textual_inversion_dicoo_dfq

# Distillation for quantization on Textual Inversion models to personalize text2image with Intel® Neural Compressor

<p float="left">
<img src="https://huggingface.co/datasets/Intel/textual_inversion_dicoo_dfq/resolve/main/FP32.png" width = "300" height = "300" alt="FP32" align=center />
<img src="https://huggingface.co/datasets/Intel/textual_inversion_dicoo_dfq/resolve/main/INT8.png" width = "300" height = "300" alt="INT8" align=center />
</p>

Image on the top is generated from the FP32 finetuned stable diffusion model, bottom image is generated from the INT8 stable diffusion model which is quantized from the FP32 model by distillation for quantization approach.
<br>
Please refer to this <a href="https://github.com/intel/neural-compressor/tree/master/examples/pytorch/diffusion_model/diffusers/textual_inversion/distillation_for_quantization">example</a> of Intel® Neural Compressor for more detail.

# 基于英特尔®神经压缩器（Intel® Neural Compressor）的文本反演（Textual Inversion）模型量化蒸馏技术：实现文生图个性化

<p float="left">
<img src="https://huggingface.co/datasets/Intel/textual_inversion_dicoo_dfq/resolve/main/FP32.png" width = "300" height = "300" alt="FP32" align=center />
<img src="https://huggingface.co/datasets/Intel/textual_inversion_dicoo_dfq/resolve/main/INT8.png" width = "300" height = "300" alt="INT8" align=center />
</p>

上方图片由经32位浮点精度（FP32）微调的稳定扩散（Stable Diffusion）模型生成，下方图片则由通过量化蒸馏方法从FP32模型量化得到的8位整型精度（INT8）稳定扩散模型生成。
<br>
欲了解更多细节，请参阅英特尔®神经压缩器（Intel® Neural Compressor）的该<a href="https://github.com/intel/neural-compressor/tree/master/examples/pytorch/diffusion_model/diffusers/textual_inversion/distillation_for_quantization">示例项目</a>。