thanks to damo-vilab ❤

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+doc/introduction.pdf filter=lfs diff=lfs merge=lfs -text
+source/i2vgen_fig_04.png filter=lfs diff=lfs merge=lfs -text

README.MD

@@ -0,0 +1,283 @@
+# VGen
+
+
+![figure1](source/VGen.jpg "figure1")
+
+VGen is an open-source video synthesis codebase developed by the Tongyi Lab of Alibaba Group, featuring state-of-the-art video generative models. This repository includes implementations of the following methods:
+
+
+- [I2VGen-xl: High-quality image-to-video synthesis via cascaded diffusion models](https://i2vgen-xl.github.io/)
+- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://videocomposer.github.io/)
+- [Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation](https://higen-t2v.github.io/)
+- [A Recipe for Scaling up Text-to-Video Generation with Text-free Videos]()
+- [InstructVideo: Instructing Video Diffusion Models with Human Feedback]()
+- [DreamVideo: Composing Your Dream Videos with Customized Subject and Motion](https://dreamvideo-t2v.github.io/)
+- [VideoLCM: Video Latent Consistency Model](https://arxiv.org/abs/2312.09109)
+- [Modelscope text-to-video technical report](https://arxiv.org/abs/2308.06571)
+
+
+VGen can produce high-quality videos from the input text, images, desired motion, desired subjects, and even the feedback signals provided.  It also offers a variety of commonly used video generation tools such as visualization, sampling, training, inference, join training using images and videos, acceleration, and more. 
+
+
+<a href='https://i2vgen-xl.github.io/'><img src='https://img.shields.io/badge/Project-Page-Green'></a> <a href='https://arxiv.org/abs/2311.04145'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> [![YouTube](https://badges.aleen42.com/src/youtube.svg)](https://youtu.be/XUi0y7dxqEQ) <a href='https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441039979087.mp4'><img src='source/logo.png'></a>
+
+
+## 🔥News!!!
+- __[2023.12]__ We release the high-efficiency video generation method [VideoLCM](https://arxiv.org/abs/2312.09109)
+- __[2023.12]__ We release the code and model of I2VGen-XL and the ModelScope T2V
+- __[2023.12]__ We release the T2V method [HiGen](https://higen-t2v.github.io) and customizing T2V method [DreamVideo](https://dreamvideo-t2v.github.io).
+- __[2023.12]__ We write an [introduction docment](doc/introduction.pdf) for VGen and compare I2VGen-XL with SVD.
+- __[2023.11]__ We release a high-quality I2VGen-XL model, please refer to the [Webpage](https://i2vgen-xl.github.io)
+
+
+## TODO
+- [x] Release the technical papers and webpage of [I2VGen-XL](doc/i2vgen-xl.md)
+- [x] Release the code and pretrained models that can generate 1280x720 videos
+- [ ] Release models optimized specifically for the human body and faces
+- [ ] Updated version can fully maintain the ID and capture large and accurate motions simultaneously
+- [ ] Release other methods and the corresponding models
+
+
+## Preparation
+
+The main features of VGen are as follows:
+- Expandability, allowing for easy management of your own experiments.
+- Completeness, encompassing all common components for video generation.
+- Excellent performance, featuring powerful pre-trained models in multiple tasks.
+
+
+### Installation
+
+```
+conda create -n vgen python=3.8
+conda activate vgen
+pip install torch==1.12.0+cu113 torchvision==0.13.0+cu113 torchaudio==0.12.0 --extra-index-url https://download.pytorch.org/whl/cu113
+pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
+### Datasets
+
+We have provided a **demo dataset** that includes images and videos, along with their lists in ``data``. 
+
+*Please note that the demo images used here are for testing purposes and were not included in the training.*
+
+
+### Clone codeb
+
+```
+git clone https://github.com/damo-vilab/i2vgen-xl.git
+cd i2vgen-xl
+```
+
+
+## Getting Started with VGen
+
+### (1) Train your text-to-video model
+
+
+Executing the following command to enable distributed training is as easy as that.
+```
+python train_net.py --cfg configs/t2v_train.yaml
+```
+
+In the `t2v_train.yaml` configuration file, you can specify the data, adjust the video-to-image ratio using `frame_lens`, and validate your ideas with different Diffusion settings, and so on.
+
+- Before the training, you can download any of our open-source models for initialization. Our codebase supports custom initialization and `grad_scale` settings, all of which are included in the `Pretrain` item in yaml file.
+- During the training, you can view the saved models and intermediate inference results in the `workspace/experiments/t2v_train`directory.
+
+After the training is completed, you can perform inference on the model using the following command.
+```
+python inference.py --cfg configs/t2v_infer.yaml
+```
+Then you can find the videos you generated in the `workspace/experiments/test_img_01` directory. For specific configurations such as data, models, seed, etc., please refer to the `t2v_infer.yaml` file.
+
+<!-- <table>
+<center>
+  <tr>
+    <td ><center>
+      <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441754174077.mp4"></video>	
+    </center></td>
+    <td ><center>
+      <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441138824052.mp4"></video>	
+    </center></td>
+  </tr>
+</center>
+</table>
+</center> -->
+
+<table>
+<center>
+  <tr>
+    <td ><center>
+      <image  height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01Ya2I5I25utrJwJ9Jf_!!6000000007587-2-tps-1280-720.png"></image>	
+    </center></td>
+    <td ><center>
+      <image height="260" src="https://img.alicdn.com/imgextra/i3/O1CN01CrmYaz1zXBetmg3dd_!!6000000006723-2-tps-1280-720.png"></image>	
+    </center></td>
+  </tr>
+  <tr>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441754174077.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441138824052.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr>
+</center>
+</table>
+</center>
+
+
+### (2) Run the I2VGen-XL model
+
+(i) Download model and test data:
+```
+!pip install modelscope
+from modelscope.hub.snapshot_download import snapshot_download
+model_dir = snapshot_download('damo/I2VGen-XL', cache_dir='models/', revision='v1.0.0')
+```
+
+(ii) Run the following command:
+```
+python inference.py --cfg configs/i2vgen_xl_infer.yaml
+```
+In a few minutes, you can retrieve the high-definition video you wish to create from the `workspace/experiments/test_img_01` directory. At present, we find that the current model performs inadequately on **anime images** and **images with a black background** due to the lack of relevant training data. We are consistently working to optimize it.
