Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908918025814016 |
|---|---|
| author | Dao, Quan Phung, Hao Dao, Trung Metaxas, Dimitris Tran, Anh |
| author_facet | Dao, Quan Phung, Hao Dao, Trung Metaxas, Dimitris Tran, Anh |
| contents | Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared to diffusion-based models. However, this method still requires numerous function evaluations in the sampling process. To address these limitations, we introduce a self-corrected flow distillation method that effectively integrates consistency models and adversarial training within the flow-matching framework. This work is a pioneer in achieving consistent generation quality in both few-step and one-step sampling. Our extensive experiments validate the effectiveness of our method, yielding superior results both quantitatively and qualitatively on CelebA-HQ and zero-shot benchmarks on the COCO dataset. Our implementation is released at https://github.com/hao-pt/SCFlow.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16906 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation Dao, Quan Phung, Hao Dao, Trung Metaxas, Dimitris Tran, Anh Computer Vision and Pattern Recognition Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared to diffusion-based models. However, this method still requires numerous function evaluations in the sampling process. To address these limitations, we introduce a self-corrected flow distillation method that effectively integrates consistency models and adversarial training within the flow-matching framework. This work is a pioneer in achieving consistent generation quality in both few-step and one-step sampling. Our extensive experiments validate the effectiveness of our method, yielding superior results both quantitatively and qualitatively on CelebA-HQ and zero-shot benchmarks on the COCO dataset. Our implementation is released at https://github.com/hao-pt/SCFlow.git. |
| title | Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.16906 |