lodestones/MOSS-Image-SFT-8-steps-dmd
AI model by lodestones
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
https://huggingface.co/spaces/hugging-apps/moss-image-8-step-dmd 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 scenegraph captions. Checkpoint: update 2600 (EMA), float32 weights. load lora.safetensors (at 1 strength recommended) or loralatest.safetensors (at 0.7 strength recommended) directly to your comfyui lora loader transformer/ is a stock MOSSImageTransformer (load it with the release pipelinemossimage.py); the text encoder, tokenizer and VAE are the base repo's. Precision: the distillation delta is smaller than bf16's rounding step, so transformer/ must be loaded AND run in fp32 (torchdtype=torch.float32, no autocast); casting it to bf16…
Read the full model card ↗ · Preview checked 2026-10-30T12:32:29.939Z
Inside the original model card — Document outline
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
lodestones/MOSS-Image-SFT-8-steps-dmd is a task-unspecified model repository published by lodestones on Hugging Face. The source reports the diffusers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- Not reported
- Library
- diffusers
- Recent downloads (30 days)
- 145,445
- Cumulative likes
- 213
- Hugging Face trending score
- 62
- Reported safetensors parameters
- 5,082,308,624
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-16T10:28:56.000Z
- Last modified
- 2026-10-17T03:44:54.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: OpenMOSS-Team/MOSS-Image-SFT
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-26T06:46:02.726Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.