Stability-AI · chunhanyao-stable · Aug 3, 2024 · Aug 2, 2024 · Aug 2, 2024 · Aug 2, 2024
diff --git a/README.md b/README.md
@@ -9,15 +9,16 @@
 - We are releasing **[Stable Video 4D (SV4D)](https://huggingface.co/stabilityai/sv4d)**, a video-to-4D diffusion model for novel-view video synthesis. For research purposes:
     - **SV4D** was trained to generate 40 frames (5 video frames x 8 camera views) at 576x576 resolution, given 5 context frames (the input video), and 8 reference views (synthesised from the first frame of the input video, using a multi-view diffusion model like SV3D) of the same size, ideally white-background images with one object.
     - To generate longer novel-view videos (21 frames), we propose a novel sampling method using SV4D, by first sampling 5 anchor frames and then densely sampling the remaining frames while maintaining temporal consistency.
+    - You can run the community-build gradio demo locally by running `python -m scripts.demo.gradio_app_sv4d`.
     - Please check our [project page](https://sv4d.github.io), [tech report](https://sv4d.github.io/static/sv4d_technical_report.pdf) and [video summary](https://www.youtube.com/watch?v=RBP8vdAWTgk) for more details.
 
-**QUICKSTART** : `python scripts/sampling/simple_video_sample_4d.py --input_path assets/test_video1.mp4 --output_folder outputs/sv4d` (after downloading [sv4d.safetensors](https://huggingface.co/stabilityai/sv4d) and [sv3d_u.safetensors](https://huggingface.co/stabilityai/sv3d) from HuggingFace into `checkpoints/`)
+**QUICKSTART** : `python scripts/sampling/simple_video_sample_4d.py --input_path assets/sv4d_example_video/test_video1.mp4 --output_folder outputs/sv4d` (after downloading [sv4d.safetensors](https://huggingface.co/stabilityai/sv4d) and [sv3d_u.safetensors](https://huggingface.co/stabilityai/sv3d) from HuggingFace into `checkpoints/`)
 
 To run **SV4D** on a single input video of 21 frames:
 - Download SV3D models (`sv3d_u.safetensors` and `sv3d_p.safetensors`) from [here](https://huggingface.co/stabilityai/sv3d) and SV4D model (`sv4d.safetensors`) from [here](https://huggingface.co/stabilityai/sv4d) to `checkpoints/`
 - Run `python scripts/sampling/simple_video_sample_4d.py --input_path <path/to/video>`
     - `input_path` : The input video `<path/to/video>` can be
-      - a single video file in `gif` or `mp4` format, such as `assets/test_video1.mp4`, or
+      - a single video file in `gif` or `mp4` format, such as `assets/sv4d_example_video/test_video1.mp4`, or
       - a folder containing images of video frames in `.jpg`, `.jpeg`, or `.png` format, or
       - a file name pattern matching images of video frames.
     - `num_steps` : default is 20, can increase to 50 for better quality but longer sampling time.

diff --git a/assets/sv4d_example_video/bunnyman.mp4 b/assets/sv4d_example_video/bunnyman.mp4
diff --git a/assets/sv4d_example_video/dolphin.mp4 b/assets/sv4d_example_video/dolphin.mp4
diff --git a/assets/sv4d_example_video/green_robot.mp4 b/assets/sv4d_example_video/green_robot.mp4
diff --git a/assets/sv4d_example_video/guppie_v0.mp4 b/assets/sv4d_example_video/guppie_v0.mp4
diff --git a/assets/hiphop_parrot.mp4 → assets/sv4d_example_video/hiphop_parrot.mp4 b/assets/hiphop_parrot.mp4 → assets/sv4d_example_video/hiphop_parrot.mp4
diff --git a/assets/sv4d_example_video/human5.mp4 b/assets/sv4d_example_video/human5.mp4
diff --git a/assets/sv4d_example_video/human7.mp4 b/assets/sv4d_example_video/human7.mp4
diff --git a/assets/sv4d_example_video/human_slow_black_bg.mp4 b/assets/sv4d_example_video/human_slow_black_bg.mp4
diff --git a/assets/sv4d_example_video/lucia_v000.mp4 b/assets/sv4d_example_video/lucia_v000.mp4
diff --git a/assets/sv4d_example_video/monkey.mp4 b/assets/sv4d_example_video/monkey.mp4
diff --git a/assets/sv4d_example_video/pistol_v0.mp4 b/assets/sv4d_example_video/pistol_v0.mp4
diff --git a/assets/sv4d_example_video/snowboard_v000.mp4 b/assets/sv4d_example_video/snowboard_v000.mp4
diff --git a/assets/sv4d_example_video/stroller_v000.mp4 b/assets/sv4d_example_video/stroller_v000.mp4
diff --git a/assets/test_video1.mp4 → assets/sv4d_example_video/test_video1.mp4 b/assets/test_video1.mp4 → assets/sv4d_example_video/test_video1.mp4
diff --git a/assets/test_video2.mp4 → assets/sv4d_example_video/test_video2.mp4 b/assets/test_video2.mp4 → assets/sv4d_example_video/test_video2.mp4
diff --git a/assets/sv4d_example_video/train_v0.mp4 b/assets/sv4d_example_video/train_v0.mp4
diff --git a/assets/sv4d_example_video/wave_hello.mp4 b/assets/sv4d_example_video/wave_hello.mp4