+
+
+<span style="color:red">Due to the compression of our video quality in GIF format, please click 'HRER' below to view the original video.</span>
+
+<center>
+<table>
+<center>
+  <tr>
+    <td ><center>
+      <image  height="260" src="https://img.alicdn.com/imgextra/i1/O1CN01CCEq7K1ZeLpNQqrWu_!!6000000003219-0-tps-1280-720.jpg"></image>	
+    </center></td>
+    <td ><center>
+      <!-- <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442125067544.mp4"></video>	 -->
+      <image  height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01hIQcvG1spmQMLqBo0_!!6000000005816-1-tps-1280-704.gif"></image>	
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <p>Input Image</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442125067544.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <image  height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01ZXY7UN23K8q4oQ3uG_!!6000000007236-2-tps-1280-720.png"></image>	
+    </center></td>
+    <td ><center>
+      <!-- <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441385957074.mp4"></video>	 -->
+      <image height="260" src="https://img.alicdn.com/imgextra/i1/O1CN01iaSiiv1aJZURUEY53_!!6000000003309-1-tps-1280-704.gif"></image>	
+    </center></td>
+  </tr>
+  <tr>
+    <td ><center>
+      <p>Input Image</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441385957074.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <image  height="260" src="https://img.alicdn.com/imgextra/i3/O1CN01NHpVGl1oat4H54Hjf_!!6000000005242-2-tps-1280-720.png"></image>	
+    </center></td>
+    <td ><center>
+      <!-- <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442102706767.mp4"></video>	 -->
+      <!-- <image muted="true" height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01DgLj1T240jfpzKoaQ_!!6000000007329-1-tps-1280-704.gif"></image>	
+       -->
+      <image  height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01DgLj1T240jfpzKoaQ_!!6000000007329-1-tps-1280-704.gif"></image>
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <p>Input Image</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442102706767.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <image height="260" src="https://img.alicdn.com/imgextra/i1/O1CN01odS61s1WW9tXen21S_!!6000000002795-0-tps-1280-720.jpg"></image>	
+    </center></td>
+    <td ><center>
+      <!-- <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442163934688.mp4"></video>	 -->
+      <image height="260" src="https://img.alicdn.com/imgextra/i3/O1CN01Jyk1HT28JkZtpAtY6_!!6000000007912-1-tps-1280-704.gif"></image>	
+    </center></td>
+  </tr>
+  <tr>
+    <td ><center>
+      <p>Input Image</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442163934688.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr> 
+</center>
+</table>
+</center>
+
+### (3) Other methods
+
+In preparation.
+
+
+## Customize your own approach
+
+Our codebase essentially supports all the commonly used components in video generation. You can manage your experiments flexibly by adding corresponding registration classes, including `ENGINE, MODEL, DATASETS, EMBEDDER, AUTO_ENCODER, DISTRIBUTION, VISUAL, DIFFUSION, PRETRAIN`, and can be compatible with all our open-source algorithms according to your own needs. If you have any questions, feel free to give us your feedback at any time.
+
+
+
+## BibTeX
+
+If this repo is useful to you, please cite our corresponding technical paper.
+
+
+```bibtex
+@article{2023i2vgenxl,
+  title={I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models},
+  author={Zhang, Shiwei and Wang, Jiayu and Zhang, Yingya and Zhao, Kang and Yuan, Hangjie and Qing, Zhiwu and Wang, Xiang  and Zhao, Deli and Zhou, Jingren},
+  booktitle={arXiv preprint arXiv:2311.04145},
+  year={2023}
+}
+@article{2023videocomposer,
+  title={VideoComposer: Compositional Video Synthesis with Motion Controllability},
+  author={Wang, Xiang and Yuan, Hangjie and Zhang, Shiwei and Chen, Dayou and Wang, Jiuniu, and Zhang, Yingya, and Shen, Yujun, and Zhao, Deli and Zhou, Jingren},
+  booktitle={arXiv preprint arXiv:2306.02018},
+  year={2023}
+}
+@article{wang2023modelscope,
+  title={Modelscope text-to-video technical report},
+  author={Wang, Jiuniu and Yuan, Hangjie and Chen, Dayou and Zhang, Yingya and Wang, Xiang and Zhang, Shiwei},
+  journal={arXiv preprint arXiv:2308.06571},
+  year={2023}
+}
+@article{dreamvideo,
+  title={DreamVideo: Composing Your Dream Videos with Customized Subject and Motion},
+  author={Wei, Yujie and Zhang, Shiwei and Qing, Zhiwu and Yuan, Hangjie and Liu, Zhiheng and Liu, Yu and Zhang, Yingya and Zhou, Jingren and Shan, Hongming},
+  journal={arXiv preprint arXiv:2312.04433},
+  year={2023}
+}
+@article{qing2023higen,
+  title={Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation},
+  author={Qing, Zhiwu and Zhang, Shiwei and Wang, Jiayu and Wang, Xiang and Wei, Yujie and Zhang, Yingya and Gao, Changxin and Sang, Nong },
+  journal={arXiv preprint arXiv:2312.04483},
+  year={2023}
+}
+@article{wang2023videolcm,
+  title={VideoLCM: Video Latent Consistency Model},
+  author={Wang, Xiang and Zhang, Shiwei and Zhang, Han and Liu, Yu and Zhang, Yingya and Gao, Changxin and Sang, Nong },
+  journal={arXiv preprint arXiv:2312.09109},
+  year={2023}
+}
+```
+
+## Disclaimer
+
+This open-source model is trained with using [WebVid-10M](https://m-bain.github.io/webvid-dataset/) and [LAION-400M](https://laion.ai/blog/laion-400-open-dataset/) datasets and is intended for <strong>RESEARCH/NON-COMMERCIAL USE ONLY</strong>. 

README.md

@@ -0,0 +1,286 @@
+---
+license: mit
+---
+# VGen
+
+
+![figure1](source/VGen.jpg "figure1")
+
+VGen is an open-source video synthesis codebase developed by the Tongyi Lab of Alibaba Group, featuring state-of-the-art video generative models. This repository includes implementations of the following methods:
+
+
+- [I2VGen-xl: High-quality image-to-video synthesis via cascaded diffusion models](https://i2vgen-xl.github.io/)
+- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://videocomposer.github.io/)
+- [Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation](https://higen-t2v.github.io/)
+- [A Recipe for Scaling up Text-to-Video Generation with Text-free Videos]()
+- [InstructVideo: Instructing Video Diffusion Models with Human Feedback]()
+- [DreamVideo: Composing Your Dream Videos with Customized Subject and Motion](https://dreamvideo-t2v.github.io/)
+- [VideoLCM: Video Latent Consistency Model](https://arxiv.org/abs/2312.09109)
+- [Modelscope text-to-video technical report](https://arxiv.org/abs/2308.06571)
+
+
+VGen can produce high-quality videos from the input text, images, desired motion, desired subjects, and even the feedback signals provided.  It also offers a variety of commonly used video generation tools such as visualization, sampling, training, inference, join training using images and videos, acceleration, and more. 
