|
5 | 5 | ## News |
6 | 6 |
|
7 | 7 | **March 18, 2024** |
8 | | -- We are releasing [SV3D](https://huggingface.co/stabilityai/sv3d), an image-to-video model for novel multi-view synthesis, for research purposes: |
9 | | - - SV3D was trained to generate 21 frames at resolution 576x576, given 1 context frame of the same size, ideally a white-background image with one object. |
10 | | - - SV3D_u: This variant generates orbital videos based on single image inputs without camera conditioning.. |
11 | | - - SV3D_p: Extending the capability of SVD3_u, this variant accommodates both single images and orbital views allowing for the creation of 3D video along specified camera paths. |
| 8 | +- We are releasing **[SV3D](https://huggingface.co/stabilityai/sv3d)**, an image-to-video model for novel multi-view synthesis, for research purposes: |
| 9 | + - **SV3D** was trained to generate 21 frames at resolution 576x576, given 1 context frame of the same size, ideally a white-background image with one object. |
| 10 | + - **SV3D_u**: This variant generates orbital videos based on single image inputs without camera conditioning.. |
| 11 | + - **SV3D_p**: Extending the capability of **SVD3_u**, this variant accommodates both single images and orbital views allowing for the creation of 3D video along specified camera paths. |
12 | 12 | - We extend the streamlit demo `scripts/demo/video_sampling.py` and the standalone python script `scripts/sampling/simple_video_sample.py` for inference of both models. |
13 | 13 | - Please check our [project page](https://sv3d.github.io), [tech report](https://sv3d.github.io/static/paper.pdf) and [video summary](https://youtu.be/Zqw4-1LcfWg) for more details. |
14 | 14 |
|
15 | | -To run SV3D_u on a single image: |
| 15 | +To run **SV3D_u** on a single image: |
16 | 16 | - Download `sv3d_u.safetensors` from https://huggingface.co/stabilityai/sv3d to `checkpoints/sv3d_u.safetensors` |
17 | 17 | - Run `python scripts/sampling/simple_video_sample.py --input_path <path/to/image.png> --version sv3d_u` |
18 | 18 |
|
19 | | -To run SV3D_u on a single image: |
| 19 | +To run **SV3D_p** on a single image: |
20 | 20 | - Download `sv3d_p.safetensors` from https://huggingface.co/stabilityai/sv3d to `checkpoints/sv3d_p.safetensors` |
21 | | -1. Generate static orbit at a specified elevation eg. 10 : `python scripts/sampling/simple_video_sample.py --input_path <path/to/image.png> --version sv3d_p --elevations_deg 10.0` |
| 21 | +1. Generate static orbit at a specified elevation eg. 10.0 : `python scripts/sampling/simple_video_sample.py --input_path <path/to/image.png> --version sv3d_p --elevations_deg 10.0` |
22 | 22 | 2. Generate dynamic orbit at a specified elevations and azimuths: specify sequences of 21 elevations (in degrees) to `elevations_deg` ([-90, 90]), and 21 azimuths (in degrees) to `azimuths_deg` [0, 360] in sorted order from 0 to 360. For example: `python scripts/sampling/simple_video_sample.py --input_path <path/to/image.png> --version sv3d_p --elevations_deg [<list of 21 elevations in degrees>] --azimuths_deg [<list of 21 azimuths in degrees>]` |
23 | 23 |
|
24 | 24 | To run SVD or SV3D on a streamlit server: |
|
0 commit comments