SenseNova 6.8 Code2Video generates videos via editable code, fully open-sourced
aftahi_ai · x · 2026-11-11
SenseNova 6.8 Code2Video takes an unusual approach: instead of hiding the pipeline, it generates videos by writing editable code. Given a reference video, it recreates the visual structure and animation, then keeps updating the same source as you refine results through conversation.
Model weights, creation skills, prompts, source code, and full creation traces are all open-sourced on GitHub.
More from Multimodal
- MiniMax H3 image model trends on Hugging Face with ComfyUI single-file release — Comfy-Org · 2026-11-11
- MiniMax H3 Image hands-on: fast plastic-free T2I, but edits and consistency fail — Divineboob · 2026-11-11
- Fish Audio's Live 3 is a full-duplex voice model that listens while talking and knows when to shut up — aliscodes · 2026-11-11
- PotionUI motion transfer: one photo + 5s clip makes still images move, 3min on RTX 5090 — cocktailpeanut · 2026-11-11
- 1-click launcher now supports 20+ media models from FLUX to Wan and MiniMax — cocktailpeanut · 2026-11-11
- Potion UI: Polished One-Click Local App for Image, Video, Audio and 3D Generation — cocktailpeanut · 2026-11-11