Allows users to create video2video and text2video animations using any SD models as a backbone. Please, make sure that 'sd-webui-controlnet' extension is also installed.

Go to file

Alexey Borsky 68bd68d1dc Update readme.md		2023-04-08 08:45:09 +03:00
LICENSE	Initial commit	2023-03-17 16:35:22 +03:00
readme.md	Update readme.md	2023-04-08 08:45:09 +03:00
script.py	Improved version	2023-04-05 08:17:42 +03:00

readme.md

SD-CN-Animation Script

This script allows you to automate video stylization task using StableDiffusion and ControlNet. It uses a simple optical flow estimation algorithm to keep the animation stable and create an inpating mask that is used to generate the next frame. Here is an example of a video made with this script:

This script can also be using to swap the person in the video like in this example: https://youtube.com/shorts/be93_dIeZWU

Dependencies

To install all necessary dependencies run this command

pip install opencv-python opencv-contrib-python numpy tqdm

Running the script

This script works on top of Automatic1111/web-ui interface via API. To run this script you have to set it up first. You also should have sd-webui-controlnet extension installed. You need to have control_hed-fp16 model installed. If you have web-ui with ControlNet working correctly do the following:

Go to the web-ui settings -> ControlNet tab -> Set "Allow other script to control this extension" checkbox to active and set "Multi ControlNet: Max models amount (requires restart)" to more then 2 -> press "Apply settings"
Run web-ui with '--api' flag. It also better to use '--xformers' flag, as you would need to have the highest resolution possible and using xformers memory optimization will greatly help.
bash webui.sh --xformers --api
Go to the script.py file and change main parameters (INPUT_VIDEO, OUTPUT_VIDEO, PROMPT, N_PROMPT, W, H) to the ones you need for your project. The script is pretty simple so you may change other parameters as well, although I would recommend to leave them as is for the first time.
Run the script with python3 script.py

Potential improvements

There are several ways overall quality of animation may be improved:

You may use a separate processing for each camera position to get a more consistent style of the characters and less ghosting.
Because the quality of the video depends on how good optical flow was estimated it might be beneficial to use high frame rate video as a source, so it would be easier to guess the flow properly.
The quality of flow estimation might be greatly improved with proper flow estimation model like this one: https://github.com/autonomousvision/unimatch