+
+
+<a href='https://i2vgen-xl.github.io/'><img src='https://img.shields.io/badge/Project-Page-Green'></a> <a href='https://arxiv.org/abs/2311.04145'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> [![YouTube](https://badges.aleen42.com/src/youtube.svg)](https://youtu.be/XUi0y7dxqEQ) <a href='https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441039979087.mp4'><img src='source/logo.png'></a>
+
+
+## 🔥News!!!
+- __[2023.12]__ We release the high-efficiency video generation method [VideoLCM](https://arxiv.org/abs/2312.09109)
+- __[2023.12]__ We release the code and model of I2VGen-XL and the ModelScope T2V
+- __[2023.12]__ We release the T2V method [HiGen](https://higen-t2v.github.io) and customizing T2V method [DreamVideo](https://dreamvideo-t2v.github.io).
+- __[2023.12]__ We write an [introduction docment](doc/introduction.pdf) for VGen and compare I2VGen-XL with SVD.
+- __[2023.11]__ We release a high-quality I2VGen-XL model, please refer to the [Webpage](https://i2vgen-xl.github.io)
+
+
+## TODO
+- [x] Release the technical papers and webpage of [I2VGen-XL](doc/i2vgen-xl.md)
+- [x] Release the code and pretrained models that can generate 1280x720 videos
+- [ ] Release models optimized specifically for the human body and faces
+- [ ] Updated version can fully maintain the ID and capture large and accurate motions simultaneously
+- [ ] Release other methods and the corresponding models
+
+
+## Preparation
+
+The main features of VGen are as follows:
+- Expandability, allowing for easy management of your own experiments.
+- Completeness, encompassing all common components for video generation.
+- Excellent performance, featuring powerful pre-trained models in multiple tasks.
+
+
+### Installation
+
+```
+conda create -n vgen python=3.8
+conda activate vgen
+pip install torch==1.12.0+cu113 torchvision==0.13.0+cu113 torchaudio==0.12.0 --extra-index-url https://download.pytorch.org/whl/cu113
+pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
+```
+
+### Datasets
+
+We have provided a **demo dataset** that includes images and videos, along with their lists in ``data``. 
+
+*Please note that the demo images used here are for testing purposes and were not included in the training.*
+
+
+### Clone codeb
+
+```
+git clone https://github.com/damo-vilab/i2vgen-xl.git
+cd i2vgen-xl
+```
+
+
+## Getting Started with VGen
+
+### (1) Train your text-to-video model
+
+
+Executing the following command to enable distributed training is as easy as that.
+```
+python train_net.py --cfg configs/t2v_train.yaml
+```
+
+In the `t2v_train.yaml` configuration file, you can specify the data, adjust the video-to-image ratio using `frame_lens`, and validate your ideas with different Diffusion settings, and so on.
+
+- Before the training, you can download any of our open-source models for initialization. Our codebase supports custom initialization and `grad_scale` settings, all of which are included in the `Pretrain` item in yaml file.
+- During the training, you can view the saved models and intermediate inference results in the `workspace/experiments/t2v_train`directory.
+
+After the training is completed, you can perform inference on the model using the following command.
+```
+python inference.py --cfg configs/t2v_infer.yaml
+```
+Then you can find the videos you generated in the `workspace/experiments/test_img_01` directory. For specific configurations such as data, models, seed, etc., please refer to the `t2v_infer.yaml` file.
+
+<!-- <table>
+<center>
+  <tr>
+    <td ><center>
+      <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441754174077.mp4"></video>	
+    </center></td>
+    <td ><center>
+      <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441138824052.mp4"></video>	
+    </center></td>
+  </tr>
+</center>
+</table>
+</center> -->
+
+<table>
+<center>
+  <tr>
+    <td ><center>
+      <image  height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01Ya2I5I25utrJwJ9Jf_!!6000000007587-2-tps-1280-720.png"></image>	
+    </center></td>
+    <td ><center>
+      <image height="260" src="https://img.alicdn.com/imgextra/i3/O1CN01CrmYaz1zXBetmg3dd_!!6000000006723-2-tps-1280-720.png"></image>	
+    </center></td>
+  </tr>
+  <tr>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441754174077.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441138824052.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr>
+</center>
+</table>
+</center>
+
+
+### (2) Run the I2VGen-XL model
+
+(i) Download model and test data:
+```
+!pip install modelscope
+from modelscope.hub.snapshot_download import snapshot_download
+model_dir = snapshot_download('damo/I2VGen-XL', cache_dir='models/', revision='v1.0.0')
+```
+
+(ii) Run the following command:
+```
+python inference.py --cfg configs/i2vgen_xl_infer.yaml
+```
+In a few minutes, you can retrieve the high-definition video you wish to create from the `workspace/experiments/test_img_01` directory. At present, we find that the current model performs inadequately on **anime images** and **images with a black background** due to the lack of relevant training data. We are consistently working to optimize it.
+
+
+<span style="color:red">Due to the compression of our video quality in GIF format, please click 'HRER' below to view the original video.</span>
+
+<center>
+<table>
+<center>
+  <tr>
+    <td ><center>
+      <image  height="260" src="https://img.alicdn.com/imgextra/i1/O1CN01CCEq7K1ZeLpNQqrWu_!!6000000003219-0-tps-1280-720.jpg"></image>	
+    </center></td>
+    <td ><center>
+      <!-- <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442125067544.mp4"></video>	 -->
+      <image  height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01hIQcvG1spmQMLqBo0_!!6000000005816-1-tps-1280-704.gif"></image>	
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <p>Input Image</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442125067544.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <image  height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01ZXY7UN23K8q4oQ3uG_!!6000000007236-2-tps-1280-720.png"></image>	
+    </center></td>
+    <td ><center>
+      <!-- <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441385957074.mp4"></video>	 -->
+      <image height="260" src="https://img.alicdn.com/imgextra/i1/O1CN01iaSiiv1aJZURUEY53_!!6000000003309-1-tps-1280-704.gif"></image>	
+    </center></td>
+  </tr>
+  <tr>
+    <td ><center>
+      <p>Input Image</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/441385957074.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <image  height="260" src="https://img.alicdn.com/imgextra/i3/O1CN01NHpVGl1oat4H54Hjf_!!6000000005242-2-tps-1280-720.png"></image>	
+    </center></td>
+    <td ><center>
+      <!-- <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442102706767.mp4"></video>	 -->
+      <!-- <image muted="true" height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01DgLj1T240jfpzKoaQ_!!6000000007329-1-tps-1280-704.gif"></image>	
+       -->
+      <image  height="260" src="https://img.alicdn.com/imgextra/i4/O1CN01DgLj1T240jfpzKoaQ_!!6000000007329-1-tps-1280-704.gif"></image>
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <p>Input Image</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442102706767.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr> 
+  <tr>
+    <td ><center>
+      <image height="260" src="https://img.alicdn.com/imgextra/i1/O1CN01odS61s1WW9tXen21S_!!6000000002795-0-tps-1280-720.jpg"></image>	
+    </center></td>
+    <td ><center>
+      <!-- <video muted="true" autoplay="true" loop="true" height="260" src="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442163934688.mp4"></video>	 -->
+      <image height="260" src="https://img.alicdn.com/imgextra/i3/O1CN01Jyk1HT28JkZtpAtY6_!!6000000007912-1-tps-1280-704.gif"></image>	
+    </center></td>
+  </tr>
+  <tr>
+    <td ><center>
+      <p>Input Image</p>
+    </center></td>
+    <td ><center>
+      <p>Clike <a href="https://cloud.video.taobao.com/play/u/null/p/1/e/6/t/1/442163934688.mp4">HRER</a> to view the generated video.</p>
+    </center></td>
+  </tr> 
+</center>
+</table>
+</center>
+
+### (3) Other methods
+
+In preparation.
