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

device = "xpu" if hasattr(torch,"xpu") and torch.xpu.is_available() else "mps" if hasattr(torch,"mps") and hasattr(torch.mps, "is_available") and torch.mps.is_available() else "cuda" if torch.cuda.is_available() else "cpu"

pipe = diffusers.StableDiffusionXLPipeline.from_pretrained("Disty0/NoobAI-XL-Vpred-v1.0-SDNQ-uint4-svd-r128", torch_dtype=torch.bfloat16)
pipe = pipe.to(device)

prompt = "masterpiece, best quality, artist:john_kafka, artist:nixeu, artist:quasarcake, chromatic aberration, film grain, horror (theme), limited palette, x-shaped pupils, high contrast, color contrast, cold colors, arlecchino (genshin impact), black theme, gritty, graphite (medium)"
negative_prompt = "nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthro"

image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=832,
    height=1216,
    num_inference_steps=28,
    guidance_scale=3.5,
    generator=torch.Generator().manual_seed(42),
).images[0]
image.save("noobai-xl-vpred-v1.0-sdnq-uint4-svd-r128.png")

Original BF16 vs SDNQ quantization comparison:

Quantization	Model Size	Visualization
Original BF16	5.14 GB	Original BF16
SDNQ UINT4	2.56 GB	SDNQ UINT4