MOSS-Image is an open-weight model from Comfy Org, released under Apache License 2.0. Its published files total 68.5 GB. It draws 1.5M downloads a month.
Repackaged model files for ComfyUI. - https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base - https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT - https://huggingface.co/darask0/MOSS-Image-color-depth-control Place the files in the following folders
Model Card
By Comfy Org, published under apache-2.0, revision 24147db865fc.
Repackaged model files for ComfyUI. - https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base - https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT - https://huggingface.co/darask0/MOSS-Image-color-depth-control Place the files in the following folders
Read Comfy Org's full model card
Repackaged model files for ComfyUI.
Original model repository:
- https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base
- https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT
- https://huggingface.co/darask0/MOSS-Image-color-depth-control
Place the files in the following folders:
ComfyUI/
├── models/
│ ├── diffusion_models/
│ │ ├── moss_image_base_bf16.safetensors
│ │ ├── moss_image_base_int8_convrot.safetensors
│ │ ├── moss_image_sft_bf16.safetensors
│ │ └── moss_image_sft_int8_convrot.safetensors
│ ├── loras/
│ │ └── moss_image_color_depth_control.safetensors
│ ├── text_encoders/
│ │ ├── qwen3.5_9b_bf16.safetensors
│ │ ├── qwen3.5_9b_int8_convrot.safetensors
│ │ └── qwen3.5_9b_w4a8_gptq.safetensors
│ ├── vae/
│ │ ├── flux2-vae_small.safetensors
│ │ └── flux2-vae.safetensors
Workflows
Identity and Version
- Repository
- Comfy-Org/MOSS-Image
- Publisher
- Comfy Org
- Task
- Not stated by the source
- Modality
- Other
- Library
- diffusion-single-file
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 24147db865fcdc207270f844777587223fed8d6e
- First published
- 2026-10-16
- Last updated
- 2026-10-22
Files and Weights
12 files, 68.5 GB in total. The weights are 10 files totalling 68.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| diffusion_models/moss_image_base_bf16.safetensors | Weights | 10.2 GB | cacd158728a1 |
| diffusion_models/moss_image_base_int8_convrot.safetensors | Weights | 5.4 GB | f601c1e11619 |
| diffusion_models/moss_image_sft_bf16.safetensors | Weights | 10.2 GB | f96738d8116d |
| diffusion_models/moss_image_sft_int8_convrot.safetensors | Weights | 5.4 GB | b4d1475bc7ee |
| loras/moss_image_color_depth_control.safetensors | Weights | 313.1 MB | e5c0c3efd05e |
| text_encoders/qwen3.5_9b_bf16.safetensors | Weights | 19.3 GB | 7e6e9f08d598 |
| text_encoders/qwen3.5_9b_int8_convrot.safetensors | Weights | 9.7 GB | 32e3787472f7 |
| text_encoders/qwen3.5_9b_w4a8_gptq.safetensors | Weights | 7.3 GB | 4cc6a1543ad2 |
| vae/flux2-vae.safetensors | Weights | 336.2 MB | 868fe7b343cc |
| vae/flux2-vae_small.safetensors | Weights | 249.5 MB | d8d52ba03647 |
| README.md | Documentation | 4.0 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 68.5 GB
Released by Comfy Org through its official repository on Hugging Face. Read the license.
Built From
- Derived from OpenMOSS-Team/MOSS-Image-Base
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 68.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Built on This Model
- Derived fromMOSS-Imagine_ComfyUI
Questions About MOSS-Image
Can I use MOSS-Image commercially?
Yes. MOSS-Image is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.