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

pipe = diffusers.FluxPipeline.from_pretrained("Disty0/FLUX.1-schnell-SDNQ-uint4-svd-r32", torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()

prompt = "A cat holding a sign that says hello world"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=0.0,
    num_inference_steps=4,
    max_sequence_length=256,
    generator=torch.manual_seed(0)
).images[0]
image.save("flux-dev-sdnq-uint4-svd-r32.png")

Original BF16 vs SDNQ quantization comparison:

Quantization	Model Size	Visualization
Original BF16	23.8 GB	Original BF16
SDNQ UINT4	6.8 GB	SDNQ UINT4