Skip to content

Latest commit

 

History

History
17 lines (11 loc) · 567 Bytes

taesd.md

File metadata and controls

17 lines (11 loc) · 567 Bytes
Raw

Using TAESD to faster decoding

You can use TAESD to accelerate the decoding of latent images by following these steps:

Or curl

curl -L -O https://huggingface.co/madebyollin/taesd/blob/main/diffusion_pytorch_model.safetensors
  • Specify the model path using the --taesd PATH parameter. example:
sd -m ../models/v1-5-pruned-emaonly.safetensors -p "a lovely cat" --taesd ../models/diffusion_pytorch_model.safetensors