Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,45 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: other
|
| 3 |
-
license_name: animegamer-lisence
|
| 4 |
-
license_link: LICENSE
|
| 5 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: animegamer-lisence
|
| 4 |
+
license_link: LICENSE
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction
|
| 8 |
+
<span>
|
| 9 |
+
<a href="https://arxiv.org/abs/2307.08623">
|
| 10 |
+
<img src="https://img.shields.io/badge/arXiv-2407.08683-b31b1b.svg" alt="arXiv">
|
| 11 |
+
</a>
|
| 12 |
+
<a href="https://github.com/TencentARC/SEED-Story">
|
| 13 |
+
<img src="https://img.shields.io/badge/GitHub-black?logo=github" alt="GitHub">
|
| 14 |
+
</a>
|
| 15 |
+
</span>
|
| 16 |
+
|
| 17 |
+
**TL;DR:** We introduce SEED-Story, a MLLM capable of generating multimodal
|
| 18 |
+
long stories consists of rich and coherent narrative texts, along with images that are consistent in characters and
|
| 19 |
+
style. We also release the StoryStream Dataset for build this model.
|
| 20 |
+
|
| 21 |
+
## Model Weights
|
| 22 |
+
We release the pretrained Tokenizer, the pretrained De-Tokenizer, the pre-trained foundation model **SEED-X-pretrained**,
|
| 23 |
+
the StoryStream instruction-tuned MLLM **SEED-Story-George**, and the StoryStream tuned De-Tokenizer in **Detokenizer-George**
|
| 24 |
+
|
| 25 |
+
Please download the checkpoints and save them under the folder `./pretrained`.
|
| 26 |
+
|
| 27 |
+
You also need to download [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) and [Qwen-VL-Chat](https://huggingface.co/Qwen/Qwen-VL-Chat), and save them under the folder `./pretrained`. Please use the following script to extract the weights of visual encoder in Qwen-VL-Chat.
|
| 28 |
+
```bash
|
| 29 |
+
python3 src/tools/reload_qwen_vit.py
|
| 30 |
+
```
|
| 31 |
+
|
| 32 |
+
## Citation
|
| 33 |
+
If you find the work helpful, please consider citing:
|
| 34 |
+
```bash
|
| 35 |
+
@article{yang2024seedstory,
|
| 36 |
+
title={SEED-Story: Multimodal Long Story Generation with Large Language Model},
|
| 37 |
+
author={Shuai Yang and Yuying Ge and Yang Li and Yukang Chen and Yixiao Ge and Ying Shan and Yingcong Chen},
|
| 38 |
+
year={2024},
|
| 39 |
+
journal={arXiv preprint arXiv:2407.08683},
|
| 40 |
+
url={https://arxiv.org/abs/2407.08683},
|
| 41 |
+
}
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
## License
|
| 45 |
+
`SEED-Story` is licensed under the Apache License Version 2.0 except for the third-party components listed in [License](License_Seed-Story.txt).
|