Merge branch 'main' of https://huggingface.co./damo-vilab/text-to-video-ms-1.7b-legacy into main

README.md

@@ -33,26 +33,46 @@ This model has a wide range of applications, and can reason and generate videos
 Let's first install the libraries required:
 
 ```bash
-$ pip install diffusers transformers git+https://github.com/huggingface/accelerate.git
+$ pip install git+https://github.com/huggingface/diffusers transformers accelerate
 ```
 
 Now, generate a video:
 
 ```python
 import torch
-from diffusers import TextToVideoMSPipeline, DPMSolverMultistepScheduler
+from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
 from diffusers.utils import export_to_video
 
-pipe = TextToVideoMSPipeline.from_pretrained("diffusers/ms-text-to-video-1.7b", torch_dtype=torch.float16)
+pipe = DiffusionPipeline.from_pretrained("damo-vilab/text-to-video-ms-1.7b-legacy", torch_dtype=torch.float16)
 pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
-pipe = pipe.to("cuda")
+pipe.enable_cpu_model_offload()
 
 prompt = "Spiderman is surfing"
-video_frames = pipe(prompt).frames
+video_frames = pipe(prompt, num_inference_steps=25).frames
 video_path = export_to_video(video_frames)
-print(video_path)
 ```
 
+Here are some results:
+
+<table>
+    <tr>
+        <td><center>
+        An astronaut riding a horse.
+        <br>
+        <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astr.gif"
+            alt="An astronaut riding a horse."
+            style="width: 300px;" />
+        </center></td>
+        <td ><center>
+        Darth vader surfing in waves.
+        <br>
+        <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/vader.gif"
+            alt="Darth vader surfing in waves."
+            style="width: 300px;" />
+        </center></td>
+    </tr>
+</table>
+
 ## View results
 
 The above code will display the save path of the output video, and the current encoding format can be played with [VLC player](https://www.videolan.org/vlc/).

model_index.json

@@ -1,5 +1,5 @@
 {
-  "_class_name": "TextToVideoMSPipeline",
+  "_class_name": "TextToVideoSDPipeline",
   "_diffusers_version": "0.15.0.dev0",
   "scheduler": [
     "diffusers",