Update README.md
Browse files
README.md
CHANGED
|
@@ -48,7 +48,7 @@ pipeline_tag: text-to-image
|
|
| 48 |
## Model Description
|
| 49 |
|
| 50 |
The ByT5 model is finetuned from [Glyph-ByT5-v2](https://arxiv.org/abs/2406.10208), which supports accurate visual text rendering in ten different languages.
|
| 51 |
-
The [SPO](https://huggingface.co/SPO-Diffusion-Models) model is a substitute for the original sdxl-base-1.0 for aesthetic improvement.
|
| 52 |
You can follow our [github]() to organize and run the model.
|
| 53 |
|
| 54 |
## Citation
|
|
|
|
| 48 |
## Model Description
|
| 49 |
|
| 50 |
The ByT5 model is finetuned from [Glyph-ByT5-v2](https://arxiv.org/abs/2406.10208), which supports accurate visual text rendering in ten different languages.
|
| 51 |
+
The [SPO](https://huggingface.co/SPO-Diffusion-Models) model is a substitute for the original sdxl-base-1.0 for aesthetic improvement. The lora/infographic and lora/slides are separately tuned on our infographics and slides datasets.
|
| 52 |
You can follow our [github]() to organize and run the model.
|
| 53 |
|
| 54 |
## Citation
|