nunchaku/examples/v1/qwen-image-edit-2509-lightning.py at f6200d9541784e4ab3008870c5610317bfc28cd0 · nunchaku-ai/nunchaku · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
import math

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

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

# From https://github.com/ModelTC/Qwen-Image-Lightning/blob/342260e8f5468d2f24d084ce04f55e101007118b/generate_with_diffusers.py#L82C9-L97C10
scheduler_config = {
    "base_image_seq_len": 256,
    "base_shift": math.log(3),  # We use shift=3 in distillation
    "invert_sigmas": False,
    "max_image_seq_len": 8192,
    "max_shift": math.log(3),  # We use shift=3 in distillation
    "num_train_timesteps": 1000,
    "shift": 1.0,
    "shift_terminal": None,  # set shift_terminal to None
    "stochastic_sampling": False,
    "time_shift_type": "exponential",
    "use_beta_sigmas": False,
    "use_dynamic_shifting": True,
    "use_exponential_sigmas": False,
    "use_karras_sigmas": False,
}
scheduler = FlowMatchEulerDiscreteScheduler.from_config(scheduler_config)

num_inference_steps = 4  # you can also use the 8-step model to improve the quality
rank = 32  # you can also use the rank=128 model to improve the quality
model_path = f"nunchaku-tech/nunchaku-qwen-image-edit-2509-lightning/svdq-{get_precision()}_r{rank}-qwen-image-edit-2509-lightningv2.0-{num_inference_steps}steps.safetensors"

# Load the model
transformer = NunchakuQwenImageTransformer2DModel.from_pretrained(model_path)

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": 1.0,
    "num_inference_steps": num_inference_steps,
}

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