CoolFace
Modelpublic

RunningHubAI/ComfyUI-RH-daVinci-MagiHuman

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face
0likes
Model Card

ComfyUI-RH-daVinci-MagiHuman INT8

![RunningHub China](https://www.runninghub.cn/?inviteCode=rh-v1367) ![RunningHub International](https://www.runninghub.ai/?inviteCode=rh-v1367) ![English](./README.md) ![简体中文](./README_CN.md)

INT8-quantised daVinci-MagiHuman DiT and super-resolution weights for 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 / ModelScope

Run Online and API Access

If you do not want to download and configure the full model assets locally, you can first try related MagiHuman workflows online on RunningHub, or integrate RunningHub AI app / workflow APIs into your own product.

RunningHub is useful for quickly validating workflows such as reference-image-to-talking-head video, digital human video, and AI presenter / spokesperson video generation. You can first run and tune the workflow online, then choose local deployment if needed, or integrate similar capabilities into your product through RunningHub API.

Want to try it quickly? Open RunningHub to explore runnable AI workflows. Want to integrate digital human / talking-head video generation into your product? Start with the RunningHub API Documentation.

RunningHub API supports model APIs, AI app APIs, workflow APIs, and LLM APIs. For MagiHuman-style video generation workflows, the recommended task flow is:

text
Submit task -> get taskId -> check task status -> retrieve generated result

Recommended use cases:

  • —Run daVinci-MagiHuman / MagiHuman talking-head video generation workflows online
  • —Add reference-image-to-video, digital human presenter, and AI video generation capabilities to your product
  • —Provide creators, developers, and teams with no-local-setup generative AI workflows
  • —Build automated video generation, content production, or multimodal applications with RunningHub API

Contents

FileSizeRole
base_int8.pt14.25 GiBINT8 Base DiT (32 steps, higher quality)
distill_int8.pt14.25 GiBINT8 Distill DiT (8 steps, faster)
sr_540p_sr_int8.pt14.25 GiBOptional INT8 540p super-resolution
sr_1080p_sr_int8.pt14.25 GiBOptional 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

NodePurpose
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 license of daVinci-MagiHuman.

Links

![RunningHub China](https://www.runninghub.cn/?inviteCode=rh-v1367) ![RunningHub International](https://www.runninghub.ai/?inviteCode=rh-v1367)