Instructions to use AX1Y2JP/FLUX.2-dev-INT8-ConvRot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use AX1Y2JP/FLUX.2-dev-INT8-ConvRot 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
This model is completely unusable in ComfyUI. Are you kidding me? It's ridiculous.
#2
by liuxingsyue - opened
No description provided.
It seems I'll have to quantize the Flux2 int8con myself for it to be reliable, I only thought downloading a 60GB BF16model was too large, which is why I wanted to download it from you, but I didn't expect it to be so garbage.