Instructions to use Comfy-Org/Qwen-Image_ComfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Comfy-Org/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
only bf16, will there be a fp8 scaled version?
#1
by jasoncow - opened
so big,,,,牛逼
It's already uploaded
It's already uploaded
The diffusion model in this repo that's FP8 isn't scaled, you can achieve better results by making use of FP8's headroom and scaling properties.
I'm unsure if scaled FP8 is supported yet, I can try making a version of it though.
oh I missed the scaled part 😅
i use text_encoders/qwen_2.5_vl_7b_fp8_scaled.safetensors
CLIPLoader 38: Value not in list: type: 'qwen_image' not in ['stable_diffusion', 'stable_cascade', 'sd3', 'stable_audio', 'mochi', 'ltxv', 'pixart', 'cosmos', 'lumina2', 'wan', 'hidream', 'chroma', 'ace', 'omnigen2']
where is Qwen Image FP8 scaled base model I can't find