• NVIDIA Scores Consecutive Win for End-to-End Autonomous Driving Grand Challenge at CVPR

    NVIDIA was today named an Autonomous Grand Challenge winner at the Computer Vision and Pattern Recognitionconference, held this week in Nashville, Tennessee. The announcement was made at the Embodied Intelligence for Autonomous Systems on the Horizon Workshop.
    This marks the second consecutive year that NVIDIA’s topped the leaderboard in the End-to-End Driving at Scale category and the third year in a row winning an Autonomous Grand Challenge award at CVPR.
    The theme of this year’s challenge was “Towards Generalizable Embodied Systems” — based on NAVSIM v2, a data-driven, nonreactive autonomous vehiclesimulation framework.
    The challenge offered researchers the opportunity to explore ways to handle unexpected situations, beyond using only real-world human driving data, to accelerate the development of smarter, safer AVs.
    Generating Safe and Adaptive Driving Trajectories
    Participants of the challenge were tasked with generating driving trajectories from multi-sensor data in a semi-reactive simulation, where the ego vehicle’s plan is fixed at the start, but background traffic changes dynamically.
    Submissions were evaluated using the Extended Predictive Driver Model Score, which measures safety, comfort, compliance and generalization across real-world and synthetic scenarios — pushing the boundaries of robust and generalizable autonomous driving research.
    The NVIDIA AV Applied Research Team’s key innovation was the Generalized Trajectory Scoringmethod, which generates a variety of trajectories and progressively filters out the best one.
    GTRS model architecture showing a unified system for generating and scoring diverse driving trajectories using diffusion- and vocabulary-based trajectories.
    GTRS introduces a combination of coarse sets of trajectories covering a wide range of situations and fine-grained trajectories for safety-critical situations, created using a diffusion policy conditioned on the environment. GTRS then uses a transformer decoder distilled from perception-dependent metrics, focusing on safety, comfort and traffic rule compliance. This decoder progressively filters out the most promising trajectory candidates by capturing subtle but critical differences between similar trajectories.
    This system has proved to generalize well to a wide range of scenarios, achieving state-of-the-art results on challenging benchmarks and enabling robust, adaptive trajectory selection in diverse and challenging driving conditions.

    NVIDIA Automotive Research at CVPR 
    More than 60 NVIDIA papers were accepted for CVPR 2025, spanning automotive, healthcare, robotics and more.
    In automotive, NVIDIA researchers are advancing physical AI with innovation in perception, planning and data generation. This year, three NVIDIA papers were nominated for the Best Paper Award: FoundationStereo, Zero-Shot Monocular Scene Flow and Difix3D+.
    The NVIDIA papers listed below showcase breakthroughs in stereo depth estimation, monocular motion understanding, 3D reconstruction, closed-loop planning, vision-language modeling and generative simulation — all critical to building safer, more generalizable AVs:

    Diffusion Renderer: Neural Inverse and Forward Rendering With Video Diffusion ModelsFoundationStereo: Zero-Shot Stereo MatchingZero-Shot Monocular Scene Flow Estimation in the WildDifix3D+: Improving 3D Reconstructions With Single-Step Diffusion Models3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting
    Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models
    Zero-Shot 4D Lidar Panoptic Segmentation
    NVILA: Efficient Frontier Visual Language Models
    RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models
    OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving With Counterfactual Reasoning

    Explore automotive workshops and tutorials at CVPR, including:

    Workshop on Data-Driven Autonomous Driving Simulation, featuring Marco Pavone, senior director of AV research at NVIDIA, and Sanja Fidler, vice president of AI research at NVIDIA
    Workshop on Autonomous Driving, featuring Laura Leal-Taixe, senior research manager at NVIDIA
    Workshop on Open-World 3D Scene Understanding with Foundation Models, featuring Leal-Taixe
    Safe Artificial Intelligence for All Domains, featuring Jose Alvarez, director of AV applied research at NVIDIA
    Workshop on Foundation Models for V2X-Based Cooperative Autonomous Driving, featuring Pavone and Leal-Taixe
    Workshop on Multi-Agent Embodied Intelligent Systems Meet Generative AI Era, featuring Pavone
    LatinX in CV Workshop, featuring Leal-Taixe
    Workshop on Exploring the Next Generation of Data, featuring Alvarez
    Full-Stack, GPU-Based Acceleration of Deep Learning and Foundation Models, led by NVIDIA
    Continuous Data Cycle via Foundation Models, led by NVIDIA
    Distillation of Foundation Models for Autonomous Driving, led by NVIDIA

