Glad to share Seaweed-7B, a cost-effective foundation model for video generation. Our tech report highlights the key designs that significantly improve compute efficiency and performance given limited resources, achieving comparable quality against other industry-level models. To

More videos are available at seaweed.video

a wonderful work and one of the most important things: open sourcing

checkout our human video generation here dsaurus.github.io/isa4d/

real-world image and video restoration in ONE step iceclear.github.io/projects/seedv…

SeedVR2 One-Step Video Restoration via Diffusion Adversarial Post-Training

Check out our latest multi-concept audio-driven human video generation here: zhenzhiwang.github.io/interacthuman/

Humans interact with this world in real-time. Our latest APT2 makes this happen in video foundation model. Now you can explore the generative world by controlling 6DoF camera poses with negligible latency. Check out more cool stuff at seaweed-apt.com/2

Grok Code Fast 1 is now available in anycoder a speedy and economical reasoning model that excels at agentic coding. one shotted a ai chatbot for gemma-3-270m-it-ONNX using transformers.js in anycoder runs completely in the browser

How do we generate videos on the scale of minutes, without drifting or forgetting about the historical context? We introduce Mixture of Contexts. Every minute-long video below is the direct output of our model in a single pass, with no post-processing, stitching, or editing. 1/4

new one

Our research: Adversarial Flow Models (AF) arxiv.org/abs/2511.22475 AF unifies Adversarial and Flow Models. Unlike GANs, AF learns optimal transport (stable). Unlike CMs, AF only trains on needed timesteps (save capacity). We can train super-deep 112-layer 1NFE model! SOTA FIDs!