.thediamondbros.comMike Tin Man Seymour @mikeseymour. www.fxguide.com. + @mikeseymourSpecial thanks to Matt Wallin for the editing & production of the show with help from Jim Shen.

AsChief Product Officer, Grant Farhall is responsible for Getty Images overall product strategy and vision. We sat down with Grant to discuss the issue of training data, rights and Getty Images strong approach.Training dataArtificial Intelligence, specifically the subset of generative AI, has captured the imagination and attention of all aspects of media and entertainment. Recent rapid advances seem to humanize AI in a way that has caught the imagination of so many people. It has been born from the nexus of new machine learning approaches, foundational models, and, in particular, advanced GPU-accelerated computing, all combined with impressive advances in neural networks and data science.One aspect of generative AI that is often too quickly passed over is the nature and quality of training data. It can sometimes be wrongly assumed that in every instance, more data is good any data, just more of it. Actually, there is a real skill in curating training data.Owning your ownGenerative AI is not limited to just large corporations or research labs. It is possible to build on a foundation model and customize it for your application without having your own massive AI factory or data centre.It is also possible to create a Generative AI model that works only on your own training data. Getty Images does exactly this with its iStock, Getty Creative Images, and API stock libraries. These models are trained on only the high-quality images approved for use, using NVIDIAs Edify NIM built on Picasso.NVIDIA developed the underlying architecture. Gettys model is not a fine-tuned version of a foundational model. It is only trained on our content, so it is a foundational model in and of itself Grant Farhall, Getty ImagesGetty produces a mix of women when prompted with Woman CEO, closeup.BiasPeople sometimes speak of biases in training data, and this is a real issue, but data scientists also know that carefully curating training data is an important skill. This is not an issue of manipulating data but rather providing the right balance in the training data to produce the most accurate results. As part of the curation process is getting enough data of the types needed and often with metadata that helps the deep learning algorithms.Particularly the nature of what data exists in the world already and the qualities of that data that can be used to make the most effective generative AI tool. At first glance, one might assume you just want the greatest amount of ground truth or perfect examples possible, but that is not how things actually work in practice.It is also key that the output responses to prompts provide a fair and equitable mix, especially when dealing with people. Stereotypes can be reinforced without attention to output bias.ProvenanceIt is important to know if the data used to build the generative AI model was licensed and approved for this use. Many early academic research efforts scraped the Internet for data since their work was non-commercial and experimental. We have since come a long way in understanding, respecting, and protecting the rights of artists and people in general, and we have to protect their work from being used without permission. As you can hear in this espisode of the podcast, companies such as Getty Images pride themselves on having clean and ethically sourced generative AI models that are free from compromise and artist exploitation. In fact, they offer not only compensation for artists whose work is used as training data but also guarantees, in some cases, indemnifies against any possible future issues over artists rights.The question that is often asked is, Can I use these images from your AI generator in a commercial way, in a commercial setting? Most services will say yes, says Grant Frarhall of Getty Images. The better question is, can I use these images commercially, and what level of legal protection are you offering me if I do? As Getty knows the provenance of every image used to train their model, their corporate customers enjoy fully uncapped legal indemnification.Furthermore, misuse is impossible if the content is not in the training model. Frarhall points out, There are no pictures of Taylor Swift, Travis Kelsey, athletes, musicians, logos, brands, or any similar stuff. None of thats included in the training set, so it cant be inappropriately generated.AI Generator imageRights & CopyrightFor centuries, artists have consciously or subconsciously drawn inspiration from one another to influence their work. However, with the rise of generative AI, it is crucial to respect the rights associated with the use of creative materials.A common issue and concern is copyright and this is an important area, but it is one open to further clarification and interpretation as governments around the world respond to this new technology. As it stands, only a person can own copyright, it is not possible for a non-human to own copyright. It is unclear how open the law is to training on material without explicit permission worldwide, as Generative AI models do not store a copy of the original.However, it is illegal in most contexts to pass off any material in a way that misrepresents, such as implying or stating the work was created by someone who did not. It is also illegal to use the likeness of someone to sell or promote something without their permission, regardless of how that image was created. The laws in each country or territory need to be clarified, but, as a rule of thumb, Generative AI should restricted by an extension of existing laws such as defamation, exploitation, and privacy rights. These laws can come into play if the AI-generated content is harmful or infringing on someones rights.In addition, there are ongoing discussions about the need for new laws or regulations specifically addressing the unique issues raised by AI, such as the question of who can be held responsible for violations using AI-generated content. It is important to note that just because a generative piece of art or music is stated as being approved for commercial use, that does not imply that the training data used to build the model was licensed and respected all contributing artists appropriately.Generative AIThis fxpodcast is not sponsored, but is based on research done for the new Field Guide to Generative AI. fxguides Mike Seymour was commissioned by NVIDIA to unpack the impact of generative AI on the media and entertainment industries, offering practical applications, ethical considerations, and a roadmap for the future.The Field Guide is free and can be downloaded here: Field Guide to Generative AI. In M&E, generative AI has proven itself a powerful tool for boosting productivity and creative exploration. But it is not a magic button that does everything. Its a companion, not a replacement. AI lacks the empathy, cultural intuition, and nuanced understanding of a storys uniqueness that only humans bring to the table. But when generative AI is paired with VFX artists and TDs, it can accelerate pipelines and unlock new creative opportunities.