Update README.md

README.md

@@ -1,3 +1,47 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
+# ExVideo
+
+ExVideo is a post-tuning technique aimed at enhancing the capability of video generation models. We have extended CogVideoX-5B to generate videos up to 129 frames long. 
+
+This is our second publicly released model, incorporating LoRA into the structure of CogVideoX-5B.
+
+
+* [Project Page](https://ecnu-cilab.github.io/ExVideoProjectPage/)
+* [Source Code](https://github.com/modelscope/DiffSynth-Studio)
+* [Technical report](https://arxiv.org/abs/2406.14130)
+
+## Usages
+
+```python
+from diffsynth import ModelManager, CogVideoPipeline, save_video, download_models
+import torch
+
+
+download_models(["CogVideoX-5B", "ExVideo-CogVideoX-LoRA-129f-v1"])
+model_manager = ModelManager(torch_dtype=torch.bfloat16)
+model_manager.load_models([
+ "models/CogVideo/CogVideoX-5b/text_encoder",
+ "models/CogVideo/CogVideoX-5b/transformer",
+ "models/CogVideo/CogVideoX-5b/vae/diffusion_pytorch_model.safetensors",
+])
+model_manager.load_lora("models/lora/ExVideo-CogVideoX-LoRA-129f-v1.safetensors")
+pipe = CogVideoPipeline.from_model_manager(model_manager)
+
+torch.manual_seed(6)
+video = pipe(
+ prompt="an astronaut riding a horse on Mars.",
+ height=480, width=720, num_frames=129,
+ cfg_scale=7.0, num_inference_steps=100,
+)
+save_video(video, "video_with_lora.mp4", fps=8, quality=5)
+```
+
+Please refer to [DiffSynth](https://github.com/modelscope/DiffSynth-Studio) for more information.
+
+## Examples
+
+Prompt: an astronaut riding a horse on Mars.
+
+<video src="videos/demo.mp4" controls="controls"></video>