KBlueLeaf/MOSS-Image-heal
text-to-image model by KBlueLeaf
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.
A full finetune of MOSS-Image-Base with a healed residual stream: the largest stream value is 3,083 (base: 58,411; fp16 max: 65,504), the stream RMS is 7.5x lower, and every weight element is within 64x its tensor's RMS (base: 349 elements above). The outputs stay close to the base model: flow loss 0.4289 vs 0.4280, velocity cosine 0.9983 on the probe set below. The transformer is the trained part. Text encoder, tokenizer, VAE, scheduler and pipeline code are the official MOSS-Image-Base ones. The concepts behind this model are written up in KohakuMoss: the few huge channels of the base model's residual stream, what they do, and how a heal shrinks them. the stream losses (write concentration, RMS) and the outlier decay of the weights used in this run, with a toy model and their combination. the fp16 residual-stream fold the training ran with. Base | heal, with the caption prompt (tags…
Read the full model card ↗ · Preview checked 2026-11-07T09:56:48.931Z
Inside the original model card — Document outline
- MOSS-Image-heal
- Samples
- Residual stream
- Weights
- Precision of the files
- Training
- Data
- Usage
- diffusers
- ComfyUI
- KohakuMoss
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
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
KBlueLeaf/MOSS-Image-heal is a text-to-image model repository published by KBlueLeaf 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
- text-to-image
- Library
- diffusers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 54
- Hugging Face trending score
- 53
- Reported safetensors parameters
- 5,082,308,624
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-04T05:39:41.000Z
- Last modified
- 2026-11-04T09:15:52.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: OpenMOSS-Team/MOSS-Image-Base
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 2026-11-07T06:52:25.630Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
stabilityai/stable-diffusion-xl-base-1.0
abenzerps/Qwen-Image-2.1-Uncensored-Quantized