Instructions to use cardamonnl/Qwen-Image-Edit-2511-int8-convrot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use cardamonnl/Qwen-Image-Edit-2511-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
why not full learned rounding without
#1
by ApexArtist - opened
can you create one without the --simple
Hi - that made me curious and I just did that.
only done a very simple test, but it looks like there is indeed a small improvement
Source image (Krea2):
Prompt: "obtain the front view", 8 steps with lightning lora
Without learned rounding:
With learned rounding:
The creature's head looks slightly better on the left side in the version with learned rounding I think.
(did not do any more extensive testing)


