I LOVE this model :)

This is a Forge UI compatible fp16 version of SRPO for those with the vram.

All credit to the wonderful @wikeeyang for the work done here.

Other versions here:

https://civitai.com/models/1953067/srpo-refine-quantized?modelVersionId=2210447

Refer to that page for more information on the model. Again, all credit to @wikeeyang. This is just a mirror of this model from https://www.modelscope.cn/models/wikeeyang/SRPO-Refine-Quantized/file/view/master/Flux1-Dev-SRPO-v1-fp16.safetensors

24gb vram + 64gb RAM minimum. Tested and works in Forge. Adjust the GPU Weights slider to slightly lower than default if you are getting an error message.

Flux loras will work about 70% or so, depending on the lora. Slightly better than Flux Krea in my experience.

More info about SRPO here: https://huggingface.co/tencent/SRPO