metadata
license: other
license_name: stability-ai-community-license-agreement
license_link: https://huggingface.co/stabilityai/sd-turbo/blob/main/LICENSE.md
language:
- en
tags:
- gguf
- sd.cpp
- stable-diffusion.cpp
- sd2
base_model:
- stabilityai/sd-turbo
quantized_by: Green-Sky
I use sd_turbo to test sd2 for sd.cpp , so here they are.
The "old" q8_0 is a direct conversion, converting to f16 first, then to q8_0 gave an equivalent performing but smaller filesize model file.
Use --cfg-scale 1 --steps 8 and maybe --schedule karras.
The model only really produces ok output for 512x512 .