README.md

---
language:
- en
---
<style>
  .title-container {
    display: flex;
    flex-direction: column; /* Stack elements vertically */
    justify-content: center;
    align-items: center;
  }
  
  .title {
    font-size: 2em;
    text-align: center;
    color: #333;
    font-family: 'Comic Sans MS', cursive; /* Use Comic Sans MS font */
    text-transform: uppercase;
    letter-spacing: 0.1em;
    padding: 0.5em 0 0.2em;
    background: transparent;
  }
  
  .title span {
    background: -webkit-linear-gradient(45deg, #6495ED, #4169E1); /* Blue gradient */
    -webkit-background-clip: text;
    -webkit-text-fill-color: transparent;
  }

  .subheading {
    font-size: 1.5em; /* Adjust the size as needed */
    text-align: center;
    color: #555; /* Adjust the color as needed */
    font-family: 'Comic Sans MS', cursive; /* Use Comic Sans MS font */
  }

  .authors {
    font-size: 1em; /* Adjust the size as needed */
    text-align: center;
    color: #777; /* Adjust the color as needed */
    font-family: 'Comic Sans MS', cursive; /* Use Comic Sans MS font */
    padding-top: 1em;
  }

  .affil {
    font-size: 1em; /* Adjust the size as needed */
    text-align: center;
    color: #777; /* Adjust the color as needed */
    font-family: 'Comic Sans MS', cursive; /* Use Comic Sans MS font */
  }

</style>

<div class="title-container">
  <div class="title">
    Ta<span>il</span>s Tell Ta<span>le</span>s
  </div>
  <div class="subheading">
    Chapter-Wide Manga Transcriptions With Character Names
  </div>
  <div class="authors">
    Ragav Sachdeva, Gyungin Shin and Andrew Zisserman
  </div>
  <div class="affil">
    University of Oxford
  </div>
</div>

# Usage
```python
from transformers import AutoModel
import PIL
import torch

batch_of_images = [PIL.Image.open("image1.jpg"), PIL.Image.open("image2.jpg")]
model = AutoModel.from_pretrained("ragavsachdeva/magiv2-crop-embedder", trust_remote_code=True).cuda().eval()
with torch.no_grad():
    embeddings = model(batch_of_images)

print(embeddings.shape)
```

# License and Citation
The provided model is available for unrestricted use in personal, research, non-commercial, and not-for-profit endeavors. For any other usage scenarios, kindly contact me via email, providing a detailed description of your requirements, to establish a tailored licensing arrangement.
My contact information can be found on my website: ragavsachdeva [dot] github [dot] io

```
@misc{magiv2,
      title={Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names}, 
      author={Ragav Sachdeva and Gyungin Shin and Andrew Zisserman},
      year={2024},
      eprint={2408.00298},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2408.00298}, 
}
```