Zhida Feng, Zhenyu Zhang, Xintong Yu, Yewei Fang, Lanxin Li, Xuyi Chen, Yuxiang Lu, Jiaxiang Liu, Weichong Yin, Shikun Feng, Yu Sun, Li Chen, Hao Tian, Hua Wu, Haifeng Wang
Recent progress in diffusion models has revolutionized the popular technology of text-to-image generation. While existing approaches could produce photorealistic high-resolution images with text conditions, there are still several open problems to be solved, which limits the further improvement of image fidelity and text relevancy. In this paper, we propose ERNIE-ViLG 2.0, a large-scale Chinese text-to-image diffusion model, to progressively upgrade the quality of generated images by: (1) incorporating fine-grained textual and visual knowledge of key elements in the scene, and (2) utilizing different denoising experts at different denoising stages. With the proposed mechanisms, ERNIE-ViLG 2.0 not only achieves a new state-of-the-art on MS-COCO with zero-shot FID score of 6.75, but also significantly outperforms recent models in terms of image fidelity and image-text alignment, with side-by-side human evaluation on the bilingual prompt set ViLG-300.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Image Generation | COCO (Common Objects in Context) | FID | 6.75 | ERNIE-ViLG 2.0 (zero-shot) |
| Text-to-Image Generation | COCO (Common Objects in Context) | FID | 6.75 | ERNIE-ViLG 2.0 (zero-shot) |
| 10-shot image generation | COCO (Common Objects in Context) | FID | 6.75 | ERNIE-ViLG 2.0 (zero-shot) |
| 1 Image, 2*2 Stitchi | COCO (Common Objects in Context) | FID | 6.75 | ERNIE-ViLG 2.0 (zero-shot) |