+
+
+## Customize your own approach
+
+Our codebase essentially supports all the commonly used components in video generation. You can manage your experiments flexibly by adding corresponding registration classes, including `ENGINE, MODEL, DATASETS, EMBEDDER, AUTO_ENCODER, DISTRIBUTION, VISUAL, DIFFUSION, PRETRAIN`, and can be compatible with all our open-source algorithms according to your own needs. If you have any questions, feel free to give us your feedback at any time.
+
+
+
+## BibTeX
+
+If this repo is useful to you, please cite our corresponding technical paper.
+
+
+```bibtex
+@article{2023i2vgenxl,
+  title={I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models},
+  author={Zhang, Shiwei and Wang, Jiayu and Zhang, Yingya and Zhao, Kang and Yuan, Hangjie and Qing, Zhiwu and Wang, Xiang  and Zhao, Deli and Zhou, Jingren},
+  booktitle={arXiv preprint arXiv:2311.04145},
+  year={2023}
+}
+@article{2023videocomposer,
+  title={VideoComposer: Compositional Video Synthesis with Motion Controllability},
+  author={Wang, Xiang and Yuan, Hangjie and Zhang, Shiwei and Chen, Dayou and Wang, Jiuniu, and Zhang, Yingya, and Shen, Yujun, and Zhao, Deli and Zhou, Jingren},
+  booktitle={arXiv preprint arXiv:2306.02018},
+  year={2023}
+}
+@article{wang2023modelscope,
+  title={Modelscope text-to-video technical report},
+  author={Wang, Jiuniu and Yuan, Hangjie and Chen, Dayou and Zhang, Yingya and Wang, Xiang and Zhang, Shiwei},
+  journal={arXiv preprint arXiv:2308.06571},
+  year={2023}
+}
+@article{dreamvideo,
+  title={DreamVideo: Composing Your Dream Videos with Customized Subject and Motion},
+  author={Wei, Yujie and Zhang, Shiwei and Qing, Zhiwu and Yuan, Hangjie and Liu, Zhiheng and Liu, Yu and Zhang, Yingya and Zhou, Jingren and Shan, Hongming},
+  journal={arXiv preprint arXiv:2312.04433},
+  year={2023}
+}
+@article{qing2023higen,
+  title={Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation},
+  author={Qing, Zhiwu and Zhang, Shiwei and Wang, Jiayu and Wang, Xiang and Wei, Yujie and Zhang, Yingya and Gao, Changxin and Sang, Nong },
+  journal={arXiv preprint arXiv:2312.04483},
+  year={2023}
+}
+@article{wang2023videolcm,
+  title={VideoLCM: Video Latent Consistency Model},
+  author={Wang, Xiang and Zhang, Shiwei and Zhang, Han and Liu, Yu and Zhang, Yingya and Gao, Changxin and Sang, Nong },
+  journal={arXiv preprint arXiv:2312.09109},
+  year={2023}
+}
+```
+
+## Disclaimer
+
+This open-source model is trained with using [WebVid-10M](https://m-bain.github.io/webvid-dataset/) and [LAION-400M](https://laion.ai/blog/laion-400-open-dataset/) datasets and is intended for <strong>RESEARCH/NON-COMMERCIAL USE ONLY</strong>. 

doc/i2vgen-xl.md

@@ -0,0 +1,19 @@
+# I2VGen-XL
+
+Official repo for [I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models](https://arxiv.org/abs/2311.04145)
+
+Please see [Project Page](https://i2vgen-xl.github.io) for more examples.
+
+
+![method](../source/i2vgen_fig_02.jpg "method")
+
+
+I2VGen-XL is capable of generating high-quality, realistically animated, and temporally coherent high-definition videos from a single input static image, based on user input.
+
+
+*Our initial version has already been open-sourced on [Modelscope](https://modelscope.cn/models/damo/Image-to-Video/summary). This project focuses on improving the version, especially in terms of motions and semantics.*
+
+## Examples
+
+![figure2](../source/i2vgen_fig_04.png "figure2")
+

doc/introduction.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d416283eb95212e1fd45c2d02045a836160929fd15e7120dd77998380c7656
+size 4857845

models/i2vgen_xl_00854500.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3921efea21a4aac109a03ea8ca1f4f6a756ba82d30bfeb82b83f94a7aff8f73
+size 5682502260

models/open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a78ef8e8c73fd0df621682e7a8e8eb36c6916cb3c16b291a082ecd52ab79cc4
+size 3944692325

models/stable_diffusion_image_key_temporal_attention_x1.json

@@ -0,0 +1 @@
+["input_blocks.0.0.weight", "input_blocks.0.0.bias", "input_blocks.1.0.in_layers.0.weight", "input_blocks.1.0.in_layers.0.bias", "input_blocks.1.0.in_layers.2.weight", "input_blocks.1.0.in_layers.2.bias", "input_blocks.1.0.emb_layers.1.weight", "input_blocks.1.0.emb_layers.1.bias", "input_blocks.1.0.out_layers.0.weight", "input_blocks.1.0.out_layers.0.bias", "input_blocks.1.0.out_layers.3.weight", "input_blocks.1.0.out_layers.3.bias", "input_blocks.1.1.norm.weight", "input_blocks.1.1.norm.bias", "input_blocks.1.1.proj_in.weight", "input_blocks.1.1.proj_in.bias", "input_blocks.1.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.1.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.1.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.1.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.1.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.1.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.1.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.1.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.1.1.transformer_blocks.0.norm1.weight", "input_blocks.1.1.transformer_blocks.0.norm1.bias", "input_blocks.1.1.transformer_blocks.0.norm2.weight", "input_blocks.1.1.transformer_blocks.0.norm2.bias", "input_blocks.1.1.transformer_blocks.0.norm3.weight", "input_blocks.1.1.transformer_blocks.0.norm3.bias", "input_blocks.1.1.proj_out.weight", "input_blocks.1.1.proj_out.bias", "input_blocks.2.0.in_layers.0.weight", "input_blocks.2.0.in_layers.0.bias", "input_blocks.2.0.in_layers.2.weight", "input_blocks.2.0.in_layers.2.bias", "input_blocks.2.0.emb_layers.1.weight", "input_blocks.2.0.emb_layers.1.bias", "input_blocks.2.0.out_layers.0.weight", "input_blocks.2.0.out_layers.0.bias", "input_blocks.2.0.out_layers.3.weight", "input_blocks.2.0.out_layers.3.bias", "input_blocks.2.1.norm.weight", "input_blocks.2.1.norm.bias", "input_blocks.2.1.proj_in.weight", "input_blocks.2.1.proj_in.bias", "input_blocks.2.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.2.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.2.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.2.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.2.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.2.