This repository provides INT8 ConvRot quantizations for OpenMOSS-Team/MOSS-Image-SFT
moss-image_comfyUI_workflow.json.
The files are organized into standard ComfyUI directory paths:
Abiray/MOSS-Image-SFT-INT8-convrot/
├── diffusion_models/
│ └── moss-image-sft-dit-int8-convrot.safetensors # 5.41 GB (INT8 DiT Backbone)
├── text_encoders/
│ └── moss-image-sft-qwen35-int8-convrot.safetensors # 8.45 GB (INT8 Qwen3.5 Text Encoder)
├── vae/
│ └── moss-image-sft-vae.safetensors # 336 MB (FLUX.2 VAE, BF16)
└── moss-image_comfyUI_workflow.json # Ready-to-use ComfyUI workflow
Standard INT8 round-to-nearest (RTN) or naive absmax clipping often causes severe structural degradation in diffusion models due to high-magnitude activation outliers across specific channels.
ConvRot applies orthogonal Hadamard matrix rotations to the weights and activation spaces prior to quantization. This flattens outlier peaks, allowing fast 1-pass absmax INT8 mapping to maintain near-lossless fidelity.
| Component | Quantized Layers | Target Precision | Original BF16 | INT8 ConvRot | Mean Relative Error |
|---|---|---|---|---|---|
| DiT Transformer (5B) | 252 GEMM linear projections across 42 layers | INT8 (.comfy_quant) | ~10.0 GB | 5.41 GB | 0.868% (cos ~1.0005) |
| Qwen3.5 Text Encoder | 308 GEMM projections + rotated per-row embeddings | INT8 (.comfy_quant) | ~16.0 GB | 8.45 GB | 0.868% (cos ~1.0002) |
| VAE | Preserved in original BF16 | BF16 | 336 MB | 336 MB | Lossless (0.00%) |
All modulation layers, LayerNorms/RMSNorms, RoPE bands, and attention scale vectors are retained in original BF16/FP32 precision.
| Parameter | Recommended Value | Notes |
|---|---|---|
| Sampler | Euler / Flow-matching | Default ODE solver |
| Sampling Steps | 30 – 50 | 50 steps provide maximum detail |
| CFG Scale | 3.0 | Recommended range: 2.5 – 3.5 |
| Flow Shift | 5.0 | Standard flow sigma shift |
| Resolutions | 1024x1024, 768x1360, 1360x768 | Width and height must be multiples of 16 |
Run this Python script inside your ComfyUI environment to place each model directly into its respective folder:
import os
from huggingface_hub import hf_hub_download
COMFY_ROOT = "/path/to/ComfyUI/models" # e.g., /tmp/workspace/ComfyUI/models
REPO_ID = "Abiray/MOSS-Image-SFT-INT8-convrot"
files = [
("diffusion_models", "moss-image-sft-dit-int8-convrot.safetensors"),
("text_encoders", "moss-image-sft-qwen35-int8-convrot.safetensors"),
("vae", "moss-image-sft-vae.safetensors"),
]
for subfolder, filename in files:
target_path = f"{subfolder}/{filename}"
print(f"⬇️ Downloading {filename}...")
hf_hub_download(
repo_id=REPO_ID,
filename=target_path,
local_dir=COMFY_ROOT,
)
print("✅ All models downloaded successfully!")
moss-image_comfyUI_workflow.json from this repository..json file into your ComfyUI window.moss-image-sft-dit-int8-convrot.safetensorsmoss-image-sft-qwen35-int8-convrot.safetensorsmoss-image-sft-vae.safetensors