Update V3

Slightly different training on WAI-REAL_CN V6, but it also supports "femboy". I tested this on V7 and V8 of WAI-REAL_CN, which works great as well.

Adetailer usage with other Lora's

Copy paste the whole prompt in Adetailer when using face enhancement, and remove all Lora prompts that does or could do something with faces and keep this one.

================================================

Pony

Second try out. Works really well with WAI-REAL_CN V6, since I trained on this Checkpoint as base.

This version is trained with 21 images (no bucket) with (1, 1 repeats) just on Civitai with a max epochs of 102. After running many tests with S/R, I concluded that the 79th epoch is best. Further training varies from likeness.

The results are best at 768 x 1152 with Adetailer.

Recommended Setting

• Steps: 24-28

• CFG scale: 6.5-7

• Sampler: Euler a or DPM++ 2M Karras

• ADetailer face_yolov8n/s.pt

Improving Quality

Quality can be improved with Add More Details XL/Pony. Either set this to one or set this up in your network to prompt.

Works with other Lora's

I am a big fan of Ruanyi's work. Most of Ruanyi's models can be used with Ka-Chu.

If you like my work, don't hesitate to leave a like or a review. Please share your renders so I gain knowledge what other potentials this model can be used for.

Last but not least, I drink a lot of Ko-Fi :)