--- 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) ## 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](https://www.runninghub.ai) - [RunningHub China](https://www.runninghub.cn) - [RunningHub API](https://www.runninghub.ai/call-api) - [RunningHub API Documentation](https://www.runninghub.cn/runninghub-api-doc-en/) - [RunningHub API Docs CN](https://www.runninghub.cn/runninghub-api-doc-cn/) - [ComfyUI-RH-daVinci-MagiHuman Plugin](https://github.com/RH-RunningHub/ComfyUI-RH-daVinci-MagiHuman) 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](https://www.runninghub.ai) to explore runnable AI workflows. Want to integrate digital human / talking-head video generation into your product? Start with the [RunningHub API Documentation](https://www.runninghub.cn/runninghub-api-doc-en/). 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 | 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) - [RunningHub](https://www.runninghub.ai) - [RunningHub China](https://www.runninghub.cn) - [RunningHub API](https://www.runninghub.ai/call-api) - [RunningHub API Documentation](https://www.runninghub.cn/runninghub-api-doc-en/) - [TokenPlus](https://tokenplus.net/) - [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)