---
license: apache-2.0
base_model:
- vladmandic/Qwen-Lightning
base_model_relation: quantized
library_name: diffusers
tags:
- sdnq
- qwen_image
- 4-bit
---
4 bit (UINT4 with SVD rank 32) quantization of [vladmandic/Qwen-Lightning](https://huggingface.co/vladmandic/Qwen-Lightning) using [SDNQ](https://github.com/vladmandic/sdnext/wiki/SDNQ-Quantization).  

Usage:  
```
pip install git+https://github.com/Disty0/sdnq
```

```py
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](https://cdn-uploads.huggingface.co/production/uploads/6456af6195082f722d178522/OQ9vhQij2b4tBMxzlOa4e.png) |
| SDNQ UINT4 | 11.6 GB | ![SDNQ UINT4](https://cdn-uploads.huggingface.co/production/uploads/6456af6195082f722d178522/i803Rv8HAwhi8b0H1J-jU.png) |