Henge
Type: ComfyUICategory: Generation
Henge is a ComfyUI workflow or node pack in our Generation category. Alisson Anjos's MIT studio on ComfyUI + MiniMax H3 with trained per-mode LoRAs: character swap, motion transfer (guide latents or TARA), head swap and Sharpness (to 2K/4K). SAM 3.1 multi-character tracking, shot-by-shot long clips, a built-in assistant and an MCP server. Local needs 32 GB VRAM / 64 GB RAM and ~125 GB of models; or RunPod pod/Serverless. Weight and LoRA licenses apply; consent required for real people.
Where it fits: ComfyUI, Open-weight video & audio models, Video MCP servers.
Listing isn’t endorsement. This is our summary of the project’s own docs. Check the licence and requirements at the source before you build on it.
Lab posts that cover Henge
Related Lab posts
- Local AI transitions between real footage, inside DaVinci Resolve: an honest test of LTX 2.5 and MiniMax H3 Omni vs Seedance 2.5
- ComfyArt: a local Lovart-style infinite canvas on your ComfyUI
- #OpenSourceHiggsfield: Comfy's $25K challenge and the first open rebuilds
- OPENjutsu: Comfy open-sources a character-swap app on MiniMax H3, and a fully local fork follows within hours
- MiniMax H3's community speed stack: 4-step LoRAs, sparse attention, and FreeVideo on an 8 GB card
Similar skills & repos
- OPENjutsu · ComfyUI, Generation
- openjutsu (local fork) · ComfyUI, Generation
- FreeVideo · ComfyUI, Generation
- DMAD (4-step H3) · Repo, Generation
- FastH3 Omni · ComfyUI, Generation
- seriesmith · ComfyUI, Generation