Request to implement FreeScale, a new diffusion scheduler

### Model/Pipeline/Scheduler description

FreeScale is a tuning-free method for higher-resolution visual generation, unlocking the 8k image generation for pre-trained SDXL! Compared to direct inference by SDXL, FreeScale brings negligible additional memory and time costs.



### 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

- Project: http://haonanqiu.com/projects/FreeScale.html
- Paper: https://arxiv.org/abs/2412.09626
- Code: https://github.com/ali-vilab/FreeScale
- Hugging Face Demo: https://huggingface.co/spaces/MoonQiu/FreeScale

The code changes of FreeScale are not complicated, but I do not know how to integrate them into diffusers smoothly. If you have questions about FreeScale, please ask me(@arthur-qiu).

Start by reading the FreeScale paper and the linked implementation to understand the scheduler changes and how they should fit into diffusers. Compare the behavior with the linked Hugging Face demo; done means FreeScale is integrated smoothly into diffusers and its high-resolution generation behavior matches the documented method.

Vom Indexierungsmodell aus dem Issue-Text verfasst.