---
title: MiniMax-H3 Character Swap LoRA
emoji: 🎭
colorFrom: purple
colorTo: pink
sdk: gradio
sdk_version: 5.49.1
app_file: app.py
short_description: Prompt + workflow demo for H3 character swap
python_version: "3.12"
license: other
tags:
  - video-to-video
  - character-swap
  - minimax-h3
  - lora
  - comfyui
models:
  - akatz-ai/MiniMax-H3-Character-Swap-LoRA
  - Comfy-Org/MiniMax-H3
datasets:
  - akatz-ai/H3-Character-Swap-v1
---

# MiniMax H3 Character Swap LoRA — demo Space

Interactive prompt builder and ComfyUI checklist for
[akatz-ai/MiniMax-H3-Character-Swap-LoRA](https://huggingface.co/akatz-ai/MiniMax-H3-Character-Swap-LoRA).

This Space does **not** run the H3 Ref2VA base model. That adapter is not a
standalone generator: you still need the pruned INT8 Ref2VA checkpoint, the
video/audio VAEs, and an H3 Ref2VA runtime (typically ComfyUI). Inference
Providers do not currently host this model.

What this demo does:

1. Take a source-clip description and a replacement-character description
2. Emit the card-recommended Ref2VA prompt (`<Video 1>` / `<Picture 1>`)
3. Print a one-page ComfyUI setup sheet at LoRA strength **1.0**

## Weights

- LoRA: `h3_character_swap_pro4500_1000.safetensors` (final 1,000-step only)
- Strength: **1.0**
- No trained trigger word
- Base: `minimax_h3_ref2va_pruned_int8_convrot.safetensors` from
  [Comfy-Org/MiniMax-H3](https://huggingface.co/Comfy-Org/MiniMax-H3)
- Training assistant (not merged): [ostris/minimax_h3_training_adapter](https://huggingface.co/ostris/minimax_h3_training_adapter)

## License

Distributed under the MiniMax H3 Community License Agreement. It is **not**
Apache-2.0. Read the full terms on the model repo before commercial or
territorial use.

## Author notes from the card

Short continuous 4–5 s shots at 24 fps work better than long 14 s tests.
Hard cuts, facial-expression lock, and multi-character swaps are unreliable.
This LoRA does not require a Turbo LoRA, Spectrum, or Sol attention.