PixelFlow: Pixel-Space Generative Models with Flow
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912319745818624 |
|---|---|
| author | Chen, Shoufa Ge, Chongjian Zhang, Shilong Sun, Peize Luo, Ping |
| author_facet | Chen, Shoufa Ge, Chongjian Zhang, Shilong Sun, Peize Luo, Ping |
| contents | We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies the image generation process by eliminating the need for a pre-trained Variational Autoencoder (VAE) and enabling the whole model end-to-end trainable. Through efficient cascade flow modeling, PixelFlow achieves affordable computation cost in pixel space. It achieves an FID of 1.98 on 256$\times$256 ImageNet class-conditional image generation benchmark. The qualitative text-to-image results demonstrate that PixelFlow excels in image quality, artistry, and semantic control. We hope this new paradigm will inspire and open up new opportunities for next-generation visual generation models. Code and models are available at https://github.com/ShoufaChen/PixelFlow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07963 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PixelFlow: Pixel-Space Generative Models with Flow Chen, Shoufa Ge, Chongjian Zhang, Shilong Sun, Peize Luo, Ping Computer Vision and Pattern Recognition We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies the image generation process by eliminating the need for a pre-trained Variational Autoencoder (VAE) and enabling the whole model end-to-end trainable. Through efficient cascade flow modeling, PixelFlow achieves affordable computation cost in pixel space. It achieves an FID of 1.98 on 256$\times$256 ImageNet class-conditional image generation benchmark. The qualitative text-to-image results demonstrate that PixelFlow excels in image quality, artistry, and semantic control. We hope this new paradigm will inspire and open up new opportunities for next-generation visual generation models. Code and models are available at https://github.com/ShoufaChen/PixelFlow. |
| title | PixelFlow: Pixel-Space Generative Models with Flow |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.07963 |