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.2.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.2.1.transformer_blocks.0.norm1.weight", "input_blocks.2.1.transformer_blocks.0.norm1.bias", "input_blocks.2.1.transformer_blocks.0.norm2.weight", "input_blocks.2.1.transformer_blocks.0.norm2.bias", "input_blocks.2.1.transformer_blocks.0.norm3.weight", "input_blocks.2.1.transformer_blocks.0.norm3.bias", "input_blocks.2.1.proj_out.weight", "input_blocks.2.1.proj_out.bias", "input_blocks.3.op.weight", "input_blocks.3.op.bias", "input_blocks.4.0.in_layers.0.weight", "input_blocks.4.0.in_layers.0.bias", "input_blocks.4.0.in_layers.2.weight", "input_blocks.4.0.in_layers.2.bias", "input_blocks.4.0.emb_layers.1.weight", "input_blocks.4.0.emb_layers.1.bias", "input_blocks.4.0.out_layers.0.weight", "input_blocks.4.0.out_layers.0.bias", "input_blocks.4.0.out_layers.3.weight", "input_blocks.4.0.out_layers.3.bias", "input_blocks.4.0.skip_connection.weight", "input_blocks.4.0.skip_connection.bias", "input_blocks.4.1.norm.weight", "input_blocks.4.1.norm.bias", "input_blocks.4.1.proj_in.weight", "input_blocks.4.1.proj_in.bias", "input_blocks.4.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.4.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.4.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.4.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.4.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.4.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.4.1.transformer_blocks.0.norm1.weight", "input_blocks.4.1.transformer_blocks.0.norm1.bias", "input_blocks.4.1.transformer_blocks.0.norm2.weight", "input_blocks.4.1.transformer_blocks.0.norm2.bias", "input_blocks.4.1.transformer_blocks.0.norm3.weight", "input_blocks.4.1.transformer_blocks.0.norm3.bias", "input_blocks.4.1.proj_out.weight", "input_blocks.4.1.proj_out.bias", "input_blocks.5.0.in_layers.0.weight", "input_blocks.5.0.in_layers.0.bias", "input_blocks.5.0.in_layers.2.weight", "input_blocks.5.0.in_layers.2.bias", "input_blocks.5.0.emb_layers.1.weight", "input_blocks.5.0.emb_layers.1.bias", "input_blocks.5.0.out_layers.0.weight", "input_blocks.5.0.out_layers.0.bias", "input_blocks.5.0.out_layers.3.weight", "input_blocks.5.0.out_layers.3.bias", "input_blocks.5.1.norm.weight", "input_blocks.5.1.norm.bias", "input_blocks.5.1.proj_in.weight", "input_blocks.5.1.proj_in.bias", "input_blocks.5.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.5.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.5.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.5.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.5.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.5.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.5.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.5.1.transformer_blocks.0.norm1.weight", "input_blocks.5.1.transformer_blocks.0.norm1.bias", "input_blocks.5.1.transformer_blocks.0.norm2.weight", "input_blocks.5.1.transformer_blocks.0.norm2.bias", "input_blocks.5.1.transformer_blocks.0.norm3.weight", "input_blocks.5.1.transformer_blocks.0.norm3.bias", "input_blocks.5.1.proj_out.weight", "input_blocks.5.1.proj_out.bias", "input_blocks.6.op.weight", "input_blocks.6.op.bias", "input_blocks.7.0.in_layers.0.weight", "input_blocks.7.0.in_layers.0.bias", "input_blocks.7.0.in_layers.2.weight", "input_blocks.7.0.in_layers.2.bias", "input_blocks.7.0.emb_layers.1.weight", "input_blocks.7.0.emb_layers.1.bias", "input_blocks.7.0.out_layers.0.weight", "input_blocks.7.0.out_layers.0.bias", "input_blocks.7.0.out_layers.3.weight", "input_blocks.7.0.out_layers.3.bias", "input_blocks.7.0.skip_connection.weight", "input_blocks.7.0.skip_connection.bias", "input_blocks.7.1.norm.weight", "input_blocks.7.1.norm.bias", "input_blocks.7.1.proj_in.weight", "input_blocks.7.1.proj_in.bias", "input_blocks.7.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.7.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.7.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.7.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.7.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.7.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.7.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.7.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.7.1.transformer_blocks.0.norm1.weight", "input_blocks.7.1.transformer_blocks.0.norm1.bias", "input_blocks.7.1.transformer_blocks.0.norm2.weight", "input_blocks.7.1.transformer_blocks.0.norm2.bias", "input_blocks.7.1.transformer_blocks.0.norm3.weight", "input_blocks.7.1.transformer_blocks.0.norm3.bias", "input_blocks.7.1.proj_out.weight", "input_blocks.7.1.proj_out.bias", "input_blocks.8.0.in_layers.0.weight", "input_blocks.8.0.in_layers.0.bias", "input_blocks.8.0.in_layers.2.weight", "input_blocks.8.0.in_layers.2.bias", "input_blocks.8.0.emb_layers.1.weight", "input_blocks.8.0.emb_layers.1.bias", "input_blocks.8.0.out_layers.0.weight", "input_blocks.8.0.out_layers.0.bias", "input_blocks.8.0.out_layers.3.weight", "input_blocks.8.0.out_layers.3.bias", "input_blocks.8.1.norm.weight", "input_blocks.8.1.norm.bias", "input_blocks.8.1.proj_in.weight", "input_blocks.8.1.proj_in.bias", "input_blocks.8.1.transformer_blocks.0.attn1.to_q.weight", "input_blocks.8.1.transformer_blocks.0.attn1.to_k.weight", "input_blocks.8.1.transformer_blocks.0.attn1.to_v.weight", "input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight", "input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias", "input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight", "input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias", "input_blocks.8.1.transformer_blocks.0.ff.net.2.weight", "input_blocks.8.1.transformer_blocks.0.ff.net.2.bias", "input_blocks.8.1.transformer_blocks.0.attn2.to_q.weight", "input_blocks.8.1.transformer_blocks.0.attn2.to_k.weight", "input_blocks.8.1.transformer_blocks.0.attn2.to_v.weight", "input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight", "input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias", "input_blocks.8.1.transformer_blocks.0.norm1.weight", "input_blocks.8.1.transformer_blocks.0.norm1.bias", "input_blocks.8.1.transformer_blocks.0.norm2.weight", "input