Illustrious :

Training : 99 images with a 1024 resolution. The lines are messy, I plan on remaking the dataset in higher quality.

FLUX:

sampler/scheduler : euler / betastep : 20cfg : 3.5guidance : 3.5 ( raising to 5 might give better hands)
All preview images include the comfyui workflow and prompt.
Training : 64 images, captions are included in the training data (not the images) and were a mix of chatgpt4 + joytagAuto learning rate : 1e-05 with a minimum of 1e-06Unet learning rate : 1e-04

PONY:

/!\ WARNING /!\The dataset used did not contain any nsfw data, to get the effect of the lora on nsfw prompt you will need to UP the weight.
Use original PonyDiffusionV6XL for maximum effect for Pony version.
Suggested settings (PONY only) :
WEIGHT:0.8 to 1.3
GEN:
25-35steps5-7cfgEuler A
Highfix res:
20 steps5-7 cfgEuler A0.5 denoise
+facedetailer recommended

Trigger :

style 240_mado

This first version lacks a bit in term of diversity, I will eventually revisit this lora to add to the original dataset to get more diversity.

This style comes from these 2 videos that I love :