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 .

GGUF

Model size

1.3B params

Architecture

undefined

8-bit

16-bit

Inference API

Unable to determine this model's library. Check the docs .

Model tree for Green-Sky/SD-Turbo-GGUF

Base model

Quantized

(3)

this model