An attempt to recreate the style of cartoonish model.
A proof of concept for Z-Image-Turbo Lora training.
Training Set: 20 SD1.5 generated images.
Training Steps: 5000 (v0.2), 3000 (v0.1 full), 1500 (v0.1 lite).
Recommended strength: 0.7 ~ 0.9 (v0.2), 0.75 ~ 1.0 (v0.1).
No trigger words needed.
Description
Retrained from the de-distilled model.