DeepSeek releases new image model family
techcrunch.com
DeepSeek, the viral AI company, has released a new set of multimodal AI models that it claims can outperform OpenAIs DALL-E 3. The models, which are available for download from the AI dev platform Hugging Face, are part of a new model family that DeepSeek is calling Janus-Pro. They range in size from 1 billion to 7 billion parameters. Parameters roughly correspond to a models problem-solving skills, and models with more parameters generally perform better than those with fewer parameters.Janus-Pro is under an MIT license, meaning it can be used commercially without restriction.Image outputs from DeepSeeks Janus Pro models.Image Credits:DeepSeekJanus-Pro, which DeepSeek describes as a novel autoregressive framework, can both analyze and create new images. According to the company, on two AI evaluation benchmarks, GenEval and DPG-Bench, the largest Janus-Pro model, Janus-Pro-7B, beats DALL-E 3 as well as models such as PixArt-alpha, Emu3-Gen, and Stability AIs Stable Diffusion XL.Granted, some of those models are on the older side, and most Janus-Pro models can only analyze small images with a resolution of up to 384 x 384. But Janus-Pros performance is impressive, considering the models compact sizes.Janus-Pro surpasses previous unified model and matches or exceeds the performance of task-specific models, DeepSeek writes in a post on Hugging Face. The simplicity, high flexibility, and effectiveness of Janus-Pro make it a strong candidate for next-generation unified multimodal models.DeepSeeks new Janus Pro models compared with the competition.Image Credits:DeepSeekDeepSeek, a Chinese AI lab funded largely by the quantitative trading firm High-Flyer Capital Management, broke into the mainstream consciousness this week after its chatbot app rose to the top of the Apple App Store charts. DeepSeeks language models, which were trained using compute-efficient techniques, have led many Wall Street analysts and technologists to question whether the U.S. can maintain its lead in the AI race and whether the demand for AI chips will sustain.Update: An earlier version of this story implied that Janus-Pro models could only output small (384 x 384) images. Thats untrue. We regret the error.TechCrunch has an AI-focused newsletter! Sign up here to get it in your inbox every Wednesday.
0 Comments ·0 Shares ·61 Views