This example is mainly adopted from StreamDiffusion txt2img. Although StreamV2V is designed for the vid2vid task, it could seamlessly integrate with the txt2img application. Compared with per-image StreamDiffusion, StreamV2V continuously generates images from texts, providing a smooth transition. The default model is one-step SD-Turbo.
Tested with VSCode with remote GPU server. The Live Server extension would help to open the local Chorme page.
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.1/install.sh | bash
# Restart terminal
nvm install 18You need Node.js 18+ and Python 3.10 to run this example. Please make sure you've installed all dependencies according to the installation instructions.
pip install -r requirements.txt
cd frontend
npm i
npm run build
cd ..
python main.pythen open http://0.0.0.0:7861 in your browser. (*If http://0.0.0.0:7861 does not work well, try http://localhost:7861)