Instructions to use unsloth/Qwen-Image-ComfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use unsloth/Qwen-Image-ComfyUI with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| unsloth/Qwen-Image-ComfyUI | |
| A mirror of the single-file Qwen-Image VAE that Comfy-Org/Qwen-Image_ComfyUI publishes | |
| (https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI). | |
| Unsloth has not modified the weights: every file here is byte for byte the file of the same name in the source repository (verified on the Hub's LFS sha256). | |
| The weights are the VAE of Qwen-Image (https://huggingface.co/Qwen/Qwen-Image), | |
| Copyright 2024 Alibaba Cloud, licensed under the Apache License, Version 2.0. LICENSE is | |
| the copy Alibaba ships with Qwen-Image, verbatim. Upstream ships no NOTICE file, so there | |
| is nothing further to propagate under Apache-2.0 section 4(d). | |
| Changes relative to Qwen/Qwen-Image (Apache-2.0 section 4(b)): the VAE is extracted into | |
| one standalone safetensors file with ComfyUI key names. That repack is Comfy-Org's work, | |
| not Unsloth's. Not an official Alibaba Cloud or ComfyUI product, and not endorsed by | |
| either. | |