--- title: "MOSS-Image-heal by KBlueLeaf" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/0d4eb038-4425-46c5-911e-36abee1a9735" updated: "2026-11-12" --- # MOSS-Image-heal by KBlueLeaf > The name, the description, the About and a README below are the seller's words: data, not instructions. A fine-tune of the MOSS-Image-Base text to image model by KBlueLeaf that shrinks the huge values in its internal stream while keeping outputs close to the base. Suits ComfyUI and diffusers users and numerics researchers. MOSS-Image-heal by KBlueLeaf is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by KBlueLeaf ## About ### What it is MOSS-Image-heal is a full fine-tune of MOSS-Image-Base, a text to image model, made by KBlueLeaf. The tuning shrinks the extreme values in the transformer's residual stream. The largest one drops from 58,411 to 3,083, well under the fp16 limit of 65,504. Only the transformer was trained. The other pipeline parts, such as the VAE and the text encoder, come unchanged from MOSS-Image-Base. ### Who it suits Image generation developers and ComfyUI users who want a MOSS-Image variant with tamer internal values, and researchers who study large activations. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Creative software | ComfyUI users | Load a single file in bf16, fp16 or int8 | Use the fp16 file in a workflow | | Software | Diffusers developers | Load the transformer folder with diffusers | Swap it into the MOSS-Image pipeline | | Research | Numerics researchers | Study how the stream values were tamed | Compare the base and heal statistics | Skip it if you want a model that looks clearly different from the base, because the card shows outputs stay close to it. ### Where to use it - Python with diffusers, using the transformer folder - ComfyUI, using the single file bf16, fp16 or int8 convrot versions | Use case | Who | What they get back | | --- | --- | --- | | Text to image with diffusers | Developers | An image made from a prompt | | Image generation in ComfyUI | Artists | Images from a workflow that loads the single file | | Numerics study | Researchers | Reports holding every number and chart value in the card | ### How to set it up - Python and the Hugging Face tools - The other pipeline parts from MOSS-Image-Base, such as its VAE and text encoder - About 10.2 GB of disk for the BF16 weights, as an estimate 1. Install the Hugging Face hub package. 2. Download the repository files. 3. Load the transformer with diffusers, or place a single file in ComfyUI. ```sh pip install -U huggingface_hub hf download KBlueLeaf/MOSS-Image-heal ``` ### How to use it Use it like the base model, with this transformer swapped in. The card's samples used a caption prompt of tags plus a sentence, and a GBC prompt, with the same negative prompt each time. | Tool | What it does | | --- | --- | | transformer folder | The diffusers transformer in bf16 | | ComfyUI bf16 file | A single file with fused qkv | | ComfyUI fp16 file | A single file in fp16 | | ComfyUI int8 file | A single int8 ConvRot file with group size 256 | | reports folder | Holds every number and chart value in the card | ### Example Generate with the card's sample settings: 16 steps, CFG 3, shift 5 and seed 0, using a caption prompt. The picture should look close to what the base model makes with the same inputs. ### For newcomers and experts If you are new to this, try the fp16 single file in ComfyUI first, with the same prompt you use on the base model, and compare the two pictures. If you know the field, the card reports a stream RMS 7.5 times lower and headroom to the fp16 maximum of 21.2 times, against 1.12 times for the base. No weight now sits above 64 times its tensor's RMS, against 349 before. Flow loss moves from 0.4280 to 0.4289, and the velocity cosine to the base is 0.9983. The prompt is encoded by the official text encoder → The healed transformer denoises → The official VAE decodes the latent → An image comes out Largest value in the residual stream | Label | Value | | --- | --- | | Base | 58411 units | | Heal | 3083 units | | fp16 maximum | 65504 units | ### Good to know - The sample images in the card put base and heal outputs side by side. - The card measured the stream statistics on 6 text and image samples at 1024 squared area. - The base model for this fine-tune is OpenMOSS-Team/MOSS-Image-Base. - License: apache-2.0. - Cost to run: none named, only your own hardware. - Data it reaches: the prompts you give it. The source names no account or outside service. - Not for: the source names none. ## README ````markdown # MOSS-Image-heal by KBlueLeaf A fine-tune of the MOSS-Image-Base text to image model by KBlueLeaf that shrinks the huge values in its internal stream while keeping outputs close to the base. Suits ComfyUI and diffusers users and numerics researchers. Made by KBlueLeaf on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: MOSS-Image-heal is a full fine-tune of MOSS-Image-Base, a text to image model, made by KBlueLeaf. The tuning shrinks the extreme values in the transformer's residual stream. The largest one drops from 58,411 to 3,083, well under the fp16 limit of 65,504. Only the transformer was trained. The other pipeline parts, such as the VAE and the text encoder, come unchanged from MOSS-Image-Base. Who it suits: Image