import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers

pipe = diffusers.QwenImagePipeline.from_pretrained("Disty0/Qwen-Image-Lightning-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "a tiny astronaut hatching from an egg on the moon, Ultra HD, 4K, cinematic composition."
negative_prompt = " "
image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=1024,
    height=1024,
    num_inference_steps=8,
    true_cfg_scale=1.0,
    generator=torch.manual_seed(0),
).images[0]

image.save("qwen-image-lightning-sdnq-uint4-svd-r32.png")

Original BF16 vs SDNQ quantization comparison:

Quantization	Model Size	Visualization
Original BF16	40.9 GB	Original BF16
SDNQ UINT4	11.6 GB	SDNQ UINT4