E-Anlia commited on
Commit
65542e9
·
verified ·
1 Parent(s): 26ee706

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
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
  ![NewBie image preview](https://huggingface.co/NewBie-AI/NewBie-image-Exp0.1/resolve/main/image/newbie_image.png)
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
  ![NewBie image preview](https://huggingface.co/NewBie-AI/NewBie-image-Exp0.1/resolve/main/image/newbie_image.png)
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>