_blocks.8.1.transformer_blocks.0.norm2.bias", "input_blocks.8.1.transformer_blocks.0.norm3.weight", "input_blocks.8.1.transformer_blocks.0.norm3.bias", "input_blocks.8.1.proj_out.weight", "input_blocks.8.1.proj_out.bias", "input_blocks.9.op.weight", "input_blocks.9.op.bias", "input_blocks.10.0.in_layers.0.weight", "input_blocks.10.0.in_layers.0.bias", "input_blocks.10.0.in_layers.2.weight", "input_blocks.10.0.in_layers.2.bias", "input_blocks.10.0.emb_layers.1.weight", "input_blocks.10.0.emb_layers.1.bias", "input_blocks.10.0.out_layers.0.weight", "input_blocks.10.0.out_layers.0.bias", "input_blocks.10.0.out_layers.3.weight", "input_blocks.10.0.out_layers.3.bias", "input_blocks.11.0.in_layers.0.weight", "input_blocks.11.0.in_layers.0.bias", "input_blocks.11.0.in_layers.2.weight", "input_blocks.11.0.in_layers.2.bias", "input_blocks.11.0.emb_layers.1.weight", "input_blocks.11.0.emb_layers.1.bias", "input_blocks.11.0.out_layers.0.weight", "input_blocks.11.0.out_layers.0.bias", "input_blocks.11.0.out_layers.3.weight", "input_blocks.11.0.out_layers.3.bias", "middle_block.0.in_layers.0.weight", "middle_block.0.in_layers.0.bias", "middle_block.0.in_layers.2.weight", "middle_block.0.in_layers.2.bias", "middle_block.0.emb_layers.1.weight", "middle_block.0.emb_layers.1.bias", "middle_block.0.out_layers.0.weight", "middle_block.0.out_layers.0.bias", "middle_block.0.out_layers.3.weight", "middle_block.0.out_layers.3.bias", "middle_block.1.norm.weight", "middle_block.1.norm.bias", "middle_block.1.proj_in.weight", "middle_block.1.proj_in.bias", "middle_block.1.transformer_blocks.0.attn1.to_q.weight", "middle_block.1.transformer_blocks.0.attn1.to_k.weight", "middle_block.1.transformer_blocks.0.attn1.to_v.weight", "middle_block.1.transformer_blocks.0.attn1.to_out.0.weight", "middle_block.1.transformer_blocks.0.attn1.to_out.0.bias", "middle_block.1.transformer_blocks.0.ff.net.0.proj.weight", "middle_block.1.transformer_blocks.0.ff.net.0.proj.bias", "middle_block.1.transformer_blocks.0.ff.net.2.weight", "middle_block.1.transformer_blocks.0.ff.net.2.bias", "middle_block.1.transformer_blocks.0.attn2.to_q.weight", "middle_block.1.transformer_blocks.0.attn2.to_k.weight", "middle_block.1.transformer_blocks.0.attn2.to_v.weight", "middle_block.1.transformer_blocks.0.attn2.to_out.0.weight", "middle_block.1.transformer_blocks.0.attn2.to_out.0.bias", "middle_block.1.transformer_blocks.0.norm1.weight", "middle_block.1.transformer_blocks.0.norm1.bias", "middle_block.1.transformer_blocks.0.norm2.weight", "middle_block.1.transformer_blocks.0.norm2.bias", "middle_block.1.transformer_blocks.0.norm3.weight", "middle_block.1.transformer_blocks.0.norm3.bias", "middle_block.1.proj_out.weight", "middle_block.1.proj_out.bias", "middle_block.3.in_layers.0.weight", "middle_block.3.in_layers.0.bias", "middle_block.3.in_layers.2.weight", "middle_block.3.in_layers.2.bias", "middle_block.3.emb_layers.1.weight", "middle_block.3.emb_layers.1.bias", "middle_block.3.out_layers.0.weight", "middle_block.3.out_layers.0.bias", "middle_block.3.out_layers.3.weight", "middle_block.3.out_layers.3.bias", "output_blocks.0.0.in_layers.0.weight", "output_blocks.0.0.in_layers.0.bias", "output_blocks.0.0.in_layers.2.weight", "output_blocks.0.0.in_layers.2.bias", "output_blocks.0.0.emb_layers.1.weight", "output_blocks.0.0.emb_layers.1.bias", "output_blocks.0.0.out_layers.0.weight", "output_blocks.0.0.out_layers.0.bias", "output_blocks.0.0.out_layers.3.weight", "output_blocks.0.0.out_layers.3.bias", "output_blocks.0.0.skip_connection.weight", "output_blocks.0.0.skip_connection.bias", "output_blocks.1.0.in_layers.0.weight", "output_blocks.1.0.in_layers.0.bias", "output_blocks.1.0.in_layers.2.weight", "output_blocks.1.0.in_layers.2.bias", "output_blocks.1.0.emb_layers.1.weight", "output_blocks.1.0.emb_layers.1.bias", "output_blocks.1.0.out_layers.0.weight", "output_blocks.1.0.out_layers.0.bias", "output_blocks.1.0.out_layers.3.weight", "output_blocks.1.0.out_layers.3.bias", "output_blocks.1.0.skip_connection.weight", "output_blocks.1.0.skip_connection.bias", "output_blocks.2.0.in_layers.0.weight", "output_blocks.2.0.in_layers.0.bias", "output_blocks.2.0.in_layers.2.weight", "output_blocks.2.0.in_layers.2.bias", "output_blocks.2.0.emb_layers.1.weight", "output_blocks.2.0.emb_layers.1.bias", "output_blocks.2.0.out_layers.0.weight", "output_blocks.2.0.out_layers.0.bias", "output_blocks.2.0.out_layers.3.weight", "output_blocks.2.0.out_layers.3.bias", "output_blocks.2.0.skip_connection.weight", "output_blocks.2.0.skip_connection.bias", "output_blocks.2.1.conv.weight", "output_blocks.2.1.conv.bias", "output_blocks.3.0.in_layers.0.weight", "output_blocks.3.0.in_layers.0.bias", "output_blocks.3.0.in_layers.2.weight", "output_blocks.3.0.in_layers.2.bias", "output_blocks.3.0.emb_layers.1.weight", "output_blocks.3.0.emb_layers.1.bias", "output_blocks.3.0.out_layers.0.weight", "output_blocks.3.0.out_layers.0.bias", "output_blocks.3.0.out_layers.3.weight", "output_blocks.3.0.out_layers.3.bias", "output_blocks.3.0.skip_connection.weight", "output_blocks.3.0.skip_connection.bias", "output_blocks.3.1.norm.weight", "output_blocks.3.1.norm.bias", "output_blocks.3.1.proj_in.weight", "output_blocks.3.1.proj_in.bias", "output_blocks.3.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.3.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.3.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.3.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.3.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.3.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.3.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.3.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.3.1.transformer_blocks.0.norm1.weight", "output_blocks.3.1.transformer_blocks.0.norm1.bias", "output_blocks.3.1.transformer_blocks.0.norm2.weight", "output_blocks.3.1.transformer_blocks.0.norm2.bias", "output_blocks.3.1.transformer_blocks.0.norm3.weight", "output_blocks.3.1.transformer_blocks.0.norm3.bias", "output_blocks.3.1.proj_out.weight", "output_blocks.3.1.proj_out.bias", "output_blocks.4.0.in_layers.0.weight", "output_blocks.4.0.in_layers.0.bias", "output_blocks.4.0.in_layers.2.weight", "output_blocks.4.0.in_layers.2.bias", "output_blocks.4.0.emb_layers.1.weight", "output_blocks.4.0.emb_layers.1.bias", "output_blocks.4.0.out_layers.0.weight", "output_blocks.4.0.out_layers.0.bias", "output_blocks.4.0.out_layers.3.weight", "output_blocks.4.0.out_layers.3.bias", "output_blocks.4.0.skip_connection.weight", "output_blocks.4.0.skip_connection.bias", "output_blocks.4.1.norm.weight", "output_blocks.4.1.norm.bias", "output_blocks.4.1.proj_in.weight", "output_blocks.4.1.proj_in.bias", "output_blocks.4.