qwen-image-edit-2509.py

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

from nunchaku import NunchakuQwenImageTransformer2DModel
from nunchaku.utils import get_gpu_memory, get_precision

rank = 128  # you can also use rank=128 model to improve the quality

# Load the model
transformer = NunchakuQwenImageTransformer2DModel.from_pretrained(
    f"nunchaku-tech/nunchaku-qwen-image-edit-2509/svdq-{get_precision()}_r{rank}-qwen-image-edit-2509.safetensors"
)

pipeline = QwenImageEditPlusPipeline.from_pretrained(
    "Qwen/Qwen-Image-Edit-2509", transformer=transformer, torch_dtype=torch.bfloat16
)

if get_gpu_memory() > 18:
    pipeline.enable_model_cpu_offload()
else:
    # use per-layer offloading for low VRAM. This only requires 3-4GB of VRAM.
    transformer.set_offload(
        True, use_pin_memory=False, num_blocks_on_gpu=1
    )  # increase num_blocks_on_gpu if you have more VRAM
    pipeline._exclude_from_cpu_offload.append("transformer")
    pipeline.enable_sequential_cpu_offload()

image1 = load_image("https://huggingface.co/datasets/nunchaku-tech/test-data/resolve/main/inputs/man.png")
image1 = image1.convert("RGB")
image2 = load_image("https://huggingface.co/datasets/nunchaku-tech/test-data/resolve/main/inputs/puppy.png")
image2 = image2.convert("RGB")
image3 = load_image("https://huggingface.co/datasets/nunchaku-tech/test-data/resolve/main/inputs/sofa.png")
image3 = image3.convert("RGB")

prompt = "Let the man in image 1 lie on the sofa in image 3, and let the puppy in image 2 lie on the floor to sleep."
inputs = {
    "image": [image1, image2, image3],
    "prompt": prompt,
    "true_cfg_scale": 4.0,
    "negative_prompt": " ",
    "num_inference_steps": 40,
}

output = pipeline(**inputs)
output_image = output.images[0]
output_image.save(f"qwen-image-edit-2509-r{rank}.png")