Deploy Dedicated GPU server to run AI models

Deploy Model
Skip to main content
DreamShaperXL_Turbo_v2_1_fix5 thumbnail

DreamShaperXL Turbo V2 1 Fix5 API Documentation

by ModelsLab

Turbo version should be used at CFG scale 2 and with around 4-8 sampling steps. This should work only with DPM++ SDE Karras (NOT 2M). You can use this with LCM sampler, but don't do it unless you need speed vs quality.
Sampler comparison at 8 steps: https://civitai.com/posts/951781
UPDATE: Lightning version targets 3-6 sampling steps at CFG scale 2 and should also work only with DPM++ SDE Karras. Avoid going too far above 1024 in either direction for the 1st step.

dreamshaperxlturbov21fix5
Open Source ModelUnlimited UsageLLMs.txt
API PlaygroundAPI Documentation