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.4.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.4.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.4.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.4.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.4.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.4.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.4.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.4.1.transformer_blocks.0.norm1.weight", "output_blocks.4.1.transformer_blocks.0.norm1.bias", "output_blocks.4.1.transformer_blocks.0.norm2.weight", "output_blocks.4.1.transformer_blocks.0.norm2.bias", "output_blocks.4.1.transformer_blocks.0.norm3.weight", "output_blocks.4.1.transformer_blocks.0.norm3.bias", "output_blocks.4.1.proj_out.weight", "output_blocks.4.1.proj_out.bias", "output_blocks.5.0.in_layers.0.weight", "output_blocks.5.0.in_layers.0.bias", "output_blocks.5.0.in_layers.2.weight", "output_blocks.5.0.in_layers.2.bias", "output_blocks.5.0.emb_layers.1.weight", "output_blocks.5.0.emb_layers.1.bias", "output_blocks.5.0.out_layers.0.weight", "output_blocks.5.0.out_layers.0.bias", "output_blocks.5.0.out_layers.3.weight", "output_blocks.5.0.out_layers.3.bias", "output_blocks.5.0.skip_connection.weight", "output_blocks.5.0.skip_connection.bias", "output_blocks.5.1.norm.weight", "output_blocks.5.1.norm.bias", "output_blocks.5.1.proj_in.weight", "output_blocks.5.1.proj_in.bias", "output_blocks.5.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.5.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.5.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.5.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.5.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.5.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.5.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.5.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.5.1.transformer_blocks.0.norm1.weight", "output_blocks.5.1.transformer_blocks.0.norm1.bias", "output_blocks.5.1.transformer_blocks.0.norm2.weight", "output_blocks.5.1.transformer_blocks.0.norm2.bias", "output_blocks.5.1.transformer_blocks.0.norm3.weight", "output_blocks.5.1.transformer_blocks.0.norm3.bias", "output_blocks.5.1.proj_out.weight", "output_blocks.5.1.proj_out.bias", "output_blocks.5.3.conv.weight", "output_blocks.5.3.conv.bias", "output_blocks.6.0.in_layers.0.weight", "output_blocks.6.0.in_layers.0.bias", "output_blocks.6.0.in_layers.2.weight", "output_blocks.6.0.in_layers.2.bias", "output_blocks.6.0.emb_layers.1.weight", "output_blocks.6.0.emb_layers.1.bias", "output_blocks.6.0.out_layers.0.weight", "output_blocks.6.0.out_layers.0.bias", "output_blocks.6.0.out_layers.3.weight", "output_blocks.6.0.out_layers.3.bias", "output_blocks.6.0.skip_connection.weight", "output_blocks.6.0.skip_connection.bias", "output_blocks.6.1.norm.weight", "output_blocks.6.1.norm.bias", "output_blocks.6.1.proj_in.weight", "output_blocks.6.1.proj_in.bias", "output_blocks.6.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.6.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.6.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.6.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.6.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.6.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.6.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.6.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.6.1.transformer_blocks.0.norm1.weight", "output_blocks.6.1.transformer_blocks.0.norm1.bias", "output_blocks.6.1.transformer_blocks.0.norm2.weight", "output_blocks.6.1.transformer_blocks.0.norm2.bias", "output_blocks.6.1.transformer_blocks.0.norm3.weight", "output_blocks.6.1.transformer_blocks.0.norm3.bias", "output_blocks.6.1.proj_out.weight", "output_blocks.6.1.proj_out.bias", "output_blocks.7.0.in_layers.0.weight", "output_blocks.7.0.in_layers.0.bias", "output_blocks.7.0.in_layers.2.weight", "output_blocks.7.0.in_layers.2.bias", "output_blocks.7.0.emb_layers.1.weight", "output_blocks.7.0.emb_layers.1.bias", "output_blocks.7.0.out_layers.0.weight", "output_blocks.7.0.out_layers.0.bias", "output_blocks.7.0.out_layers.3.weight", "output_blocks.7.0.out_layers.3.bias", "output_blocks.7.0.skip_connection.weight", "output_blocks.7.0.skip_connection.bias", "output_blocks.7.1.norm.weight", "output_blocks.7.1.norm.bias", "output_blocks.7.1.proj_in.weight", "output_blocks.7.1.proj_in.bias", "output_blocks.7.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.7.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.7.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.7.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.7.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.7.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.7.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.7.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.7.1.transformer_blocks.0.norm1.weight", "output_blocks.7.1.transformer_blocks.0.norm1.bias", "output_blocks.7.1.transformer_blocks.0.norm2.weight", "output_blocks.7.1.transformer_blocks.0.norm2.bias", "output_blocks.7.1.transformer_blocks.0.norm3.weight", "output_blocks.7.1.transformer_blocks.0.norm3.bias", "output_blocks.7.1.proj_out.weight", "output_blocks.7.1.proj_out.bias", "output_blocks.8.0.in_layers.0.weight", "output_blocks.8.0.in_layers.0.bias", "output_blocks.8.0.in_layers.2.weight", "output_blocks.8.0.in_layers.2.bias", "output_blocks.8.0.emb_layers.1.weight", "output_blocks.8.0.emb_layers.1.bias", "output_blocks.8.0.out_layers.0.weight", "output_blocks.8.0.out_layers.0.bias", "output_blocks.8.0.out_layers.3.weight", "output_blocks.8.0.out_layers.3.bias", "output_blocks.8.0.skip_connection.weight", "output_blocks.8.0.skip_connection.bias", "output_blocks.8.1.norm.weight", "output_blocks.8.1.norm.bias", "output_blocks.8.1.proj_in.weight", "output_blocks.8.1.proj_in.bias", "output_blocks.8.