MOSS-Image-Base 8step
Note: All model files and custom nodes below must be downloaded via the client. If you do not have the client, Download >>>
MOSS‑Image is an open-source AI image generation model developed by OpenMOSS. It supports Chinese and English prompts, and its biggest highlight is the ability to precisely control the position of text and objects in images, making it great for creating posters and graphic pictures. It comes in two versions: Base and SFT. The Base is the original basic model, more suitable for developers to modify and retrain, but it does not work well for ordinary users for direct drawing and struggles to understand prompts. SFT is an optimized version built on Base. Regular users can use it right away. It understands your text requests better and produces images with more stable layouts and text effects. Choose SFT first for daily creation.
| Name | Size | Target Dir |
|---|
| qwen3.5_9b_w4a8_gptq.safetensors | 7.34 GB | text_encoders |
| qwen3.5_9b_int8_convrot.safetensors | 9.75 GB | text_encoders |
| qwen3.5_9b_bf16.safetensors | 19.31 GB | text_encoders |
| Name | Size | Target Dir |
|---|
| MOSS-Image-Base-8-steps-dmd.safetensors | 1.19 GB | loras |
| Name | Size | Target Dir |
|---|
| flux2-vae_small.safetensors | 249.52 MB | vae |
| flux2-vae.safetensors | 336.21 MB | vae |
| Name | Size | Target Dir |
|---|
| moss_image_base_int8_convrot.safetensors | 5.41 GB | diffusion_models |
| moss_image_sft_int8_convrot.safetensors | 5.41 GB | diffusion_models |
| moss_image_base_bf16.safetensors | 10.16 GB | diffusion_models |
| moss_image_sft_bf16.safetensors | 10.16 GB | diffusion_models |
