ming-image-0.1-design-layer-fp8 (community quant, unofficial)

static selective fp8 quantization of inclusionAI/Ming-Image-0.1-Design-Layer (mit license).

metric	upstream (bf16/fp32)	this quant (fp8 e4m3)	reduction
total size	~61 GB	~25 GB	-59%
scheme	mixed bf16/fp32	selective f8_e4m3 + bf16	0 / 15,365 saturated
linears	2d linear weights	f8_e4m3	norms/embeds/moe/vae kept

quantization details

• linear layers: converted to torch.float8_e4m3fn with saturating cast.
• preserved precision: rmsnorm, token embeddings, moe routing gates, biases, vae, and mlp prediction heads remain in native precision (bf16/fp32).
• quality: verified zero saturation across all 15,365 cast tensors (max|w| <= 448). deterministic, calibration-free.
• audit: see quant_report.json for per-file layer statistics.

how to load & run

layout mirrors upstream (connector/, mllm/, transformer/, vae/).

1. dequantize on load (in-memory)

load fp8 safetensors and cast to bf16 in memory to reduce disk footprint and transfer bandwidth:

import torch
from safetensors.torch import load_file

def load_fp8_state_dict(safetensors_path: str, target_dtype=torch.bfloat16):
    state_dict = load_file(safetensors_path)
    for k, v in state_dict.items():
        if v.dtype == torch.float8_e4m3fn:
            state_dict[k] = v.to(target_dtype)
    return state_dict

2. upstream inference

use the official Ming-Image repository:

git clone https://github.com/inclusionAI/Ming-Image
cd Ming-Image
pip install -r requirements.txt

python infer.py \
  --model 6chan/Ming-Image-0.1-Design-Layer-FP8 \
  --task layer-decompose \
  --input-image assets/layer_samples/card_making_input.png \
  --prompt assets/layer_samples/card_making_prompt.txt \
  --attn-implementation flash_attention_2 \
  --resolution 1024 \
  --output-dir outputs/layers

comfyui status

no official loader exists for the layer checkpoint yet. comfyui support will be developed as a standalone custom node wrapper handling bailingmm2 conditioning and multi-frame rgba latents.

acknowledgements & links

• original model: inclusionAI/Ming-Image-0.1-Design-Layer
• demo space: Xiaolong-Wang/Ming-Image-0.1-Design-Layer
• source repo: inclusionAI/Ming-Image
• license: MIT