    Explore the NVIDIA research papers to be presented at CVPR and watch the NVIDIA GTC Paris keynote from NVIDIA founder and CEO Jensen Huang.
    Learn more about NVIDIA Research, a global team of hundreds of scientists and engineers focused on topics including AI, computer graphics, computer vision, self-driving cars and robotics.
    The featured image above shows how an autonomous vehicle adapts its trajectory to navigate an urban environment with dynamic traffic using the GTRS model.
    #nvidia #scores #consecutive #win #endtoend
    NVIDIA Scores Consecutive Win for End-to-End Autonomous Driving Grand Challenge at CVPR
    NVIDIA was today named an Autonomous Grand Challenge winner at the Computer Vision and Pattern Recognitionconference, held this week in Nashville, Tennessee. The announcement was made at the Embodied Intelligence for Autonomous Systems on the Horizon Workshop. This marks the second consecutive year that NVIDIA’s topped the leaderboard in the End-to-End Driving at Scale category and the third year in a row winning an Autonomous Grand Challenge award at CVPR. The theme of this year’s challenge was “Towards Generalizable Embodied Systems” — based on NAVSIM v2, a data-driven, nonreactive autonomous vehiclesimulation framework. The challenge offered researchers the opportunity to explore ways to handle unexpected situations, beyond using only real-world human driving data, to accelerate the development of smarter, safer AVs. Generating Safe and Adaptive Driving Trajectories Participants of the challenge were tasked with generating driving trajectories from multi-sensor data in a semi-reactive simulation, where the ego vehicle’s plan is fixed at the start, but background traffic changes dynamically. Submissions were evaluated using the Extended Predictive Driver Model Score, which measures safety, comfort, compliance and generalization across real-world and synthetic scenarios — pushing the boundaries of robust and generalizable autonomous driving research. The NVIDIA AV Applied Research Team’s key innovation was the Generalized Trajectory Scoringmethod, which generates a variety of trajectories and progressively filters out the best one. GTRS model architecture showing a unified system for generating and scoring diverse driving trajectories using diffusion- and vocabulary-based trajectories. GTRS introduces a combination of coarse sets of trajectories covering a wide range of situations and fine-grained trajectories for safety-critical situations, created using a diffusion policy conditioned on the environment. GTRS then uses a transformer decoder distilled from perception-dependent metrics, focusing on safety, comfort and traffic rule compliance. This decoder progressively filters out the most promising trajectory candidates by capturing subtle but critical differences between similar trajectories. This system has proved to generalize well to a wide range of scenarios, achieving state-of-the-art results on challenging benchmarks and enabling robust, adaptive trajectory selection in diverse and challenging driving conditions. NVIDIA Automotive Research at CVPR  More than 60 NVIDIA papers were accepted for CVPR 2025, spanning automotive, healthcare, robotics and more. In automotive, NVIDIA researchers are advancing physical AI with innovation in perception, planning and data generation. This year, three NVIDIA papers were nominated for the Best Paper Award: FoundationStereo, Zero-Shot Monocular Scene Flow and Difix3D+. The NVIDIA papers listed below showcase breakthroughs in stereo depth estimation, monocular motion understanding, 3D reconstruction, closed-loop planning, vision-language modeling and generative simulation — all critical to building safer, more generalizable AVs: Diffusion Renderer: Neural Inverse and Forward Rendering With Video Diffusion ModelsFoundationStereo: Zero-Shot Stereo MatchingZero-Shot Monocular Scene Flow Estimation in the WildDifix3D+: Improving 3D Reconstructions With Single-Step Diffusion Models3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models Zero-Shot 4D Lidar Panoptic Segmentation NVILA: Efficient Frontier Visual Language Models RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving With Counterfactual Reasoning Explore automotive workshops and tutorials at CVPR, including: Workshop on Data-Driven Autonomous Driving Simulation, featuring Marco Pavone, senior director of AV research at NVIDIA, and Sanja Fidler, vice president of AI research at NVIDIA Workshop on Autonomous Driving, featuring Laura Leal-Taixe, senior research manager at NVIDIA Workshop on Open-World 3D Scene Understanding with Foundation Models, featuring Leal-Taixe Safe Artificial Intelligence for All Domains, featuring Jose Alvarez, director of AV applied research at NVIDIA Workshop on Foundation Models for V2X-Based Cooperative Autonomous Driving, featuring Pavone and Leal-Taixe Workshop on Multi-Agent Embodied Intelligent Systems Meet Generative AI Era, featuring Pavone LatinX in CV Workshop, featuring Leal-Taixe Workshop on Exploring the Next Generation of Data, featuring Alvarez Full-Stack, GPU-Based Acceleration of Deep Learning and Foundation Models, led by NVIDIA Continuous Data Cycle via Foundation Models, led by NVIDIA Distillation of Foundation Models for Autonomous Driving, led by NVIDIA Explore the NVIDIA research papers to be presented at CVPR and watch the NVIDIA GTC Paris keynote from NVIDIA founder and CEO Jensen Huang. Learn more about NVIDIA Research, a global team of hundreds of scientists and engineers focused on topics including AI, computer graphics, computer vision, self-driving cars and robotics. The featured image above shows how an autonomous vehicle adapts its trajectory to navigate an urban environment with dynamic traffic using the GTRS model. #nvidia #scores #consecutive #win #endtoend
    BLOGS.NVIDIA.COM
    NVIDIA Scores Consecutive Win for End-to-End Autonomous Driving Grand Challenge at CVPR
    NVIDIA was today named an Autonomous Grand Challenge winner at the Computer Vision and Pattern Recognition (CVPR) conference, held this week in Nashville, Tennessee. The announcement was made at the Embodied Intelligence for Autonomous Systems on the Horizon Workshop. This marks the second consecutive year that NVIDIA’s topped the leaderboard in the End-to-End Driving at Scale category and the third year in a row winning an Autonomous Grand Challenge award at CVPR. The theme of this year’s challenge was “Towards Generalizable Embodied Systems” — based on NAVSIM v2, a data-driven, nonreactive autonomous vehicle (AV) simulation framework. The challenge offered researchers the opportunity to explore ways to handle unexpected situations, beyond using only real-world human driving data, to accelerate the development of smarter, safer AVs. Generating Safe and Adaptive Driving Trajectories Participants of the challenge were tasked with generating driving trajectories from multi-sensor data in a semi-reactive simulation, where the ego vehicle’s plan is fixed at the start, but background traffic changes dynamically. Submissions were evaluated using the Extended Predictive Driver Model Score, which measures safety, comfort, compliance and generalization across real-world and synthetic scenarios — pushing the boundaries of robust and generalizable autonomous driving research. The NVIDIA AV Applied Research Team’s key innovation was the Generalized Trajectory Scoring (GTRS) method, which generates a variety of trajectories and progressively filters out the best one. GTRS model architecture showing a unified system for generating and scoring diverse driving trajectories using diffusion- and vocabulary-based trajectories. GTRS introduces a combination of coarse sets of trajectories covering a wide range of situations and fine-grained trajectories for safety-critical situations, created using a diffusion policy conditioned on the environment. GTRS then uses a transformer decoder distilled from perception-dependent metrics, focusing on safety, comfort and traffic rule compliance. This decoder progressively filters out the most promising trajectory candidates by capturing subtle but critical differences between similar trajectories. This system has proved to generalize well to a wide range of scenarios, achieving state-of-the-art results on challenging benchmarks and enabling robust, adaptive trajectory selection in diverse and challenging driving conditions. NVIDIA Automotive Research at CVPR  More than 60 NVIDIA papers were accepted for CVPR 2025, spanning automotive, healthcare, robotics and more. In automotive, NVIDIA researchers are advancing physical AI with innovation in perception, planning and data generation. This year, three NVIDIA papers were nominated for the Best Paper Award: FoundationStereo, Zero-Shot Monocular Scene Flow and Difix3D+. The NVIDIA papers listed below showcase breakthroughs in stereo depth estimation, monocular motion understanding, 3D reconstruction, closed-loop planning, vision-language modeling and generative simulation — all critical to building safer, more generalizable AVs: Diffusion Renderer: Neural Inverse and Forward Rendering With Video Diffusion Models (Read more in this blog.) FoundationStereo: Zero-Shot Stereo Matching (Best Paper nominee) Zero-Shot Monocular Scene Flow Estimation in the Wild (Best Paper nominee) Difix3D+: Improving 3D Reconstructions With Single-Step Diffusion Models (Best Paper nominee) 3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models Zero-Shot 4D Lidar Panoptic Segmentation NVILA: Efficient Frontier Visual Language Models RADIO Amplified: Improved Baselines for Agglomerative Vision Foundation Models OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving With Counterfactual Reasoning Explore automotive workshops and tutorials at CVPR, including: Workshop on Data-Driven Autonomous Driving Simulation, featuring Marco Pavone, senior director of AV research at NVIDIA, and Sanja Fidler, vice president of AI research at NVIDIA Workshop on Autonomous Driving, featuring Laura Leal-Taixe, senior research manager at NVIDIA Workshop on Open-World 3D Scene Understanding with Foundation Models, featuring Leal-Taixe Safe Artificial Intelligence for All Domains, featuring Jose Alvarez, director of AV applied research at NVIDIA Workshop on Foundation Models for V2X-Based Cooperative Autonomous Driving, featuring Pavone and Leal-Taixe Workshop on Multi-Agent Embodied Intelligent Systems Meet Generative AI Era, featuring Pavone LatinX in CV Workshop, featuring Leal-Taixe Workshop on Exploring the Next Generation of Data, featuring Alvarez Full-Stack, GPU-Based Acceleration of Deep Learning and Foundation Models, led by NVIDIA Continuous Data Cycle via Foundation Models, led by NVIDIA Distillation of Foundation Models for Autonomous Driving, led by NVIDIA Explore the NVIDIA research papers to be presented at CVPR and watch the NVIDIA GTC Paris keynote from NVIDIA founder and CEO Jensen Huang. Learn more about NVIDIA Research, a global team of hundreds of scientists and engineers focused on topics including AI, computer graphics, computer vision, self-driving cars and robotics. The featured image above shows how an autonomous vehicle adapts its trajectory to navigate an urban environment with dynamic traffic using the GTRS model.
    Like
    Love
    Wow
    Angry
    27
    0 Comentários 0 Compartilhamentos
  • Introducing the GEEKDeck: the revolutionary step in gaming that answers the age-old question: "What if I could enjoy my favorite games without the annoyance of an actual screen?" Yes, ladies and gentlemen, say goodbye to portability and hello to a glorified, screenless brick that you can proudly display in your living room. Because who needs to enjoy immersive graphics when you can just admire the solid, unyielding form of your new paperweight? The Steam Deck’s only flaw was its ability to be played on the go, and GEEKDeck has lovingly eradicated that issue. Finally, a device that truly understands the essence of sitting still and doing absolutely nothing!

