visualseed/RORem-merged

RORem (merged)

SDXL - RORem (CVPR 2025) repackaged as a plain diffusers StableDiffusionXLInpaintPipeline: the LetsThink/RORem weights with their LCM-distillation LoRA already merged into the UNet, so conversion pipelines install straight from this repository with no adapter step. Nothing was retrained — the merge is a plain B@A bake at scale 1 (788 adapters), numerically equivalent to diffusers' own fuse_lora.

Inference contract

Verified by instrumenting the reference inference_RORem_4S.py call (diffusers 0.41):

pipe(prompt="", image=image, mask_image=mask, guidance_scale=1.0,
     num_inference_steps=4, strength=0.99)  # LCMScheduler

The scheduler places [999, 759, 499, 259] and the strength slice drops the head — three denoiser passes at [759, 499, 259], with the photo noised to 759. Guidance is off and the prompt is empty: RORem is prompt-free.

Provenance

Derived from LetsThink/RORem (Apache-2.0), the LCM LoRA from the RORem-LCM release, on the CreativeML Open RAIL++-M SDXL inpainting base. Project page: github.com/leeruibin/RORem.