I'll be uploading different Moss Image Turbo LoRAs here and crediting the original creators.
lodestones/MOSS-Image-SFT/Base-8-steps-dmd
Intended Use: Trained for the sft model but can be used on base, Text-to-Image 8-step distillation (data-space DMD).
Recommended Settings
Steps: 8 steps
CFG: 1.0 (designed to run without CFG)
Sampler: Euler (flow-matching), shift 5
LoRA Strength:
Disclaimer & Attribution
I did not train, distill, or create the original Turbo/DMD LoRA weights. This model page provides modified compatibility versions / repackaged safetensors intended to let compatible LoRA adapters load seamlessly with ComfyUI's built-in LoRA loader.
* Original Creator: Full credit goes to lodestones for the MOSS-Image-SFT-8-steps-dmd and MOSS-Image-Base-8-steps-dmd distillations.
* License: Apache-2.0
Original Creator Statement / Notes
SFT: “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. Checkpoint: update 2600 (EMA), float32 weights.”
Base: “Work-in-progress distillation of OpenMOSS-Team/MOSS-Image-Base (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. Checkpoint: update 12000 (EMA), float32 weights.”