    #GEEKDeck #SteamDeck #GamingRevolution #ScreenlessGaming #
    Introducing the GEEKDeck: the revolutionary step in gaming that answers the age-old question: "What if I could enjoy my favorite games without the annoyance of an actual screen?" Yes, ladies and gentlemen, say goodbye to portability and hello to a glorified, screenless brick that you can proudly display in your living room. Because who needs to enjoy immersive graphics when you can just admire the solid, unyielding form of your new paperweight? The Steam Deck’s only flaw was its ability to be played on the go, and GEEKDeck has lovingly eradicated that issue. Finally, a device that truly understands the essence of sitting still and doing absolutely nothing! #GEEKDeck #SteamDeck #GamingRevolution #ScreenlessGaming #
    HACKADAY.COM
    GEEKDeck is a SteamDeck for Your Living Room
    You know what the worst thing about the Steam Deck is? Being able to play your games on the go. Wouldn’t it be better if it was a screenless brick …read more
    1 Comentários 0 Compartilhamentos
  • Get The BioShock And Mafia Trilogies For Just $18 In This New Deal

    If you're craving some FPS gaming this summer, you'll want to check out Humble's latest bundle deal, the 2K Classic Trilogies Mafia X Bioshock Game Bundle. The deal lets you grab each mainline entry in the BioShock and Mafia series on PC for just Like other Humble Bundle deals, the company donates a portion of proceeds to charity--in this case, the bundle supports Covenant House, which provides food, shelter, immediate crisis care, and ongoing services to homeless and trafficked young people. You can also adjust the revenue split between Humble, 2K, and Covenant House before checkout. See bundle at Humble Humble's 2K Classic Trilogies Mafia X Bioshock Game Bundle offers a tiered payment option, and the more you pay, the more games you get.If you only want the Bioshock series, you can grab the base tier that includes the Remastered Editions of BioShock 1 and 2, alongside the original BioShock Infinite. The enhanced editions of Bioshock 1 and 2 included in this bundle offer improved graphics and UI, with support for up to 4K resolutions. It's also worth noting that the version of Bioshock Infinite included in the bundle does not include the Season Pass DLC content, and must be purchased separately.Continue Reading at GameSpot
    #get #bioshock #mafia #trilogies #just
    Get The BioShock And Mafia Trilogies For Just $18 In This New Deal
    If you're craving some FPS gaming this summer, you'll want to check out Humble's latest bundle deal, the 2K Classic Trilogies Mafia X Bioshock Game Bundle. The deal lets you grab each mainline entry in the BioShock and Mafia series on PC for just Like other Humble Bundle deals, the company donates a portion of proceeds to charity--in this case, the bundle supports Covenant House, which provides food, shelter, immediate crisis care, and ongoing services to homeless and trafficked young people. You can also adjust the revenue split between Humble, 2K, and Covenant House before checkout. See bundle at Humble Humble's 2K Classic Trilogies Mafia X Bioshock Game Bundle offers a tiered payment option, and the more you pay, the more games you get.If you only want the Bioshock series, you can grab the base tier that includes the Remastered Editions of BioShock 1 and 2, alongside the original BioShock Infinite. The enhanced editions of Bioshock 1 and 2 included in this bundle offer improved graphics and UI, with support for up to 4K resolutions. It's also worth noting that the version of Bioshock Infinite included in the bundle does not include the Season Pass DLC content, and must be purchased separately.Continue Reading at GameSpot #get #bioshock #mafia #trilogies #just
    WWW.GAMESPOT.COM
    Get The BioShock And Mafia Trilogies For Just $18 In This New Deal
    If you're craving some FPS gaming this summer, you'll want to check out Humble's latest bundle deal, the 2K Classic Trilogies Mafia X Bioshock Game Bundle. The deal lets you grab each mainline entry in the BioShock and Mafia series on PC for just $18. Like other Humble Bundle deals, the company donates a portion of proceeds to charity--in this case, the bundle supports Covenant House, which provides food, shelter, immediate crisis care, and ongoing services to homeless and trafficked young people. You can also adjust the revenue split between Humble, 2K, and Covenant House before checkout. See bundle at Humble Humble's 2K Classic Trilogies Mafia X Bioshock Game Bundle offers a tiered payment option, and the more you pay, the more games you get.If you only want the Bioshock series, you can grab the base $10 tier that includes the Remastered Editions of BioShock 1 and 2, alongside the original BioShock Infinite. The enhanced editions of Bioshock 1 and 2 included in this bundle offer improved graphics and UI, with support for up to 4K resolutions. It's also worth noting that the version of Bioshock Infinite included in the bundle does not include the Season Pass DLC content, and must be purchased separately.Continue Reading at GameSpot
    Like
    Love
    Wow
    Angry
    Sad
    34
    0 Comentários 0 Compartilhamentos
  • So, Aggro Crab and Landfall have cracked the code to success with "Co-op Climbing: Hit Peak," selling 2 million copies for less than $200,000. Who knew that the secret sauce was a pinch of Korean barbecue mixed with the power of friendship? I mean, forget about innovative gameplay or stunning graphics; it’s all about grilling meat and sharing laughs, right? Maybe next time I should host a barbecue instead of working on my game designs. Clearly, the magic happens when you add a side of bulgogi! If only my life choices came with such a tasty recipe for success.

    #CoopClimbing #GamingSuccess #KoreanBarbecue #PowerOfFriendship #IndieGames
    So, Aggro Crab and Landfall have cracked the code to success with "Co-op Climbing: Hit Peak," selling 2 million copies for less than $200,000. Who knew that the secret sauce was a pinch of Korean barbecue mixed with the power of friendship? I mean, forget about innovative gameplay or stunning graphics; it’s all about grilling meat and sharing laughs, right? Maybe next time I should host a barbecue instead of working on my game designs. Clearly, the magic happens when you add a side of bulgogi! If only my life choices came with such a tasty recipe for success. #CoopClimbing #GamingSuccess #KoreanBarbecue #PowerOfFriendship #IndieGames
    How co-op climbing hit Peak achieved 2 million sales for less than $200,000
    The secret behind Aggro Crab and Landfall's latest hit? Korean barbecue and the power of friendship.
    1 Comentários 0 Compartilhamentos
  • Startup Uses NVIDIA RTX-Powered Generative AI to Make Coolers, Cooler

    Mark Theriault founded the startup FITY envisioning a line of clever cooling products: cold drink holders that come with freezable pucks to keep beverages cold for longer without the mess of ice. The entrepreneur started with 3D prints of products in his basement, building one unit at a time, before eventually scaling to mass production.
    Founding a consumer product company from scratch was a tall order for a single person. Going from preliminary sketches to production-ready designs was a major challenge. To bring his creative vision to life, Theriault relied on AI and his NVIDIA GeForce RTX-equipped system. For him, AI isn’t just a tool — it’s an entire pipeline to help him accomplish his goals. about his workflow below.
    Plus, GeForce RTX 5050 laptops start arriving today at retailers worldwide, from GeForce RTX 5050 Laptop GPUs feature 2,560 NVIDIA Blackwell CUDA cores, fifth-generation AI Tensor Cores, fourth-generation RT Cores, a ninth-generation NVENC encoder and a sixth-generation NVDEC decoder.
    In addition, NVIDIA’s Plug and Play: Project G-Assist Plug-In Hackathon — running virtually through Wednesday, July 16 — invites developers to explore AI and build custom G-Assist plug-ins for a chance to win prizes. the date for the G-Assist Plug-In webinar on Wednesday, July 9, from 10-11 a.m. PT, to learn more about Project G-Assist capabilities and fundamentals, and to participate in a live Q&A session.
    From Concept to Completion
    To create his standout products, Theriault tinkers with potential FITY Flex cooler designs with traditional methods, from sketch to computer-aided design to rapid prototyping, until he finds the right vision. A unique aspect of the FITY Flex design is that it can be customized with fun, popular shoe charms.
    For packaging design inspiration, Theriault uses his preferred text-to-image generative AI model for prototyping, Stable Diffusion XL — which runs 60% faster with the NVIDIA TensorRT software development kit — using the modular, node-based interface ComfyUI.
    ComfyUI gives users granular control over every step of the generation process — prompting, sampling, model loading, image conditioning and post-processing. It’s ideal for advanced users like Theriault who want to customize how images are generated.
    Theriault’s uses of AI result in a complete computer graphics-based ad campaign. Image courtesy of FITY.
    NVIDIA and GeForce RTX GPUs based on the NVIDIA Blackwell architecture include fifth-generation Tensor Cores designed to accelerate AI and deep learning workloads. These GPUs work with CUDA optimizations in PyTorch to seamlessly accelerate ComfyUI, reducing generation time on FLUX.1-dev, an image generation model from Black Forest Labs, from two minutes per image on the Mac M3 Ultra to about four seconds on the GeForce RTX 5090 desktop GPU.
    ComfyUI can also add ControlNets — AI models that help control image generation — that Theriault uses for tasks like guiding human poses, setting compositions via depth mapping and converting scribbles to images.
    Theriault even creates his own fine-tuned models to keep his style consistent. He used low-rank adaptationmodels — small, efficient adapters into specific layers of the network — enabling hyper-customized generation with minimal compute cost.
    LoRA models allow Theriault to ideate on visuals quickly. Image courtesy of FITY.
    “Over the last few months, I’ve been shifting from AI-assisted computer graphics renders to fully AI-generated product imagery using a custom Flux LoRA I trained in house. My RTX 4080 SUPER GPU has been essential for getting the performance I need to train and iterate quickly.” – Mark Theriault, founder of FITY 

