NarratoAI Modpack v0.1.2 is released 🚀

Hurry up and follow the WeChat public account [NarratoAI助手] and reply to the keyword [整合包] to get the latest download link! Give it a try!

Note:

• Currently only available for Windows, Mac version is in development, Linux version will be available in a future release.

• Windows Integration Pack Release
• Optimized the story generation process and improved the generation effect
• Support local large model MiniCPM-V
• Support local large model Qwen2-VL
• ...

• Recommended minimum: CPU with 4 cores or more, 8GB RAM or more, GPU is not required
• Windows 10 or MacOS 11.0 or above

1. Visit https://aistudio.google.com/app/prompts/new_chat to apply for an account.
2. Click Get API Key to request an API Key.
3. Enter the obtained API Key into the gemini_api_key setting in the config.example.toml file.

The method to configure VPN is not restricted, as long as you can access Google's network. Here, clash is used as an example.

1. Note the port of the clash service, usually https://127.0.0.1:7890.

2. If the port is not 7890, modify the VPN_PROXY_URL in the docker-compose.yml file to your proxy address.

   environment:
     - "VPN_PROXY_URL=https://host.docker.internal:7890" # Change to your proxy port; host.docker.internal represents the IP of the physical machine.

3. (Optional) Or modify the proxy settings in the config.example.toml file.

   [proxy]
    ### Use a proxy to access the Pexels API
    ### Format: "https://<username>:<password>@<proxy>:<port>"
    ### Example: "https://user:pass@proxy:1234"
    ### Doc: https://requests.readthedocs.io/en/latest/user/advanced/#proxies
   
    http = "https://xx.xx.xx.xx:7890"
    https = "https://xx.xx.xx.xx:7890"

git clone https://github.com/linyqh/NarratoAI.git
cd NarratoAI
docker-compose up

Open your browser and go to https://127.0.0.1:8501

Open your browser and go to https://127.0.0.1:8080/docs or https://127.0.0.1:8080/redoc

Currently, only the Gemini model is supported. Other modes will be added in future updates. Contributions are welcome via PR to join in the development 🎉🎉🎉

A demo video is included in the platform. To use your own video, place the mp4 file in the resource/videos directory and refresh your browser. Note: The filename can be anything, but it must not contain Chinese characters, special characters, spaces, backslashes, etc.

After saving the script, refresh the browser, and the newly generated .json script file will appear in the script file dropdown. Select the json file and video to start editing.

1. Install Dependencies

conda create -n narratoai python=3.10
conda activate narratoai
cd narratoai
pip install -r requirements.txt

2. Install ImageMagick

• Download https://imagemagick.org/archive/binaries/ImageMagick-7.1.1-36-Q16-x64-static.exe
• Install the downloaded ImageMagick, ensuring you do not change the installation path
• Update imagemagick_path in the config.toml file to your actual installation path (typically C:\Program Files\ImageMagick-7.1.1-Q16\magick.exe)

brew install imagemagick

sudo apt-get install imagemagick

sudo yum install ImageMagick

3. initiate webui

streamlit run ./webui/Main.py --browser.serverAddress=127.0.0.1 --server.enableCORS=True --browser.gatherUsageStats=False

4. Access https://127.0.0.1:8501

• https://github.com/FujiwaraChoki/MoneyPrinter
• https://github.com/harry0703/MoneyPrinterTurbo

This project was refactored based on the above projects with the addition of video narration features. Thanks to the original authors for their open-source spirit 🥳🥳🥳

Click to view the LICENSE file