I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917803610603520 |
|---|---|
| author | Du, Ruoyi Liu, Dongyang Zhuo, Le Qi, Qin Li, Hongsheng Ma, Zhanyu Gao, Peng |
| author_facet | Du, Ruoyi Liu, Dongyang Zhuo, Le Qi, Qin Li, Hongsheng Ma, Zhanyu Gao, Peng |
| contents | Rectified Flow Transformers (RFTs) offer superior training and inference efficiency, making them likely the most viable direction for scaling up diffusion models. However, progress in generation resolution has been relatively slow due to data quality and training costs. Tuning-free resolution extrapolation presents an alternative, but current methods often reduce generative stability, limiting practical application. In this paper, we review existing resolution extrapolation methods and introduce the I-Max framework to maximize the resolution potential of Text-to-Image RFTs. I-Max features: (i) a novel Projected Flow strategy for stable extrapolation and (ii) an advanced inference toolkit for generalizing model knowledge to higher resolutions. Experiments with Lumina-Next-2K and Flux.1-dev demonstrate I-Max's ability to enhance stability in resolution extrapolation and show that it can bring image detail emergence and artifact correction, confirming the practical value of tuning-free resolution extrapolation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07536 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow Du, Ruoyi Liu, Dongyang Zhuo, Le Qi, Qin Li, Hongsheng Ma, Zhanyu Gao, Peng Computer Vision and Pattern Recognition Rectified Flow Transformers (RFTs) offer superior training and inference efficiency, making them likely the most viable direction for scaling up diffusion models. However, progress in generation resolution has been relatively slow due to data quality and training costs. Tuning-free resolution extrapolation presents an alternative, but current methods often reduce generative stability, limiting practical application. In this paper, we review existing resolution extrapolation methods and introduce the I-Max framework to maximize the resolution potential of Text-to-Image RFTs. I-Max features: (i) a novel Projected Flow strategy for stable extrapolation and (ii) an advanced inference toolkit for generalizing model knowledge to higher resolutions. Experiments with Lumina-Next-2K and Flux.1-dev demonstrate I-Max's ability to enhance stability in resolution extrapolation and show that it can bring image detail emergence and artifact correction, confirming the practical value of tuning-free resolution extrapolation. |
| title | I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.07536 |