    Theriault also taps into generative AI to create marketing assets like FITY Flex product packaging. He uses FLUX.1, which excels at generating legible text within images, addressing a common challenge in text-to-image models.
    Though FLUX.1 models can typically consume over 23GB of VRAM, NVIDIA has collaborated with Black Forest Labs to help reduce the size of these models using quantization — a technique that reduces model size while maintaining quality. The models were then accelerated with TensorRT, which provides an up to 2x speedup over PyTorch.
    To simplify using these models in ComfyUI, NVIDIA created the FLUX.1 NIM microservice, a containerized version of FLUX.1 that can be loaded in ComfyUI and enables FP4 quantization and TensorRT support. Combined, the models come down to just over 11GB of VRAM, and performance improves by 2.5x.
    Theriault uses the Blender Cycles app to render out final files. For 3D workflows, NVIDIA offers the AI Blueprint for 3D-guided generative AI to ease the positioning and composition of 3D images, so anyone interested in this method can quickly get started.
    Photorealistic renders. Image courtesy of FITY.
    Finally, Theriault uses large language models to generate marketing copy — tailored for search engine optimization, tone and storytelling — as well as to complete his patent and provisional applications, work that usually costs thousands of dollars in legal fees and considerable time.
    Generative AI helps Theriault create promotional materials like the above. Image courtesy of FITY.
    “As a one-man band with a ton of content to generate, having on-the-fly generation capabilities for my product designs really helps speed things up.” – Mark Theriault, founder of FITY

