---
license: apache-2.0
library_name: comfyui
base_model: GAIR/daVinci-MagiHuman
pipeline_tag: image-to-video
language:
  - en
  - zh
  - ja
  - ko
  - de
  - fr
  - yue
tags:
  - comfyui
  - image-to-video
  - image-text-to-audio-video
  - multimodal
  - int8
---

# ComfyUI-RH-daVinci-MagiHuman INT8

[![RunningHub China](https://img.shields.io/badge/RunningHub-China-2F80ED)](https://www.runninghub.cn/?inviteCode=rh-v1367)
[![RunningHub International](https://img.shields.io/badge/RunningHub-International-7B61FF)](https://www.runninghub.ai/?inviteCode=rh-v1367)
[![English](https://img.shields.io/badge/Language-English-2563EB)](./README.md)
[![简体中文](https://img.shields.io/badge/Language-%E7%AE%80%E4%BD%93%E4%B8%AD%E6%96%87-EF4444)](./README_CN.md)

INT8-quantised daVinci-MagiHuman DiT and super-resolution weights for
[ComfyUI-RH-daVinci-MagiHuman](https://github.com/RH-RunningHub/ComfyUI-RH-daVinci-MagiHuman).
This repository contains only the four converted `.pt` files. TurboVAE, the
T5 text encoder, and the video/audio VAEs still come from the official
releases.

The ComfyUI nodes load these INT8 files directly. Official BF16 DiT shards and
official `540p_sr/` / `1080p_sr/` config directories are not required.

Full snapshot is about **57 GiB**. Download only the files you need.

Mirror: [Hugging Face](https://huggingface.co/Gluttony10/ComfyUI-RH-daVinci-MagiHuman) /
[ModelScope](https://www.modelscope.cn/models/Gluttony10/ComfyUI-RH-daVinci-MagiHuman)

## Contents

| File | Size | Role |
|---|---:|---|
| `base_int8.pt` | 14.25 GiB | INT8 Base DiT (32 steps, higher quality) |
| `distill_int8.pt` | 14.25 GiB | INT8 Distill DiT (8 steps, faster) |
| `sr_540p_sr_int8.pt` | 14.25 GiB | Optional INT8 540p super-resolution |
| `sr_1080p_sr_int8.pt` | 14.25 GiB | Optional INT8 1080p super-resolution |

You need **one** of `base_int8.pt` / `distill_int8.pt`. Add an SR file only
when the loader's `sr_model` is `540p_sr` or `1080p_sr`.

## Install into ComfyUI

```text
ComfyUI/models/MagiHuman/
├── base_int8.pt
├── distill_int8.pt
├── sr_540p_sr_int8.pt          # optional
└── sr_1080p_sr_int8.pt         # optional
```

### Hugging Face

```bash
cd /path/to/ComfyUI
python3 -m pip install -U huggingface_hub

hf download Gluttony10/ComfyUI-RH-daVinci-MagiHuman base_int8.pt \
  --local-dir ./models/MagiHuman
hf download Gluttony10/ComfyUI-RH-daVinci-MagiHuman distill_int8.pt \
  --local-dir ./models/MagiHuman
hf download Gluttony10/ComfyUI-RH-daVinci-MagiHuman sr_540p_sr_int8.pt \
  --local-dir ./models/MagiHuman
hf download Gluttony10/ComfyUI-RH-daVinci-MagiHuman sr_1080p_sr_int8.pt \
  --local-dir ./models/MagiHuman
```

### ModelScope

```bash
pip install modelscope
cd /path/to/ComfyUI
modelscope download --model Gluttony10/ComfyUI-RH-daVinci-MagiHuman base_int8.pt \
  --local_dir ./models/MagiHuman
modelscope download --model Gluttony10/ComfyUI-RH-daVinci-MagiHuman distill_int8.pt \
  --local_dir ./models/MagiHuman
modelscope download --model Gluttony10/ComfyUI-RH-daVinci-MagiHuman sr_540p_sr_int8.pt \
  --local_dir ./models/MagiHuman
modelscope download --model Gluttony10/ComfyUI-RH-daVinci-MagiHuman sr_1080p_sr_int8.pt \
  --local_dir ./models/MagiHuman
```

## Other required assets

These files are **not** in this repository:

```bash
# Official MagiHuman assets (TurboVAE, T5 text encoder)
hf download GAIR/daVinci-MagiHuman --local-dir ./models/MagiHuman
pip install modelscope
modelscope download --model GAIR/daVinci-MagiHuman --local_dir ./models/MagiHuman

# External VAEs
hf download stabilityai/stable-audio-open-1.0 \
  --local-dir ./models/audio_checkpoints/stable-audio-open-1.0
hf download Wan-AI/Wan2.2-TI2V-5B \
  --local-dir ./models/Ovi/Wan2.2-TI2V-5B
```

Expected layout after everything is in place:

```text
ComfyUI/models/
├── MagiHuman/
│   ├── base_int8.pt
│   ├── distill_int8.pt
│   ├── sr_540p_sr_int8.pt
│   ├── sr_1080p_sr_int8.pt
│   ├── t5gemma-9b-9b-ul2/
│   └── turbo_vae/
├── audio_checkpoints/stable-audio-open-1.0/
└── Ovi/Wan2.2-TI2V-5B/
```

## Plugin

Current plugin: [RH-RunningHub/ComfyUI-RH-daVinci-MagiHuman](https://github.com/RH-RunningHub/ComfyUI-RH-daVinci-MagiHuman)

| Node | Purpose |
|---|---|
| `RH MagiHuman Model Loader` (`RH_MagiHumanModelLoader`) | Load INT8 DiT, VAEs, and optional SR |
| `RH MagiHuman Generate` (`RH_MagiHumanGenerate`) | Talking-head video from a reference image and text prompt |

Loader options:

- `model_type`: `base` (32 steps) or `distill` (8 steps)
- `vram_mode`: `mid_vram` (~16 GB) or `low_vram` (~6.5 GB)
- `sr_model`: `none` / `540p_sr` / `1080p_sr`

`mid_vram` + 540p SR needs about 24 GB. `mid_vram` + 1080p SR needs about 48 GB.

## License

Converted weights follow the upstream
[Apache-2.0](https://opensource.org/licenses/Apache-2.0) license of
[daVinci-MagiHuman](https://huggingface.co/GAIR/daVinci-MagiHuman).

## Links

[![RunningHub China](https://img.shields.io/badge/RunningHub-China-2F80ED)](https://www.runninghub.cn/?inviteCode=rh-v1367)
[![RunningHub International](https://img.shields.io/badge/RunningHub-International-7B61FF)](https://www.runninghub.ai/?inviteCode=rh-v1367)

- [Official daVinci-MagiHuman](https://github.com/GAIR-NLP/daVinci-MagiHuman)
- [Official weights](https://huggingface.co/GAIR/daVinci-MagiHuman)
- [Official assets on ModelScope](https://www.modelscope.cn/models/GAIR/daVinci-MagiHuman)
- [ComfyUI-RH-daVinci-MagiHuman](https://github.com/RH-RunningHub/ComfyUI-RH-daVinci-MagiHuman)