Trigger words makes lora much stronger.
Recommended settings:
Sampler:
er_sde
euler
dpmpp_sde_gpu
Scheduler:
beta - for more drawn style
linear_quadratic - for more softened, 3d look
Sampling steps: 25-40
CFG: 4-5
Lora Strength: 1
SAIPACo Chibi - v1
Version Detail
Trained by Tensor
Anima
10
Project Permissions
Use in TENSORHUB ART Online
As a online training base model on TENSORHUB ART
Use without crediting me
Share merges of this model
Use different permissions on merges
Use Permissions
Sell generated contents
Use on generation services
Sell this model or merges