| ---
|
| license: apache-2.0
|
| base_model: OpenMOSS-Team/MOSS-Image-SFT
|
| base_model_relation: quantized
|
| language:
|
| - en
|
| - zh
|
| pipeline_tag: text-to-image
|
| library_name: comfyui
|
| tags:
|
| - moss-image
|
| - comfyui
|
| - text-to-image
|
| - quantized
|
| - int8
|
| - w4a8
|
| - gptq
|
| - convrot
|
| ---
|
|
|
| # MOSS-Image-SFT — INT8 / W4A8 ConvRot (ComfyUI)
|
|
|
| Single-file, ComfyUI-ready quantization of
|
| [**OpenMOSS-Team/MOSS-Image-SFT**](https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT)
|
| (code and docs: [OpenMOSS/MOSS-Image](https://github.com/OpenMOSS/MOSS-Image)).
|
| All credit for the model goes to OpenMOSS; this repo only re-packages the weights.
|
|
|
| | Component | Format | Size | Original |
|
| |---|---|---|---|
|
| | Diffusion model (DiT, 42 blocks) | **INT8 ConvRot** | 5.41 GB | 10.16 GB (bf16) |
|
| | Text encoder (Qwen3.5-9B) | **W4A8 GPTQ ConvRot** | 5.43 GB | 16.79 GB (bf16) |
|
| | VAE (`AutoencoderKLFlux2`) | **bf16** | 125 MB | 250 MB (fp32) |
|
|
|
| ## File layout
|
|
|
| ```
|
| MOSS-Image-SFT-INT8-W4A8-ConvRot/
|
| ├── diffusion_models/
|
| │ └── moss_image_sft_int8_convrot.safetensors # 5.41 GB
|
| ├── text_encoders/
|
| │ └── qwen3.5_9b_moss_image_sft_w4a8_gptq.safetensors # 5.43 GB
|
| ├── vae/
|
| │ └── moss_image_vae_bf16.safetensors # 125 MB
|
| └── assets/ # comparison images
|
| ```
|
|
|
| Drop each file into the matching folder of your ComfyUI `models/` directory.
|
|
|
| ## Usage (ComfyUI)
|
|
|
| 1. Install the official node pack from the
|
| [MOSS-Image ComfyUI guide](https://github.com/OpenMOSS/MOSS-Image/blob/main/comfyui/README.md)
|
| (copy `comfyui/moss-image` into `custom_nodes/`). ComfyUI needs
|
| [comfy-kitchen](https://github.com/Comfy-Org/comfy-kitchen) quantized-op support; the
|
| quantization type is auto-detected from the files.
|
| 2. Load with the plugin's single-file loaders:
|
| - **MOSSImageUNETLoader** → `moss_image_sft_int8_convrot.safetensors`
|
| - **MOSSImageCLIPLoader** → `qwen3.5_9b_moss_image_sft_w4a8_gptq.safetensors`
|
| - **VAELoader** → `moss_image_vae_bf16.safetensors`
|
| 3. Use the official SFT sampling settings: **Euler**, 50 steps, **CFG 3**, `ModelSamplingSD3` shift **5**,
|
| uncond skip-layer **22**.
|
|
|
| Tested end-to-end in stock ComfyUI on an 8 GB RTX 3060 Ti (≈210 s for 1024×1536, 50 steps).
|
|
|
| ## How it was made
|
|
|
| - **DiT:** all 252 block linears (`layers.N.proj.{q,k,v,o,ffn_up_gate,ffn_down}`) quantized to INT8 with a
|
| group-Hadamard (size 256) ConvRot rotation and per-output-channel scales. Embedders, modulation,
|
| final layers and norms are kept in original precision.
|
| - **Text encoder:** the 200 body linears (attention / linear-attention / MLP) quantized to 4-bit weights
|
| (group 16, fp8 relative scales) with 8-bit activations, using GPTQ run in the rotated basis. Calibration used
|
| the model's real chat template on the official example prompts and negatives plus public prompt datasets.
|
| Embeddings and the vision tower are INT8 ConvRot; everything else is unchanged.
|
| - **VAE:** plain fp32 → bf16 cast.
|
|
|
| ## Quality check
|
|
|
| 50 steps, official sizes, same seed, cfg 3. Left → right in each strip: original bf16 pipeline ·
|
| bf16 VAE · INT8 DiT · everything quantized (INT8 DiT + W4A8 text encoder + bf16 VAE).
|
|
|
| 
|
| 
|
| 
|
|
|
| - bf16 VAE vs. fp32 decode: **~54 dB PSNR** (visually identical).
|
| - Quantized DiT / full stack diverge in fine detail over the 50-step trajectory (PSNR 19–27 dB vs. the
|
| original output), but composition, identity, style, lighting and rendered text are preserved.
|
| - Text-encoder `last_hidden_state` cosine vs. bf16: ≈ 0.996 (mean over tokens, first example prompt).
|
|
|
| Limitations: only three prompts were compared visually; the original model card recommends an fp32 VAE, which
|
| is the safest choice if you see banding. Results in ComfyUI's sampler will not match the diffusers pipeline
|
| pixel for pixel.
|
|
|
| ## Checksums (SHA-256)
|
|
|
| ```
|
| ffd98820ac8f0f57c48386bd98852720de50c3acb502f73fd641d0cd9df6d0af moss_image_sft_int8_convrot.safetensors
|
| b5f31a430e4912decb152f3a0761350f52282176823b597edd43b2e3f6403da4 qwen3.5_9b_moss_image_sft_w4a8_gptq.safetensors
|
| 81a27c7135775f149648fa35a58eec6d78a3e6a9bb9273885b51895cbc212d5d moss_image_vae_bf16.safetensors
|
| ```
|
|
|
| ## License & attribution
|
|
|
| Apache-2.0, same as the original. Original model, architecture and pipeline © OpenMOSS-Team
|
| ([MOSS-Image-Base](https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base),
|
| [MOSS-Image-SFT](https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT),
|
| [technical report](https://github.com/OpenMOSS/MOSS-Image/blob/main/paper/MOSS_Image_Technical_Report.pdf)).
|
| This repo is an unofficial community quantization and is not affiliated with OpenMOSS.
|
|
|
