This adapter for Stable Diffusion 1.5 and SDXL is designed to inject the general composition of an image into the model while mostly ignoring the style and content. Meaning a portrait of a person waving their left hand will result in an image of a completely different person waving with their left hand.
### Follow Me
I do a lot of experiments and other things. To keep up to date, follow me on [Twitter](https://twitter.com/ostrisai).
### Thanks
I want to give a special thanks to [POM](https://huggingface.co/peteromallet) with [BANODOCO](https://huggingface.co/BANODOCO). This was their idea, I just trained it. Full credit goes to them.
## Usage
Use just like other IP+ adapters from [h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter). For both SD1.5 and SDXL variants, use the CLIP vision encoder ([CLIP-H](https://huggingface.co/h94/IP-Adapter/tree/main/models/image_encoder))
You may need to lower the CFG to around 3 for best results, especially on the SDXL variant.
### How is it different from control nets?
Control nets are more rigid. A control net will spatially align an image to nearly perfectly match the control image. The composition adapter allows the control to be more flexible.
