API Requests

add image reference for Photorealism v2 to API

Can take in images as input and answer questions about them, not just OCR. Something like GPT4 vision, LLaVA, BakLLaVA, CogVLM, Qwen-VL

An API endpoint for a SDXL pipeline that has ControlNets integrated.

I tried you AI Resizer which is very useful feature, but the only missing point is want to use it as API but currently there is no support for this so please include this as soon as possible as I want to use this to generates thousands of Images!!

The API supports ControlNet, but the input image has to be a normal image which later is preprocessed to be fed to ControlNet. For some use cases is useful to input an already processed image, such as a depth map, or a pose. This way the user can have more control over the image. This feature is already supported in the AI generator, but not in the API.