    Every texture, every word, every photo, every accessory was a micro-decision, Theriault said. AI helped him survive the “death by a thousand cuts” that can stall solo startup founders, he added.
    Each week, the RTX AI Garage blog series features community-driven AI innovations and content for those looking to learn more about NVIDIA NIM microservices and AI Blueprints, as well as building AI agents, creative workflows, digital humans, productivity apps and more on AI PCs and workstations. 
    Plug in to NVIDIA AI PC on Facebook, Instagram, TikTok and X — and stay informed by subscribing to the RTX AI PC newsletter.
    Follow NVIDIA Workstation on LinkedIn and X. 
    See notice regarding software product information.
    #startup #uses #nvidia #rtxpowered #generative
    Startup Uses NVIDIA RTX-Powered Generative AI to Make Coolers, Cooler
    Mark Theriault founded the startup FITY envisioning a line of clever cooling products: cold drink holders that come with freezable pucks to keep beverages cold for longer without the mess of ice. The entrepreneur started with 3D prints of products in his basement, building one unit at a time, before eventually scaling to mass production. Founding a consumer product company from scratch was a tall order for a single person. Going from preliminary sketches to production-ready designs was a major challenge. To bring his creative vision to life, Theriault relied on AI and his NVIDIA GeForce RTX-equipped system. For him, AI isn’t just a tool — it’s an entire pipeline to help him accomplish his goals. about his workflow below. Plus, GeForce RTX 5050 laptops start arriving today at retailers worldwide, from GeForce RTX 5050 Laptop GPUs feature 2,560 NVIDIA Blackwell CUDA cores, fifth-generation AI Tensor Cores, fourth-generation RT Cores, a ninth-generation NVENC encoder and a sixth-generation NVDEC decoder. In addition, NVIDIA’s Plug and Play: Project G-Assist Plug-In Hackathon — running virtually through Wednesday, July 16 — invites developers to explore AI and build custom G-Assist plug-ins for a chance to win prizes. the date for the G-Assist Plug-In webinar on Wednesday, July 9, from 10-11 a.m. PT, to learn more about Project G-Assist capabilities and fundamentals, and to participate in a live Q&A session. From Concept to Completion To create his standout products, Theriault tinkers with potential FITY Flex cooler designs with traditional methods, from sketch to computer-aided design to rapid prototyping, until he finds the right vision. A unique aspect of the FITY Flex design is that it can be customized with fun, popular shoe charms. For packaging design inspiration, Theriault uses his preferred text-to-image generative AI model for prototyping, Stable Diffusion XL — which runs 60% faster with the NVIDIA TensorRT software development kit — using the modular, node-based interface ComfyUI. ComfyUI gives users granular control over every step of the generation process — prompting, sampling, model loading, image conditioning and post-processing. It’s ideal for advanced users like Theriault who want to customize how images are generated. Theriault’s uses of AI result in a complete computer graphics-based ad campaign. Image courtesy of FITY. NVIDIA and GeForce RTX GPUs based on the NVIDIA Blackwell architecture include fifth-generation Tensor Cores designed to accelerate AI and deep learning workloads. These GPUs work with CUDA optimizations in PyTorch to seamlessly accelerate ComfyUI, reducing generation time on FLUX.1-dev, an image generation model from Black Forest Labs, from two minutes per image on the Mac M3 Ultra to about four seconds on the GeForce RTX 5090 desktop GPU. ComfyUI can also add ControlNets — AI models that help control image generation — that Theriault uses for tasks like guiding human poses, setting compositions via depth mapping and converting scribbles to images. Theriault even creates his own fine-tuned models to keep his style consistent. He used low-rank adaptationmodels — small, efficient adapters into specific layers of the network — enabling hyper-customized generation with minimal compute cost. LoRA models allow Theriault to ideate on visuals quickly. Image courtesy of FITY. “Over the last few months, I’ve been shifting from AI-assisted computer graphics renders to fully AI-generated product imagery using a custom Flux LoRA I trained in house. My RTX 4080 SUPER GPU has been essential for getting the performance I need to train and iterate quickly.” – Mark Theriault, founder of FITY  Theriault also taps into generative AI to create marketing assets like FITY Flex product packaging. He uses FLUX.1, which excels at generating legible text within images, addressing a common challenge in text-to-image models. Though FLUX.1 models can typically consume over 23GB of VRAM, NVIDIA has collaborated with Black Forest Labs to help reduce the size of these models using quantization — a technique that reduces model size while maintaining quality. The models were then accelerated with TensorRT, which provides an up to 2x speedup over PyTorch. To simplify using these models in ComfyUI, NVIDIA created the FLUX.1 NIM microservice, a containerized version of FLUX.1 that can be loaded in ComfyUI and enables FP4 quantization and TensorRT support. Combined, the models come down to just over 11GB of VRAM, and performance improves by 2.5x. Theriault uses the Blender Cycles app to render out final files. For 3D workflows, NVIDIA offers the AI Blueprint for 3D-guided generative AI to ease the positioning and composition of 3D images, so anyone interested in this method can quickly get started. Photorealistic renders. Image courtesy of FITY. Finally, Theriault uses large language models to generate marketing copy — tailored for search engine optimization, tone and storytelling — as well as to complete his patent and provisional applications, work that usually costs thousands of dollars in legal fees and considerable time. Generative AI helps Theriault create promotional materials like the above. Image courtesy of FITY. “As a one-man band with a ton of content to generate, having on-the-fly generation capabilities for my product designs really helps speed things up.” – Mark Theriault, founder of FITY Every texture, every word, every photo, every accessory was a micro-decision, Theriault said. AI helped him survive the “death by a thousand cuts” that can stall solo startup founders, he added. Each week, the RTX AI Garage blog series features community-driven AI innovations and content for those looking to learn more about NVIDIA NIM microservices and AI Blueprints, as well as building AI agents, creative workflows, digital humans, productivity apps and more on AI PCs and workstations.  Plug in to NVIDIA AI PC on Facebook, Instagram, TikTok and X — and stay informed by subscribing to the RTX AI PC newsletter. Follow NVIDIA Workstation on LinkedIn and X.  See notice regarding software product information. #startup #uses #nvidia #rtxpowered #generative