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.8.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.8.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.8.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.8.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.8.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.8.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.8.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.8.1.transformer_blocks.0.norm1.weight", "output_blocks.8.1.transformer_blocks.0.norm1.bias", "output_blocks.8.1.transformer_blocks.0.norm2.weight", "output_blocks.8.1.transformer_blocks.0.norm2.bias", "output_blocks.8.1.transformer_blocks.0.norm3.weight", "output_blocks.8.1.transformer_blocks.0.norm3.bias", "output_blocks.8.1.proj_out.weight", "output_blocks.8.1.proj_out.bias", "output_blocks.8.3.conv.weight", "output_blocks.8.3.conv.bias", "output_blocks.9.0.in_layers.0.weight", "output_blocks.9.0.in_layers.0.bias", "output_blocks.9.0.in_layers.2.weight", "output_blocks.9.0.in_layers.2.bias", "output_blocks.9.0.emb_layers.1.weight", "output_blocks.9.0.emb_layers.1.bias", "output_blocks.9.0.out_layers.0.weight", "output_blocks.9.0.out_layers.0.bias", "output_blocks.9.0.out_layers.3.weight", "output_blocks.9.0.out_layers.3.bias", "output_blocks.9.0.skip_connection.weight", "output_blocks.9.0.skip_connection.bias", "output_blocks.9.1.norm.weight", "output_blocks.9.1.norm.bias", "output_blocks.9.1.proj_in.weight", "output_blocks.9.1.proj_in.bias", "output_blocks.9.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.9.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.9.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.9.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.9.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.9.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.9.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.9.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.9.1.transformer_blocks.0.norm1.weight", "output_blocks.9.1.transformer_blocks.0.norm1.bias", "output_blocks.9.1.transformer_blocks.0.norm2.weight", "output_blocks.9.1.transformer_blocks.0.norm2.bias", "output_blocks.9.1.transformer_blocks.0.norm3.weight", "output_blocks.9.1.transformer_blocks.0.norm3.bias", "output_blocks.9.1.proj_out.weight", "output_blocks.9.1.proj_out.bias", "output_blocks.10.0.in_layers.0.weight", "output_blocks.10.0.in_layers.0.bias", "output_blocks.10.0.in_layers.2.weight", "output_blocks.10.0.in_layers.2.bias", "output_blocks.10.0.emb_layers.1.weight", "output_blocks.10.0.emb_layers.1.bias", "output_blocks.10.0.out_layers.0.weight", "output_blocks.10.0.out_layers.0.bias", "output_blocks.10.0.out_layers.3.weight", "output_blocks.10.0.out_layers.3.bias", "output_blocks.10.0.skip_connection.weight", "output_blocks.10.0.skip_connection.bias", "output_blocks.10.1.norm.weight", "output_blocks.10.1.norm.bias", "output_blocks.10.1.proj_in.weight", "output_blocks.10.1.proj_in.bias", "output_blocks.10.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.10.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.10.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.10.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.10.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.10.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.10.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.10.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.10.1.transformer_blocks.0.norm1.weight", "output_blocks.10.1.transformer_blocks.0.norm1.bias", "output_blocks.10.1.transformer_blocks.0.norm2.weight", "output_blocks.10.1.transformer_blocks.0.norm2.bias", "output_blocks.10.1.transformer_blocks.0.norm3.weight", "output_blocks.10.1.transformer_blocks.0.norm3.bias", "output_blocks.10.1.proj_out.weight", "output_blocks.10.1.proj_out.bias", "output_blocks.11.0.in_layers.0.weight", "output_blocks.11.0.in_layers.0.bias", "output_blocks.11.0.in_layers.2.weight", "output_blocks.11.0.in_layers.2.bias", "output_blocks.11.0.emb_layers.1.weight", "output_blocks.11.0.emb_layers.1.bias", "output_blocks.11.0.out_layers.0.weight", "output_blocks.11.0.out_layers.0.bias", "output_blocks.11.0.out_layers.3.weight", "output_blocks.11.0.out_layers.3.bias", "output_blocks.11.0.skip_connection.weight", "output_blocks.11.0.skip_connection.bias", "output_blocks.11.1.norm.weight", "output_blocks.11.1.norm.bias", "output_blocks.11.1.proj_in.weight", "output_blocks.11.1.proj_in.bias", "output_blocks.11.1.transformer_blocks.0.attn1.to_q.weight", "output_blocks.11.1.transformer_blocks.0.attn1.to_k.weight", "output_blocks.11.1.transformer_blocks.0.attn1.to_v.weight", "output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.weight", "output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.bias", "output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.weight", "output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.bias", "output_blocks.11.1.transformer_blocks.0.ff.net.2.weight", "output_blocks.11.1.transformer_blocks.0.ff.net.2.bias", "output_blocks.11.1.transformer_blocks.0.attn2.to_q.weight", "output_blocks.11.1.transformer_blocks.0.attn2.to_k.weight", "output_blocks.11.1.transformer_blocks.0.attn2.to_v.weight", "output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.weight", "output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.bias", "output_blocks.11.1.transformer_blocks.0.norm1.weight", "output_blocks.11.1.transformer_blocks.0.norm1.bias", "output_blocks.11.1.transformer_blocks.0.norm2.weight", "output_blocks.11.1.transformer_blocks.0.norm2.bias", "output_blocks.11.1.transformer_blocks.0.norm3.weight", "output_blocks.11.1.transformer_blocks.0.norm3.bias", "output_blocks.11.1.proj_out.weight", "output_blocks.11.1.proj_out.bias", "out.0.weight", "out.0.bias", "out.2.weight", "out.2.bias"]

models/v2-1_512-ema-pruned.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ecb782561455673c4b78d05093494b9c539fc6bfc08f3a9a4a0dd7b0b10f36
+size 5214865159