init readme
Browse files
README.md
CHANGED
@@ -61,7 +61,7 @@ Our machine evaluation involved a comprehensive comparison of various models. Th
|
|
61 |
|
62 |
As shown in the figures below, a comparison of different models in Chinese and English text-to-image generation performance is presented. The XL version models, such as SD-XL and Taiyi-XL, show significant improvements over the 1.5 version models like SD-v1.5 and Alt-Diffusion. DALL-E 3 is renowned for its vibrant colors and its ability to closely follow text prompts, setting a high standard. Our Taiyi-XL model, with its photographic style, closely matches the performance of Midjourney and excels in bilingual (Chinese and English) text-to-image generation.
|
63 |
|
64 |
-
尽管Taiyi-XL
|
65 |
|
66 |
Although Taiyi-XL may not yet rival commercial models, it excels among current bilingual open-source models. The gap with commercial models is mainly due to differences in the quantity, quality, and diversity of training data. Our model is trained exclusively on copyright-compliant image-text data. As is well known, copyright issues remain the biggest challenge in text-to-image and AI-generated content (AIGC) models.
|
67 |
|
@@ -77,9 +77,19 @@ We also evaluated the impact of using Latent Consistency Models (LCM) to acceler
|
|
77 |
|
78 |
## 引用 Citation
|
79 |
|
80 |
-
|
81 |
|
82 |
-
If you are using the resource for your work, please cite the our
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
83 |
|
84 |
```text
|
85 |
@article{fengshenbang,
|
|
|
61 |
|
62 |
As shown in the figures below, a comparison of different models in Chinese and English text-to-image generation performance is presented. The XL version models, such as SD-XL and Taiyi-XL, show significant improvements over the 1.5 version models like SD-v1.5 and Alt-Diffusion. DALL-E 3 is renowned for its vibrant colors and its ability to closely follow text prompts, setting a high standard. Our Taiyi-XL model, with its photographic style, closely matches the performance of Midjourney and excels in bilingual (Chinese and English) text-to-image generation.
|
63 |
|
64 |
+
尽管Taiyi-XL可能还未能与商业模型相媲美,但它比当前双语开源模型优越不少。我们认为我们模型与商业模型的差距主要归因于训练数据的数量、质量和多样性的差异。我们的模型仅使用学术数据集和符合版权要求的图文数据进行训练。正如大家所知的,版权问题仍然是文生图和AIGC模型最大的问题。对于中国人像或者元素我们也希望开源社区进一步数据微调。
|
65 |
|
66 |
Although Taiyi-XL may not yet rival commercial models, it excels among current bilingual open-source models. The gap with commercial models is mainly due to differences in the quantity, quality, and diversity of training data. Our model is trained exclusively on copyright-compliant image-text data. As is well known, copyright issues remain the biggest challenge in text-to-image and AI-generated content (AIGC) models.
|
67 |
|
|
|
77 |
|
78 |
## 引用 Citation
|
79 |
|
80 |
+
如果您在您的工作中使用了我们的模型,可以引用我们的论文:
|
81 |
|
82 |
+
If you are using the resource for your work, please cite the our paper:
|
83 |
+
```text
|
84 |
+
@misc{wu2024taiyidiffusionxl,
|
85 |
+
title={Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support},
|
86 |
+
author={Xiaojun Wu and Dixiang Zhang and Ruyi Gan and Junyu Lu and Ziwei Wu and Renliang Sun and Jiaxing Zhang and Pingjian Zhang and Yan Song},
|
87 |
+
year={2024},
|
88 |
+
eprint={2401.14688},
|
89 |
+
archivePrefix={arXiv},
|
90 |
+
primaryClass={cs.CL}
|
91 |
+
}
|
92 |
+
```
|
93 |
|
94 |
```text
|
95 |
@article{fengshenbang,
|