Update README.md
Browse files
README.md
CHANGED
|
@@ -40,7 +40,7 @@ Use the FLUX.1-dev 16channel VAE to encode images into latents, delivering riche
|
|
| 40 |
## 🖼️Task type
|
| 41 |
**NewBie image Exp0.1** is pretrain on a large corpus of high-quality anime data, enabling the model to generate remarkably detailed and visually striking anime style images.
|
| 42 |

|
| 43 |
-
We reformatted the dataset text into an XML structured format for our experiments. Empirically, this improved attention binding and attribute/element disentanglement, and also led to faster convergence.
|
| 44 |
|
| 45 |
**In multi character scenes, using XML structured prompt typically leads to more accurate image generation results.**
|
| 46 |
</div>
|
|
|
|
| 40 |
## 🖼️Task type
|
| 41 |
**NewBie image Exp0.1** is pretrain on a large corpus of high-quality anime data, enabling the model to generate remarkably detailed and visually striking anime style images.
|
| 42 |

|
| 43 |
+
We reformatted the dataset text into an **XML structured format** for our experiments. Empirically, this improved attention binding and attribute/element disentanglement, and also led to faster convergence.
|
| 44 |
|
| 45 |
**In multi character scenes, using XML structured prompt typically leads to more accurate image generation results.**
|
| 46 |
</div>
|