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 .
- Downloads last month
- 100
Hardware compatibility
Log In
to view the estimation
8-bit
16-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Green-Sky/SD-Turbo-GGUF
Base model
stabilityai/sd-turbo