    BLOGS.NVIDIA.COM
    Startup Uses NVIDIA RTX-Powered Generative AI to Make Coolers, Cooler
    Mark Theriault founded the startup FITY envisioning a line of clever cooling products: cold drink holders that come with freezable pucks to keep beverages cold for longer without the mess of ice. The entrepreneur started with 3D prints of products in his basement, building one unit at a time, before eventually scaling to mass production. Founding a consumer product company from scratch was a tall order for a single person. Going from preliminary sketches to production-ready designs was a major challenge. To bring his creative vision to life, Theriault relied on AI and his NVIDIA GeForce RTX-equipped system. For him, AI isn’t just a tool — it’s an entire pipeline to help him accomplish his goals. Read more about his workflow below. Plus, GeForce RTX 5050 laptops start arriving today at retailers worldwide, from $999. GeForce RTX 5050 Laptop GPUs feature 2,560 NVIDIA Blackwell CUDA cores, fifth-generation AI Tensor Cores, fourth-generation RT Cores, a ninth-generation NVENC encoder and a sixth-generation NVDEC decoder. In addition, NVIDIA’s Plug and Play: Project G-Assist Plug-In Hackathon — running virtually through Wednesday, July 16 — invites developers to explore AI and build custom G-Assist plug-ins for a chance to win prizes. Save the date for the G-Assist Plug-In webinar on Wednesday, July 9, from 10-11 a.m. PT, to learn more about Project G-Assist capabilities and fundamentals, and to participate in a live Q&A session. From Concept to Completion To create his standout products, Theriault tinkers with potential FITY Flex cooler designs with traditional methods, from sketch to computer-aided design to rapid prototyping, until he finds the right vision. A unique aspect of the FITY Flex design is that it can be customized with fun, popular shoe charms. For packaging design inspiration, Theriault uses his preferred text-to-image generative AI model for prototyping, Stable Diffusion XL — which runs 60% faster with the NVIDIA TensorRT software development kit — using the modular, node-based interface ComfyUI. ComfyUI gives users granular control over every step of the generation process — prompting, sampling, model loading, image conditioning and post-processing. It’s ideal for advanced users like Theriault who want to customize how images are generated. Theriault’s uses of AI result in a complete computer graphics-based ad campaign. Image courtesy of FITY. NVIDIA and GeForce RTX GPUs based on the NVIDIA Blackwell architecture include fifth-generation Tensor Cores designed to accelerate AI and deep learning workloads. These GPUs work with CUDA optimizations in PyTorch to seamlessly accelerate ComfyUI, reducing generation time on FLUX.1-dev, an image generation model from Black Forest Labs, from two minutes per image on the Mac M3 Ultra to about four seconds on the GeForce RTX 5090 desktop GPU. ComfyUI can also add ControlNets — AI models that help control image generation — that Theriault uses for tasks like guiding human poses, setting compositions via depth mapping and converting scribbles to images. Theriault even creates his own fine-tuned models to keep his style consistent. He used low-rank adaptation (LoRA) models — small, efficient adapters into specific layers of the network — enabling hyper-customized generation with minimal compute cost. LoRA models allow Theriault to ideate on visuals quickly. Image courtesy of FITY. “Over the last few months, I’ve been shifting from AI-assisted computer graphics renders to fully AI-generated product imagery using a custom Flux LoRA I trained in house. My RTX 4080 SUPER GPU has been essential for getting the performance I need to train and iterate quickly.” – Mark Theriault, founder of FITY  Theriault also taps into generative AI to create marketing assets like FITY Flex product packaging. He uses FLUX.1, which excels at generating legible text within images, addressing a common challenge in text-to-image models. Though FLUX.1 models can typically consume over 23GB of VRAM, NVIDIA has collaborated with Black Forest Labs to help reduce the size of these models using quantization — a technique that reduces model size while maintaining quality. The models were then accelerated with TensorRT, which provides an up to 2x speedup over PyTorch. To simplify using these models in ComfyUI, NVIDIA created the FLUX.1 NIM microservice, a containerized version of FLUX.1 that can be loaded in ComfyUI and enables FP4 quantization and TensorRT support. Combined, the models come down to just over 11GB of VRAM, and performance improves by 2.5x. Theriault uses the Blender Cycles app to render out final files. For 3D workflows, NVIDIA offers the AI Blueprint for 3D-guided generative AI to ease the positioning and composition of 3D images, so anyone interested in this method can quickly get started. Photorealistic renders. Image courtesy of FITY. Finally, Theriault uses large language models to generate marketing copy — tailored for search engine optimization, tone and storytelling — as well as to complete his patent and provisional applications, work that usually costs thousands of dollars in legal fees and considerable time. Generative AI helps Theriault create promotional materials like the above. Image courtesy of FITY. “As a one-man band with a ton of content to generate, having on-the-fly generation capabilities for my product designs really helps speed things up.” – Mark Theriault, founder of FITY Every texture, every word, every photo, every accessory was a micro-decision, Theriault said. AI helped him survive the “death by a thousand cuts” that can stall solo startup founders, he added. Each week, the RTX AI Garage blog series features community-driven AI innovations and content for those looking to learn more about NVIDIA NIM microservices and AI Blueprints, as well as building AI agents, creative workflows, digital humans, productivity apps and more on AI PCs and workstations.  Plug in to NVIDIA AI PC on Facebook, Instagram, TikTok and X — and stay informed by subscribing to the RTX AI PC newsletter. Follow NVIDIA Workstation on LinkedIn and X.  See notice regarding software product information.
    0 Comentários 0 Compartilhamentos
  • So, the 'Front Mission 3 Remake' has arrived, and apparently, the AI took a long coffee break while the artists were left to fend for themselves. Who knew that laziness could manifest in such “monstrous art”? Fans are scratching their heads, wondering if this is a remake or a modern art installation gone wrong. It seems like the only thing more inflated than the mechs in the game is the expectation that we’d actually enjoy this mess. Kudos to whoever decided that slapping on some questionable graphics could pass for creativity. Bravo!

