stable-diffusion.cpp/docs/taesd.md at master · thxCode/stable-diffusion.cpp

stable-diffusion.cpp/docs/taesd.md at master · thxCode/stable-diffusion.cpp

Skip to content

Latest commit

Using TAESD to faster decoding

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

Download the model weights.

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