Instructions to use chestnutlzj/Edit-R1-FLUX.1-Kontext-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use chestnutlzj/Edit-R1-FLUX.1-Kontext-dev 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("chestnutlzj/Edit-R1-FLUX.1-Kontext-dev", 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
Update model card with UniWorld-V2 paper link and main GitHub repository
#1
by nielsr HF Staff - opened
This PR updates the model card to improve its documentation:
- Adds a direct link to the associated paper, Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback, in the markdown content.
- Updates the "Code" link in the header to point to the main project GitHub repository:
https://github.com/PKU-YuanGroup/UniWorld-V2.
The existing metadata, performance table, usage example, and dataset link remain unchanged.
chestnutlzj changed pull request status to merged