Instructions to use CSWRY/VOSR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CSWRY/VOSR with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CSWRY/VOSR", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Missing license on the VOSR Hugging Face model page
Hi,
I've been looking at your VOSR project (https://github.com/cswry/VOSR) and wanted to flag that the Hugging Face model page (https://huggingface.co/CSWRY/VOSR) currently has no license tag and no model card.
The GitHub repo states the project is under Apache License 2.0 unless otherwise noted, but this isn't reflected on the Hugging Face page itself. Without a clear license there, many users (myself included) hesitate to use the model weights, since it's unclear what terms actually apply to the downloaded files.
Would you be able to:
Add a license tag to the Hugging Face repo (e.g. Apache-2.0, if that's what applies), and
Add a short model card noting the license and any usage restrictions?
I also opened an issue on GitHub with the same request (#14: https://github.com/cswry/VOSR/issues/14), in case that's a more convenient place to track it.
Thanks for the great work on this project, and I appreciate you taking a look at this.
Best regards,
Steven
Hi Steven,
Thanks for pointing this out, and apologies for the missing information. We’ve now added the Apache-2.0 license tag and a model card to the Hugging Face page, clarifying the license for the VOSR checkpoints and the applicable terms for bundled third-party components.
Thank you for your interest in VOSR and for helping us improve the documentation!