### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### The Feature

Enable `/images/edits` endpoint to be used with Xinference provider

### Motivation, pitch

It is great that LiteLLM can use Xinference as openai-compatible image generation endpoint. Many open-source models such as FLUX.2-dev, that can be hosted with Xinference also support `image2image`. It would be great to allow using `/images/edits` endpoint for Xinference provider as well.

``` curl -o >(jq -r '.data[0].b64_json' | base64 --decode > image-edit.jpeg) \ -X POST "http://localhost:9997/v1/images/edits" \ -H "Authorization: Bearer sk-key" \ -F "model=FLUX.2-dev" \ -F "image[]=@image.jpeg" \ -F 'prompt=Add a rainy sky outside' \ -F "response_format=b64_json" ```

### What part of LiteLLM is this about?

Proxy

### LiteLLM is hiring a founding backend engineer, are you interested in joining us and shipping to all our users?

No

### Twitter / LinkedIn details

_No response_