Instructions to use chestnutlzj/Edit-R1-Qwen-Image-Edit-2509 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use chestnutlzj/Edit-R1-Qwen-Image-Edit-2509 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("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("chestnutlzj/Edit-R1-Qwen-Image-Edit-2509") 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
- Local Apps
- Draw Things
Update model card with Uniworld-V2 paper link and main code repository
#1
by nielsr HF Staff - opened
This PR improves the model card for chestnutlzj/Edit-R1-Qwen-Image-Edit-2509 by:
- Linking directly to its associated paper: Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback.
- Updating the main code repository link to
https://github.com/PKU-YuanGroup/UniWorld-V2for better discoverability. - Adding a brief introductory description based on the paper's context.
The existing diffusers usage example and performance metrics are preserved.
chestnutlzj changed pull request status to merged
This actually works pretty well!