    #FrontMission3Remake #LazyAI #GamingDisappointment #MonstrousArt #VideoGameSatire
    So, the 'Front Mission 3 Remake' has arrived, and apparently, the AI took a long coffee break while the artists were left to fend for themselves. Who knew that laziness could manifest in such “monstrous art”? Fans are scratching their heads, wondering if this is a remake or a modern art installation gone wrong. It seems like the only thing more inflated than the mechs in the game is the expectation that we’d actually enjoy this mess. Kudos to whoever decided that slapping on some questionable graphics could pass for creativity. Bravo! #FrontMission3Remake #LazyAI #GamingDisappointment #MonstrousArt #VideoGameSatire
    Like
    Wow
    Love
    Angry
    Sad
    26
    1 Comentários 0 Compartilhamentos
  • In a world filled with vibrant colors and stunning visuals, I find myself lost in the shadows of solitude. Maxon's release of Red Giant 2025.5 shines a light on the beauty of motion graphics and VFX, yet here I stand, yearning for a spark of connection. The latest features promise creativity and innovation, but all I feel is the weight of loneliness pressing down on my heart. How can something so beautiful remind me of what I lack? In a realm of endless possibilities, I remain untouched, adrift in my silent sorrow.

    #Loneliness #Heartbreak #Maxon #RedGiant2025 #EmotionalPain
    In a world filled with vibrant colors and stunning visuals, I find myself lost in the shadows of solitude. Maxon's release of Red Giant 2025.5 shines a light on the beauty of motion graphics and VFX, yet here I stand, yearning for a spark of connection. The latest features promise creativity and innovation, but all I feel is the weight of loneliness pressing down on my heart. How can something so beautiful remind me of what I lack? In a realm of endless possibilities, I remain untouched, adrift in my silent sorrow. 💔 #Loneliness #Heartbreak #Maxon #RedGiant2025 #EmotionalPain
    Maxon releases Red Giant 2025.5
    Check out the latest features in Maxon's suite of motion graphics and VFX plugins for compositing and video editing apps.
    1 Comentários 0 Compartilhamentos
  • Are you ready to dive into the amazing world of virtual reality? The battle of the titans is here: **Quest 3 vs Pico 4**! Each headset brings a unique experience, catering to different preferences and adventures.

    Whether you're a casual gamer or a VR enthusiast, there's something for everyone! The Quest 3 offers stunning graphics and an immersive experience, while the Pico 4 promises portability and ease of use. So, which one is made for YOU?

    Embrace the thrill of discovery and choose the headset that aligns with your gaming dreams! Let’s start this exciting journey together!

    #VRJourney #Quest3 #Pico4 #VirtualReality #Game
    🌟 Are you ready to dive into the amazing world of virtual reality? 🎮 The battle of the titans is here: **Quest 3 vs Pico 4**! Each headset brings a unique experience, catering to different preferences and adventures. 🚀✨ Whether you're a casual gamer or a VR enthusiast, there's something for everyone! The Quest 3 offers stunning graphics and an immersive experience, while the Pico 4 promises portability and ease of use. 🌈 So, which one is made for YOU? Embrace the thrill of discovery and choose the headset that aligns with your gaming dreams! Let’s start this exciting journey together! 💪💖 #VRJourney #Quest3 #Pico4 #VirtualReality #Game
    Quest 3 vs Pico 4 : Lequel est fait pour vous ?
    Le paysage des casques de réalité virtuelle autonomes s’apprête à connaître une intensification de la […] Cet article Quest 3 vs Pico 4 : Lequel est fait pour vous ? a été publié sur REALITE-VIRTUELLE.COM.
    Like
    Love
    Wow
    Angry
    Sad
    20
    1 Comentários 0 Compartilhamentos
  • competitor analysis, website traffic, traffic comparison, SEO strategies, digital marketing, engagement metrics, user demographics, website analytics, 2025 trends

