Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
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_ | 1866914703488319488 |
|---|---|
| author | Esser, Patrick Kulal, Sumith Blattmann, Andreas Entezari, Rahim Müller, Jonas Saini, Harry Levi, Yam Lorenz, Dominik Sauer, Axel Boesel, Frederic Podell, Dustin Dockhorn, Tim English, Zion Lacey, Kyle Goodwin, Alex Marek, Yannik Rombach, Robin |
| author_facet | Esser, Patrick Kulal, Sumith Blattmann, Andreas Entezari, Rahim Müller, Jonas Saini, Harry Levi, Yam Lorenz, Dominik Sauer, Axel Boesel, Frederic Podell, Dustin Dockhorn, Tim English, Zion Lacey, Kyle Goodwin, Alex Marek, Yannik Rombach, Robin |
| contents | Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perceptual data such as images and videos. Rectified flow is a recent generative model formulation that connects data and noise in a straight line. Despite its better theoretical properties and conceptual simplicity, it is not yet decisively established as standard practice. In this work, we improve existing noise sampling techniques for training rectified flow models by biasing them towards perceptually relevant scales. Through a large-scale study, we demonstrate the superior performance of this approach compared to established diffusion formulations for high-resolution text-to-image synthesis. Additionally, we present a novel transformer-based architecture for text-to-image generation that uses separate weights for the two modalities and enables a bidirectional flow of information between image and text tokens, improving text comprehension, typography, and human preference ratings. We demonstrate that this architecture follows predictable scaling trends and correlates lower validation loss to improved text-to-image synthesis as measured by various metrics and human evaluations. Our largest models outperform state-of-the-art models, and we will make our experimental data, code, and model weights publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_03206 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Scaling Rectified Flow Transformers for High-Resolution Image Synthesis Esser, Patrick Kulal, Sumith Blattmann, Andreas Entezari, Rahim Müller, Jonas Saini, Harry Levi, Yam Lorenz, Dominik Sauer, Axel Boesel, Frederic Podell, Dustin Dockhorn, Tim English, Zion Lacey, Kyle Goodwin, Alex Marek, Yannik Rombach, Robin Computer Vision and Pattern Recognition Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perceptual data such as images and videos. Rectified flow is a recent generative model formulation that connects data and noise in a straight line. Despite its better theoretical properties and conceptual simplicity, it is not yet decisively established as standard practice. In this work, we improve existing noise sampling techniques for training rectified flow models by biasing them towards perceptually relevant scales. Through a large-scale study, we demonstrate the superior performance of this approach compared to established diffusion formulations for high-resolution text-to-image synthesis. Additionally, we present a novel transformer-based architecture for text-to-image generation that uses separate weights for the two modalities and enables a bidirectional flow of information between image and text tokens, improving text comprehension, typography, and human preference ratings. We demonstrate that this architecture follows predictable scaling trends and correlates lower validation loss to improved text-to-image synthesis as measured by various metrics and human evaluations. Our largest models outperform state-of-the-art models, and we will make our experimental data, code, and model weights publicly available. |
| title | Scaling Rectified Flow Transformers for High-Resolution Image Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.03206 |