---
license: openrail
tags:
- stable-diffusion
- pytorch
- INT8
- text-to-image
base_model: stabilityai/sdxl-turbo
---

# Stable Diffusion XL Turbo - PyTorch INT8

This is a INT8 pytorch version of **stabilityai/sdxl-turbo**.

## Model Details
- **Model Type**: Stable Diffusion XL Turbo
- **Parameters**: 3.5B
- **Backend**: PyTorch
- **Quantization**: INT8
- **Memory Usage**: ~3.2GB
- **Conversion Date**: 2025-08-09

## Usage

### PyTorch INT8

```python


# PyTorch INT8 quantized model
from diffusers import StableDiffusionXLPipeline
import torch

# Load INT8 quantized model
pipe = StableDiffusionXLPipeline.from_pretrained(
    "Mitchins/sdxl-turbo-torch-int8",
    torch_dtype=torch.qint8,
    use_safetensors=True
)

# For CPU inference
pipe = pipe.to("cpu")

# Generate image
image = pipe("A beautiful landscape", num_inference_steps=20).images[0]
image.save("output.png")


```

## Performance

| Backend | Quantization | Memory | Speed (CPU) | Speed (GPU) | Quality |
|---------|-------------|---------|-------------|-------------|---------|
| PyTorch | INT8 | ~3.2GB | Good | Fast | Slightly Reduced |

## Limitations


- INT8 quantization may slightly reduce image quality
- Best suited for CPU inference or memory-constrained environments


## Citation

```bibtex
@misc{sdxl-turbo-pytorch-int8,
  title = {Stable Diffusion XL Turbo PyTorch INT8}
  author = {ImageAI Server Contributors}
  year = {2024}
  publisher = {HuggingFace}
  url = {https://huggingface.co/Mitchins/sdxl-turbo-torch-int8}
}
```

---
*Converted using ImageAI Server Model Converter v1.0*