전체 검색

AI 모델 21

• MOSS-Image-SFT-8-steps-dmd↗

  lodestones

  Work-in-progress distillation of OpenMOSS-Team/MOSS-Image-SFT (50 steps, CFG 3) to 8 network evaluations, no CFG. Data-space DMD (arXiv 2610.12102): the generator iterates on its own clean estimate from fixed noise. Trained on compact-JSON `scene_graph` captions. load lora.safetensors (at 1 strength recommended) or lora_latest.safetensors (at 0.7 strength recommended) directly to your comfyui lora loader `transformer/` is a stock `MOSSImageTransformer` (load it with the release `pipeline_moss_image.py`); the text encoder, tokenizer and VAE are the base repo's.