Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909302273343488 |
|---|---|
| author | Egiazarian, Vage Kuznedelev, Denis Voronov, Anton Svirschevski, Ruslan Goin, Michael Pavlov, Daniil Alistarh, Dan Baranchuk, Dmitry |
| author_facet | Egiazarian, Vage Kuznedelev, Denis Voronov, Anton Svirschevski, Ruslan Goin, Michael Pavlov, Daniil Alistarh, Dan Baranchuk, Dmitry |
| contents | Text-to-image diffusion models have emerged as a powerful framework for high-quality image generation given textual prompts. Their success has driven the rapid development of production-grade diffusion models that consistently increase in size and already contain billions of parameters. As a result, state-of-the-art text-to-image models are becoming less accessible in practice, especially in resource-limited environments. Post-training quantization (PTQ) tackles this issue by compressing the pretrained model weights into lower-bit representations. Recent diffusion quantization techniques primarily rely on uniform scalar quantization, providing decent performance for the models compressed to 4 bits. This work demonstrates that more versatile vector quantization (VQ) may achieve higher compression rates for large-scale text-to-image diffusion models. Specifically, we tailor vector-based PTQ methods to recent billion-scale text-to-image models (SDXL and SDXL-Turbo), and show that the diffusion models of 2B+ parameters compressed to around 3 bits using VQ exhibit the similar image quality and textual alignment as previous 4-bit compression techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_00492 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization Egiazarian, Vage Kuznedelev, Denis Voronov, Anton Svirschevski, Ruslan Goin, Michael Pavlov, Daniil Alistarh, Dan Baranchuk, Dmitry Computer Vision and Pattern Recognition Text-to-image diffusion models have emerged as a powerful framework for high-quality image generation given textual prompts. Their success has driven the rapid development of production-grade diffusion models that consistently increase in size and already contain billions of parameters. As a result, state-of-the-art text-to-image models are becoming less accessible in practice, especially in resource-limited environments. Post-training quantization (PTQ) tackles this issue by compressing the pretrained model weights into lower-bit representations. Recent diffusion quantization techniques primarily rely on uniform scalar quantization, providing decent performance for the models compressed to 4 bits. This work demonstrates that more versatile vector quantization (VQ) may achieve higher compression rates for large-scale text-to-image diffusion models. Specifically, we tailor vector-based PTQ methods to recent billion-scale text-to-image models (SDXL and SDXL-Turbo), and show that the diffusion models of 2B+ parameters compressed to around 3 bits using VQ exhibit the similar image quality and textual alignment as previous 4-bit compression techniques. |
| title | Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.00492 |