Qwen-Image-SDNQ-uint4-svd-r32

pip install sdnq

import torch
import diffusers
from sdnq import SDNQConfig # import sdnq to register it into diffusers and transformers
from sdnq.common import use_torch_compile as triton_is_available
from sdnq.loader import apply_sdnq_options_to_model

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

# Enable INT8 MatMul for AMD, Intel ARC and Nvidia GPUs:
if triton_is_available and (torch.cuda.is_available() or torch.xpu.is_available()):
    pipe.transformer = apply_sdnq_options_to_model(pipe.transformer, use_quantized_matmul=True)
    pipe.text_encoder = apply_sdnq_options_to_model(pipe.text_encoder, use_quantized_matmul=True)
    # pipe.transformer = torch.compile(pipe.transformer) # optional for faster speeds

pipe.enable_model_cpu_offload()

positive_magic = {
    "en": ", Ultra HD, 4K, cinematic composition.", # for english prompt
    "zh": ", 超清，4K，电影级构图." # for chinese prompt
}

# Generate image
prompt = '''A coffee shop entrance features a chalkboard sign reading "Qwen Coffee 😊 $2 per cup," with a neon light beside it displaying "通义千问". Next to it hangs a poster showing a beautiful Chinese woman, and beneath the poster is written "π≈3.1415926-53589793-23846264-33832795-02384197". Ultra HD, 4K, cinematic composition'''

negative_prompt = " " # using an empty string if you do not have specific concept to remove


# Generate with different aspect ratios
aspect_ratios = {
    "1:1": (1328, 1328),
    "16:9": (1664, 928),
    "9:16": (928, 1664),
    "4:3": (1472, 1140),
    "3:4": (1140, 1472),
    "3:2": (1584, 1056),
    "2:3": (1056, 1584),
}

width, height = aspect_ratios["16:9"]

image = pipe(
    prompt=prompt + positive_magic["en"],
    negative_prompt=negative_prompt,
    width=width,
    height=height,
    num_inference_steps=50,
    true_cfg_scale=4.0,
    generator=torch.Generator(device="cpu").manual_seed(42)
).images[0]

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