Qwen-Image-Edit-2511-FP8-Diffusers

Qwen-Image-Edit-2511-FP8-Diffusers

This repository contains a Diffusers-compatible FP8 (torch.float8_e4m3fn) quantized version of the Qwen/Qwen-Image-Edit-2511 model.

Model Overview

• Base Model: Qwen/Qwen-Image-Edit-2511
• Quantization: FP8 (torch.float8_e4m3fn) on the transformer component.
• Pipeline Compatibility: Hugging Face Diffusers (QwenImageEditPlusPipeline).
• License: Apache 2.0 (Inherited from upstream base model).

For detailed model architecture, training details, and evaluations, please refer to the official Qwen/Qwen-Image-Edit-2511 repository.

Usage Example

import torch
from diffusers import QwenImageEditPlusPipeline
from diffusers.utils import load_image

pipe = QwenImageEditPlusPipeline.from_pretrained(
    "milan33/Qwen-Image-Edit-2511-FP8-Diffusers",
    torch_dtype=torch.bfloat16,
).to("cuda")

input_image = load_image("https://example.com/input.jpg")

output_image = pipe(
    prompt="A realistic tattoo on forearm",
    image=[input_image],
    num_inference_steps=20,
    guidance_scale=4.5,
    height=1024,
    width=768,
).images[0]

output_image.save("output.png")

License

This model is released under the Apache License 2.0, consistent with the original Qwen/Qwen-Image-Edit-2511 release.