Add ReNeg: An end-toend method designed to learn improved Negative embeddings (CVPR 2025 Highlight)

### **Model/Pipeline/Scheduler description**

[ReNeg] is a reward-guided approach that directly learns Negative embeddings through gradient descent. The negative embedding learned within the same text embedding space exhibits strong generalization capabilities.

For example, using the same CLIP text encoder, the negative embedding learned on SD1.5 can be seamlessly transferred to text-to-image or even text-to-video models such as ControlNet, ZeroScope, and VideoCrafter2, resulting in consistent performance improvements across the board.


### **Open Source Status**

- [x] The model implementation is available.
- [x] The model weights are available (Only relevant if addition is not a scheduler).

### **Provide useful links for the implementation**

Official implementation: https://github.com/AMD-AIG-AIMA/ReNeg

The payload names no target files or tests. Start by reading the official ReNeg implementation and its model, pipeline, and scheduler entry points; done means integrating the available ReNeg implementation and weights into diffusers while preserving the described transfer to supported text-to-image and text-to-video models.

Scritto dal modello di indicizzazione a partire dal testo della issue.