Spaces:
Runtime error
Runtime error
jhj0517
commited on
Commit
·
404fd96
1
Parent(s):
f9d29dd
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,7 @@
|
|
| 1 |
# sam2-playground
|
| 2 |
Gradio based Playground Web UI using [facebook/segment-anything-2](https://github.com/facebookresearch/segment-anything-2) models.
|
| 3 |
|
| 4 |
-
|
| 5 |
-
[image]
|
| 6 |
-
|
| 7 |
-
## Notebook
|
| 8 |
<div>
|
| 9 |
<a href="https://colab.research.google.com/github/jhj0517/sam2-playground/blob/master/notebooks/sam2_playground.ipynb">
|
| 10 |
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab" style="display:inline-block;">
|
|
@@ -12,15 +9,55 @@ Gradio based Playground Web UI using [facebook/segment-anything-2](https://githu
|
|
| 12 |
</div>
|
| 13 |
|
| 14 |
## Feature
|
| 15 |
-
- Add
|
| 16 |
-
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
# Installation and Running
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
-
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
-
|
| 24 |
|
| 25 |
|
| 26 |
## Todo
|
|
|
|
|
|
| 1 |
# sam2-playground
|
| 2 |
Gradio based Playground Web UI using [facebook/segment-anything-2](https://github.com/facebookresearch/segment-anything-2) models.
|
| 3 |
|
| 4 |
+
## Online Demos
|
|
|
|
|
|
|
|
|
|
| 5 |
<div>
|
| 6 |
<a href="https://colab.research.google.com/github/jhj0517/sam2-playground/blob/master/notebooks/sam2_playground.ipynb">
|
| 7 |
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Colab" style="display:inline-block;">
|
|
|
|
| 9 |
</div>
|
| 10 |
|
| 11 |
## Feature
|
| 12 |
+
- Add filters to segment parts of a video with pixelated or solid color
|
| 13 |
+
|
| 14 |
+
<table>
|
| 15 |
+
<tr>
|
| 16 |
+
<td>Pixelize the girl's face</td>
|
| 17 |
+
</tr>
|
| 18 |
+
<tr>
|
| 19 |
+
<td>
|
| 20 |
+
<video controls autoplay loop src="https://github.com/user-attachments/assets/c5758970-dc15-4bc8-a918-8d3e8e44a73a" muted="false"></video>
|
| 21 |
+
</td>
|
| 22 |
+
</tr>
|
| 23 |
+
</table>
|
| 24 |
+
|
| 25 |
+
- Divide segmentation parts into layers and save them as PSD files.
|
| 26 |
+
|
| 27 |
+
<table>
|
| 28 |
+
<tr>
|
| 29 |
+
<td>Divide clothes into layers and save as PSD file</td>
|
| 30 |
+
</tr>
|
| 31 |
+
<tr>
|
| 32 |
+
<td>
|
| 33 |
+
<img src="https://github.com/jhj0517/sam2-playground/blob/master/docs/example_psd_file.png" alt="Example_PSD">
|
| 34 |
+
</td>
|
| 35 |
+
</tr>
|
| 36 |
+
</table>
|
| 37 |
+
|
| 38 |
+
See PROMPT_GUIDE.md to see how to prompt the segmentation parts of the image.
|
| 39 |
|
| 40 |
# Installation and Running
|
| 41 |
+
### Prerequisites
|
| 42 |
+
To run this Web UI, you need these prerequisites. If you don't have them, please install them in the following links :
|
| 43 |
+
|
| 44 |
+
- `git` : https://git-scm.com/downloads
|
| 45 |
+
- `python => 3.10` : https://www.python.org/downloads/
|
| 46 |
+
- `FFmpeg` : https://ffmpeg.org/download.html
|
| 47 |
+
|
| 48 |
+
After installing FFmpeg, **make sure to add the `FFmpeg/bin` folder to your system PATH!** <br>
|
| 49 |
+
And for CUDA, if you're not using an Nvidia GPU and CUDA 12.4, edit the [requirements.txt](https://github.com/jhj0517/sam2-playground/blob/master/requirements.txt) to match your environment.
|
| 50 |
+
|
| 51 |
+
### Running with Shell / Batch Scripts
|
| 52 |
+
There's a set of shell / batch scripts for installation and running.
|
| 53 |
|
| 54 |
+
1. Download `sam2-playground.zip` with the file corresponding to your OS from [sam2-playground-portable.zip]() and extract its contents.
|
| 55 |
+
2. Run `install.bat` or `install.sh` to install dependencies. (This will create a `venv` directory and install dependencies there.)
|
| 56 |
+
3. Start WebUI with `start-webui.bat` or `start-webui.sh`
|
| 57 |
+
4. To update the WebUI, run `update.bat` or `update.sh`
|
| 58 |
|
| 59 |
+
### Docker
|
| 60 |
|
| 61 |
|
| 62 |
## Todo
|
| 63 |
+
- [ ] Support `change()` API for `gradio_image_prompter` and automatically generate preview for video predictor
|