Comfy-Org/MOSS-Image — new model trending #30 on Hugging Face
Comfy-Org republished MOSS-Image weights packaged for ComfyUI, now trending on Hugging Face.
Comfy-Org/MOSS-Image publishes repackaged MOSS-Image weights for ComfyUI and was trending at number 30 on Hugging Face. The files come from OpenMOSS-Team’s MOSS-Image-Base and MOSS-Image-SFT repositories. Diffusion weights are provided in bf16 and int8 ConvRot formats, alongside Qwen3.5 9B text encoders in bf16, int8, and W4A8 GPTQ, plus Flux2 VAE files.
- ComfyUI repack of OpenMOSS MOSS-Image-Base and MOSS-Image-SFT.
- Includes bf16 and int8 ConvRot diffusion weights for both variants.
- Bundles Qwen3.5 9B text encoders and Flux2 VAE files.
- Trending at number 30 on Hugging Face.
Full article76 words · extracted from huggingface.co · click to collapse
# MOSS-image
Repackaged model files for ComfyUI.
Original model repository:
- https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base
- https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT
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
│ ├── 📂 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
```
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/Comfy-Org/MOSS-Image