• Auto1111 extension implements ModelScope text2video using only its webui dependencies and downloadable models.
  • The extension works with GPUs having at least 8GB VRAM and supports video resolutions up to 256x256.

Key terms:

  • ModelScope text2video: An implementation that converts text to video using Auto1111 webui dependencies.
  • StableDiffusion WebUI: The web user interface for Auto1111's StableDiffusion.
  • Downloadable models: Models that can be downloaded and used without requiring logins.
  • 8GB VRAM: Minimum video memory required to run the extension on GPU.
  • 256x256 resolution: Maximum video resolution supported by the extension.


Open Source Tools GitHub NVIDIA StableDiffusion WebUI Auto1111 Video Resolution Extension Downloadable Models