open source
Every SLOP TV News story about open source.
MiniMax H3's open license excludes the US, UK and EU
Builds keep appearing under it, including one from NVIDIA Research, while a rival open video model ships with no territory clause at all.
FlashVSR+ runs untiled 4K video upscaling on one RTX 4090
The open-source model from Shanghai AI Lab skips the spatial tiling that leaves seams in 4K clips, reporting up to 2x DiT speedup and 45% lower peak memory.
Shots fired: ComfyUI pays $25,000 to rebuild Higgsfield in the open
Comfy says Higgsfield promised to open-source its platform and never did, so it put up $25,000 with NVIDIA and RunPod underwriting the fight. The question underneath is the one worth asking: is Comfy all you need?
Kandinsky S2V 1.0 ships 2B and 21B open speech-to-video models
The Kandinsky Lab models animate one reference image at 25 frames per second, and the team's own human study preferred Pro for lip sync over HeyGen and Kling.
Tencent opens Multics, a world model for 10 players
One 4-player checkpoint generates video for 6, 8 and 10 players without retraining, using communication across player, group and global levels.
How Claude Opus 5.5 painted a hand-drawn music video in code
X user NotinReality handed the lyrics and audio to Claude Opus 5.5, which wrote the JavaScript that paints all 156.6 seconds frame by frame.
HyperFrames Studio: how to make video with a coding agent
The free, Apache-2.0 editor from HeyGen's HyperFrames team lets Claude Code or Codex build the project, then you trim clips and edit on the same timeline.
Tencent Hunyuan's Prism renders 2K video with sound in one pass
The Fudan and Tencent Hunyuan model is MIT-licensed and open on GitHub, but native 2K output needs four or more 80 GB GPUs.
4 free upgrades for local AI video released this week
ComfyUI, a timeline editor, an inpainting sampler and a camera-angle LoRA all shipped in the last four days, and all of them are free.
OpenMontage: turning a coding assistant into a video studio
The open-source project ships no clip generator of its own, and its zero-key path renders a finished narrated video without paying a video API.