Two-Reference Image Editing — MiniMax H3
Perfil de execução
Descrição da fonte
Two-Reference Image Editing — MiniMax H3
A ComfyUI workflow built on the MiniMax H3 model, designed to edit images using two reference images at once. The first image sets the foundation — the scene, object, or character — while the second brings in the desired change: different clothing, an accessory, or a new object to add to the original photo. The model blends both sources carefully, preserving the composition and recognizability of the original.
Great for outfit changes, adding objects, and targeted object-level edits. ⚠️ This workflow does not change pose — the original pose is preserved as-is.
Use MiniMax-H3-Ref2VA-pruned_int8_convrot.safetensors for best result
The workflow has been updated. fixed an error with file names when saving. Don't judge me harshly - this is the first time I've published it.
Fontes
1 fonteTrechos de fonte
1 trechoSource context: 537 downloads · Type Workflows · Base model MiniMax H3
Estimativa de requisito VRAM
32+ GB estimados
39,6 GB de arquivos de modelo. Total de arquivos do modelo + 25% de overhead de carregamento + 2 GB de buffer de execução, arredondado para cima.
Requisitos
Requisitos 5minimax_h3_audio_vae_fp32.safetensors
EncontradoVAE · 577 MB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
Checkpoint · 19.5 GB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
minimax_h3_video_vae_fp16.safetensors
EncontradoVAE · 4.85 GB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
Text encoder · 14.6 GB · SAFETENSORS · Hugging Face · Comfy-Org/MiniMax-H3
Pacote de nós · Registry