---
language:
- en
library_name: diffusers
license: apache-2.0
pipeline_tag: image-to-image
---

# UniWorld-R1

This model is part of the work presented in the paper [Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback](https://huggingface.co/papers/2510.16888).

<p align="center">
        <a href="https://github.com/PKU-YuanGroup/UniWorld-V2"><b>Code</b></a> | <a href="https://github.com/PKU-YuanGroup/Edit-R1"><b>Dataset</b></a>
</p>


# Performance

|Benchmark| FLUX.1-Kontext-dev  | Edit-R1-FLUX.1-Kontext-dev |
| ---- | ---- | ----|
| GEdit-Bench | 6.00 | **6.74** |
| ImgEdit | 3.71 | **4.02** |

# Usage

```python
import torch
from diffusers import FluxKontextPipeline
from diffusers.utils import load_image

pipe = FluxKontextPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.bfloat16)

pipe.load_lora_weights(
    "chestnutlzj/Edit-R1-FLUX.1-Kontext-dev",
    adapter_name="lora",
)
pipe.set_adapters(["lora"], adapter_weights=[1])

pipe.to("cuda")


input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")

image = pipe(
  image=input_image,
  prompt="Add a hat to the cat",
  guidance_scale=2.5
).images[0]

```

# Licence

FLUX.1-Kontext-dev falls under the [FLUX.1 [dev] Non-Commercial License](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev).