Viggle open-sources Minimax H3 finetune, closing the open-source AI loop
cocktailpeanut · x · 2026-09-07
A full-circle open-source story: two years ago Viggle broke the internet with a proprietary model that was imperfect but met real demand. Now the same team finetuned Minimax H3 and released it as open weights, and it works very well.
- The author demonstrates a workflow: upload the reference video to ChatGPT or a local image-edit model, swap in any character (e.g. tung tung tung sahur), then feed that single frame plus the reference video—one frame is enough
- Framed as a model example of how open-source AI compounds: MiniMax open-sourced, Viggle built on it and gave back
More from Multimodal
- Mockumentary-style prompt recreates The Office look on Friends with AI video — cocktailpeanut · 2026-09-07
- MiniMax H3 powers a retro 'Jem: Holographic Pop Star' animated demo — darthfurbyyoutube · 2026-09-07
- GPT-6 Astra + LTX-2.5 combo turns websites into interactive video worlds — Mr_AllenT · 2026-09-07
- Gemini Omni 1.1 hands-on: strong at animation, ~$120/mo of free credits on Flow — oyacaro · 2026-09-07
- AI-generated 'last march of the ents' video: 1% of trees grow legs, plus kid-invented cheat codes — tomjohndesign · 2026-09-07
- Inpaint Canvas: layers, selections and retouching in one ComfyUI node — Direction_Mountain · 2026-09-07