SDXL pony kurzgesagt style: v1.0: kurzgesagt_v1.safetensors

Metadata contains training config

A Kurzgesagt style LoRA trained on BlipMix2 (a pony based model mix)

The training data are images captioned by wd and florence, with minimal manual input. Overall, a quick and dirty LoRA with surprisingly good results!
---
I will post all my stuff for free, including other LoRAs/checkpoints and coding tools like useful scripts/webapps, such as a blind rating elo ranker for LoRAs. You can find them here.

If you'd like to support me, every little bit helps! As I said I will post everything freely, but living do be costing money. Feel free to buy me a coffee, even a dollar helps ;)