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
About BF16 Models
#13
by FrederickSun - opened
Thanks a lot with the update of bf16 models!
I encountered some errors with qwen_image_bf16.safetensors. Under the official workflow, loading the model and Fp16 version of CLIP (qwen_2.5_vl_7b.safetensor) would cause severe color shift in the generated image. Are there anything wrong with the mismatch of data type ? (BF16 vs FP16)