SDXL-Lightning: Progressive Adversarial Diffusion Distillation
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_ | 1866910350026211328 |
|---|---|
| author | Lin, Shanchuan Wang, Anran Yang, Xiao |
| author_facet | Lin, Shanchuan Wang, Anran Yang, Xiao |
| contents | We propose a diffusion distillation method that achieves new state-of-the-art in one-step/few-step 1024px text-to-image generation based on SDXL. Our method combines progressive and adversarial distillation to achieve a balance between quality and mode coverage. In this paper, we discuss the theoretical analysis, discriminator design, model formulation, and training techniques. We open-source our distilled SDXL-Lightning models both as LoRA and full UNet weights. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13929 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SDXL-Lightning: Progressive Adversarial Diffusion Distillation Lin, Shanchuan Wang, Anran Yang, Xiao Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning We propose a diffusion distillation method that achieves new state-of-the-art in one-step/few-step 1024px text-to-image generation based on SDXL. Our method combines progressive and adversarial distillation to achieve a balance between quality and mode coverage. In this paper, we discuss the theoretical analysis, discriminator design, model formulation, and training techniques. We open-source our distilled SDXL-Lightning models both as LoRA and full UNet weights. |
| title | SDXL-Lightning: Progressive Adversarial Diffusion Distillation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2402.13929 |