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
- Two Midjourney sref codes for grainy pastel fashion illustration style — sergeantsref · 2026-10-23
- Three free ways to try MOSS-Image: API playground, HF Space, ComfyUI — songguoxiansen · 2026-10-23
- Open-source MOSS-Image tops 1M ComfyUI downloads, 5B model rivals closed rivals — songguoxiansen · 2026-10-23
- GAFU Uses Generation-Side Representations to Boost Fine-Grained Visual Understanding in Unified Multimodal Models — Tengju Ru · 2026-10-23
- MiniMax Design MCP goes live: create with Design inside Codex and other agents — Hailuo_AI · 2026-10-23
- Quiver's detailed SVG generation sparks debate: code-drawn images could replace pixel-based image models — stuffyokodraws · 2026-10-23