edit: 1.1 can work with long vídeos, long context, mask with sam, this is veeeeeeeeeeeery best than 1.0 try xD!
MiniMax H3 Character Replacement — Ref2VA + Turbo
A simple ComfyUI workflow for full character replacement using MiniMax H3 Ref2VA.
Provide a source video and a reference image of the new character. The workflow uses the original video as reference for motion, poses, camera movement, timing and scene composition, while replacing the original character with the identity and appearance from the reference image.
⚡ Uses the MiniMax H3 Turbo LoRA (Pruned) for fast 4-step generation, making character replacement significantly faster than the standard 20-step workflow.
Inputs:
🎬 Source Video — motion, camera and scene reference
🖼️ Character Image — replacement character
✍️ Prompt — optional adjustments
Model: MiniMax H3 Ref2VA Pruned INT8 ConvRot
Sampler: MiniMax H3 Turbo
Steps: 4
Description
FAQ
Comments (10)
testing it now.
genious, didn't know about that node, thanks man.
@necroryona what node? =)
@kimimorgam the video motion scene uploader
@necroryona xd
Thanks, worked!
you are welcome
hey i'm trying to use this turbo lora do u happen know the link for this. Also it seems im using the wrong mode for this, can u tell me which variant that i should use (if u happen to have the hugginface link i'd really appreciate it)
@LeakNudeCollector
I am using this
https://huggingface.co/larryvrh/MiniMax-H3-Turbo-Lora/tree/main
minimax_h3_turbo_v4_step600_ema.safetensors
With 6 Steps.
@LeakNudeCollector it depends, if i2v or t2v