Hugging Face's logo

maxin-cn
/
Latte

Diffusers
Model card Files Community
1
maxin-cn commited on
Commit
fc35c8c
β€’
1 Parent(s): b0f802b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -3
README.md CHANGED
@@ -4,16 +4,17 @@ license: mit
4
 
5
  ## Latte: Latent Diffusion Transformer for Video Generation
6
 
7
- This repo contains pre-trained weights for our paper exploring latent diffusion models with transformers (Latte). You can find more visualizations on our [project page](https://maxin-cn.github.io/latte_project/).
 
8
 
9
  ## News
10
- - (πŸ”₯ New) May. 23, 2024. πŸ’₯ The updated LatteT2V model is released at [here](https://huggingface.co/maxin-cn/Latte/blob/main/t2v_v20240523.pt). If you want to use the updated model to generate images directly, please make sure `video_length=1`, `enable_temporal_attentions=True` and `enable_vae_temporal_decoder=False` in [t2v_sample.yaml](configs/t2v/t2v_sample.yaml).
11
 
12
  - (πŸ”₯ New) Mar. 20, 2024. πŸ’₯ An updated LatteT2V model is coming soon, stay tuned!
13
 
14
  - (πŸ”₯ New) Feb. 24, 2024. πŸ’₯ We are very grateful that researchers and developers like our work. We will continue to update our LatteT2V model, hoping that our efforts can help the community develop. Our Latte [discord](https://discord.gg/RguYqhVU92) channel is created for discussions. Coders are welcome to contribute.
15
 
16
- - (πŸ”₯ New) Jan. 9, 2024. πŸ’₯ An updated LatteT2V model initialized with the [PixArt-Ξ±](https://github.com/PixArt-alpha/PixArt-alpha) is released, the checkpoint can be found [here](https://huggingface.co/maxin-cn/Latte/resolve/main/t2v.pt?download=true).
17
 
18
  - (πŸ”₯ New) Oct. 31, 2023. πŸ’₯ The training and inference code is released. All checkpoints (including FaceForensics, SkyTimelapse, UCF101, and Taichi-HD) can be found [here](https://huggingface.co/maxin-cn/Latte/tree/main). In addition, the LatteT2V inference code is provided.
19
 
 
4
 
5
  ## Latte: Latent Diffusion Transformer for Video Generation
6
 
7
+ This repo contains pre-trained weights on FaceForensics, SkyTimelapse, UCF101, and Taichi-HD for our paper exploring latent diffusion models with transformers (Latte). You can find more visualizations on our [project page](https://maxin-cn.github.io/latte_project/).
8
+ If you want to obtain text-to-video generation pre-trained weights, please refer to [here](https://huggingface.co/maxin-cn/LatteT2V).
9
 
10
  ## News
11
+ - (πŸ”₯ New) May. 23, 2024. πŸ’₯ **Latte-1** for Text-to-video generation is released! You can download pre-trained model [here](https://huggingface.co/maxin-cn/LatteT2V/tree/main/transformer_v1). Latte-1 also supports Text-to-image generation, please run bash sample/t2i.sh.
12
 
13
  - (πŸ”₯ New) Mar. 20, 2024. πŸ’₯ An updated LatteT2V model is coming soon, stay tuned!
14
 
15
  - (πŸ”₯ New) Feb. 24, 2024. πŸ’₯ We are very grateful that researchers and developers like our work. We will continue to update our LatteT2V model, hoping that our efforts can help the community develop. Our Latte [discord](https://discord.gg/RguYqhVU92) channel is created for discussions. Coders are welcome to contribute.
16
 
17
+ - (πŸ”₯ New) Jan. 9, 2024. πŸ’₯ An updated LatteT2V model initialized with the [PixArt-Ξ±](https://github.com/PixArt-alpha/PixArt-alpha) is released, the checkpoint can be found [here](https://huggingface.co/maxin-cn/LatteT2V/tree/main/transformer).
18
 
19
  - (πŸ”₯ New) Oct. 31, 2023. πŸ’₯ The training and inference code is released. All checkpoints (including FaceForensics, SkyTimelapse, UCF101, and Taichi-HD) can be found [here](https://huggingface.co/maxin-cn/Latte/tree/main). In addition, the LatteT2V inference code is provided.
20