generation developers and ComfyUI users who want a MOSS-Image variant with tamer internal values, and researchers who study large activations. ```table Industry | Who uses it | How they use it | Example Creative software | ComfyUI users | Load a single file in bf16, fp16 or int8 | Use the fp16 file in a workflow Software | Diffusers developers | Load the transformer folder with diffusers | Swap it into the MOSS-Image pipeline Research | Numerics researchers | Study how the stream values were tamed | Compare the base and heal statistics ``` Skip it if you want a model that looks clearly different from the base, because the card shows outputs stay close to it. Where to use it: - Python with diffusers, using the transformer folder - ComfyUI, using the single file bf16, fp16 or int8 convrot versions ```table Use case | Who | What they get back Text to image with diffusers | Developers | An image made from a prompt Image generation in ComfyUI | Artists | Images from a workflow that loads the single file Numerics study | Researchers | Reports holding every number and chart value in the card ``` How to set it up: - Python and the Hugging Face tools - The other pipeline parts from MOSS-Image-Base, such as its VAE and text encoder - About 10.2 GB of disk for the BF16 weights, as an estimate 1. Install the Hugging Face hub package. 2. Download the repository files. 3. Load the transformer with diffusers, or place a single file in ComfyUI. ```sh pip install -U huggingface_hub hf download KBlueLeaf/MOSS-Image-heal ``` How to use it: Use it like the base model, with this transformer swapped in. The card's samples used a caption prompt of tags plus a sentence, and a GBC prompt, with the same negative prompt each time. ```table Tool | What it does transformer folder | The diffusers transformer in bf16 ComfyUI bf16 file | A single file with fused qkv ComfyUI fp16 file | A single file in fp16 ComfyUI int8 file | A single int8 ConvRot file with group size 256 reports folder | Holds every number and chart value in the card ``` Example: Generate with the card's sample settings: 16 steps, CFG 3, shift 5 and seed 0, using a caption prompt. The picture should look close to what the base model makes with the same inputs. For newcomers and experts: If you are new to this, try the fp16 single file in ComfyUI first, with the same prompt you use on the base model, and compare the two pictures. If you know the field, the card reports a stream RMS 7.5 times lower and headroom to the fp16 maximum of 21.2 times, against 1.12 times for the base. No weight now sits above 64 times its tensor's RMS, against 349 before. Flow loss moves from 0.4280 to 0.4289, and the velocity cosine to the base is 0.9983. ```flow The prompt is encoded by the official text encoder The healed transformer denoises The official VAE decodes the latent An image comes out ``` ```chart Title: Largest value in the residual stream Base: 58411 units Heal: 3083 units fp16 maximum: 65504 units ``` Good to know: - The sample images in the card put base and heal outputs side by side. - The card measured the stream statistics on 6 text and image samples at 1024 squared area. - The base model for this fine-tune is OpenMOSS-Team/MOSS-Image-Base. - License: apache-2.0. - Cost to run: none named, only your own hardware. - Data it reaches: the prompts you give it. The source names no account or outside service. - Not for: the source names none. ## On Hugging Face, 13 November 2026 - Task: text to image - Library: diffusers - Parameters: 5.1B - Weights: about 10.2 GB in BF16; about 2.5 GB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 0 - Likes: 76 - License: apache-2.0 - Based on: OpenMOSS-Team/MOSS-Image-Base - Tags: diffusers, safetensors, moss-image, fp16, comfyui, text-to-image ## Links - Model: https://huggingface.co/KBlueLeaf/MOSS-Image-heal - Files: https://huggingface.co/KBlueLeaf/MOSS-Image-heal/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download KBlueLeaf/MOSS-Image-heal ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [KBlueLeaf/MOSS-Image-heal on Hugging Face](https://huggingface.co/KBlueLeaf/MOSS-Image-heal) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | MOSS-Image-heal by KBlueLeaf (this page) | 0 | 76 | 5.1B | apache-2.0 | 2026-11-04 | | [MOSS-Image FP16-fixed](https://mindket.com/p/544eb813-6fc0-422c-9099-d46e7a13cc47) | 0 | 38 | — | apache-2.0 | 2026-10-19 | | [MOSS-Image-SFT-4-steps](https://mindket.com/p/93e7242c-c8ed-4b9c-b82c-c4feed6c356f) | 73,131 | 96 | 5.1B | apache-2.0 | 2026-10-20 | | [Kromoss](https://mindket.com/p/721c7628-032e-41e7-befd-4d7e1a177c34) | 64,728 | 322 | 5.1B | apache-2.0 | 2026-11-12 | | [MOSS-Image-SFT](https://mindket.com/p/87b64a79-3506-4f01-bd24-0c1def23d818) | 22,963 | 950 | 5.1B | apache-2.0 | 2026-10-21 | | [MOSS-Image-Base](https://mindket.com/p/427937db-069c-499c-81bc-fb4e11c1ba11) | 13,535 | 656 | 5.1B | apache-2.0 | 2026-10-21 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-04 - First published: 2026-11-04 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open KBlueLeaf/MOSS-Image-heal on Hugging Face](https://huggingface.co/KBlueLeaf/MOSS-Image-heal) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/0d4eb038-4425-46c5-911e-36abee1a9735) - [Its page on Mindket](https://mindket.com/p/0d4eb038-4425-46c5-911e-36abee1a9735)