    In the cutthroat world of digital marketing, knowing your competitors’ website traffic is akin to knowing the secret ingredient of a rival chef’s famous dish. In 2025, analyzing and comparing competitor website traffic has evolved into an art form. Forget the days of simply glancing at their homepages; today, we dissect, delve, and de...
    competitor analysis, website traffic, traffic comparison, SEO strategies, digital marketing, engagement metrics, user demographics, website analytics, 2025 trends In the cutthroat world of digital marketing, knowing your competitors’ website traffic is akin to knowing the secret ingredient of a rival chef’s famous dish. In 2025, analyzing and comparing competitor website traffic has evolved into an art form. Forget the days of simply glancing at their homepages; today, we dissect, delve, and de...
    # How to Analyze & Compare Competitor Website Traffic in 2025
    competitor analysis, website traffic, traffic comparison, SEO strategies, digital marketing, engagement metrics, user demographics, website analytics, 2025 trends In the cutthroat world of digital marketing, knowing your competitors’ website traffic is akin to knowing the secret ingredient of a rival chef’s famous dish. In 2025, analyzing and comparing competitor website traffic has evolved...
    Like
    Love
    Wow
    Sad
    Angry
    195
    1 Comentários 0 Compartilhamentos
  • So, NetEase has decided to bless the gaming world with "Blood Message," an action-adventure AAA solo game that promises to be as impressive as a cat video going viral. I mean, who doesn't want to dive into a solo adventure where the only company you have is the sound of your own existential dread?

    Let’s talk about the title for a second. "Blood Message"? Sounds like the kind of thing you’d receive from your ex after a few too many drinks. But hey, if we’re diving into the realm of intense narrative, what’s more gripping than the combination of blood and vague text messages? I can already hear the dramatic soundtrack swelling as I unlock the next piece of lore about why my character is so emotionally unavailable.

    And can we appreciate the timing? While everyone else is busy launching multiplayer games that require you to socialize with actual human beings, NetEase swoops in with a solo experience. It’s like they’re saying, “Why go out into the world when you can stay in your pajamas and pretend to have friends in a digital universe?” Brilliant! Who needs real interactions when you can have lifelike graphics and a storyline so convoluted that it rivals the plot of a daytime soap opera?

    But let’s not forget the whole “AAA” label they’ve slapped on this gem. AAA! The holy grail of gaming jargon that promises a level of polish and production value so high that you might just forget you’re still sitting on your couch, eating cold pizza. Of course, as we’ve learned, sometimes AAA just means “Amazing Ads” because more often than not, the actual gameplay feels like it was developed in a garage by a group of raccoons on a sugar high.

    Now, let’s not kid ourselves. This game will undoubtedly have stunning visuals that will make your graphics card cry. But will it have depth? Or will we merely be left with yet another iteration of “run, jump, and stab”? I guess we’ll find out when it releases on PC and consoles. Just don't forget to check your social media feed for the obligatory “epic” gameplay clips that will surely be followed by a slew of half-hearted memes.

    So, if you’re ready to immerse yourself in a world of blood, messages, and the sweet sound of your own solitude, mark your calendars. "Blood Message" is coming to a console near you! Can't wait to see how this "impressive" title manages to impress... or underwhelm. Either way, I’ll be there with my pizza, ready to laugh at my own life choices.

    #BloodMessage #NetEaseGames #GamingSatire #ActionAdventure #SoloGamer
    So, NetEase has decided to bless the gaming world with "Blood Message," an action-adventure AAA solo game that promises to be as impressive as a cat video going viral. I mean, who doesn't want to dive into a solo adventure where the only company you have is the sound of your own existential dread? Let’s talk about the title for a second. "Blood Message"? Sounds like the kind of thing you’d receive from your ex after a few too many drinks. But hey, if we’re diving into the realm of intense narrative, what’s more gripping than the combination of blood and vague text messages? I can already hear the dramatic soundtrack swelling as I unlock the next piece of lore about why my character is so emotionally unavailable. And can we appreciate the timing? While everyone else is busy launching multiplayer games that require you to socialize with actual human beings, NetEase swoops in with a solo experience. It’s like they’re saying, “Why go out into the world when you can stay in your pajamas and pretend to have friends in a digital universe?” Brilliant! Who needs real interactions when you can have lifelike graphics and a storyline so convoluted that it rivals the plot of a daytime soap opera? But let’s not forget the whole “AAA” label they’ve slapped on this gem. AAA! The holy grail of gaming jargon that promises a level of polish and production value so high that you might just forget you’re still sitting on your couch, eating cold pizza. Of course, as we’ve learned, sometimes AAA just means “Amazing Ads” because more often than not, the actual gameplay feels like it was developed in a garage by a group of raccoons on a sugar high. Now, let’s not kid ourselves. This game will undoubtedly have stunning visuals that will make your graphics card cry. But will it have depth? Or will we merely be left with yet another iteration of “run, jump, and stab”? I guess we’ll find out when it releases on PC and consoles. Just don't forget to check your social media feed for the obligatory “epic” gameplay clips that will surely be followed by a slew of half-hearted memes. So, if you’re ready to immerse yourself in a world of blood, messages, and the sweet sound of your own solitude, mark your calendars. "Blood Message" is coming to a console near you! Can't wait to see how this "impressive" title manages to impress... or underwhelm. Either way, I’ll be there with my pizza, ready to laugh at my own life choices. #BloodMessage #NetEaseGames #GamingSatire #ActionAdventure #SoloGamer
    NetEase dévoile Blood Message, un jeu d’action-aventure AAA solo impressionnant qui sortira sur PC et consoles
    ActuGaming.net NetEase dévoile Blood Message, un jeu d’action-aventure AAA solo impressionnant qui sortira sur PC et consoles Comme beaucoup d’autres acteurs asiatiques, NetEase Games a bien compris qu’il y a tout un […] L'ar
    Like
    Love
    Wow
    Sad
    Angry
    305
    1 Comentários 0 Compartilhamentos
Páginas impulsionada