sparkling621

/

EditHF-Reward

like 0

Hi! I'm Niels from the Hugging Face community team.

This PR adds a model card for the EditHF-Reward model. This model is an advanced version of Qwen-Image-Edit, refined through reinforcement learning using human preference feedback as described in the paper EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing.

The PR includes:

• Metadata for the image-to-image pipeline tag.
• Metadata for the diffusers library.
• Links to the official research paper and GitHub repository.
• A description of the training process and the EditHF-1M dataset.