This example provides a simple implementation of the use of StreamDiffusion to generate images from text. You can realtimely generate 4x4 images from text, on changing the input prompt.
pip install -r requirements.txt
cd view
npm i
npm run build
cd ../server
python main.py
The video and image demos in this GitHub repository were generated using kohakuV2 and SD-Turbo.
Special thanks to Kohaku BlueLeaf (@KBlueleaf) for providing the KohakuV2 model, and to Stability AI for SD-Turbo.
KohakuV2 Models can be downloaded from Civitai and Hugging Face.
SD-Turbo is also available on Hugging Face.