Morphs everything into DOODLES

The triggers are - ArsWorld, Doodle . It works without it , but the results are better with it.

Start turning everything into DOODLES in the 0.4 - 0.8 range .

Recommended use 0.8 - 1.2, depending on the model you use and Lora stack.

You can go pretty high with the strength. Around 1.5 the images start to distort a little bit.

The Lora is really strong so start low.

Making this Lora was real delight! Have fun making "serious art" with it!!!

描述:

The model produces nice effects in the 0.4 - 1.5 strength range.
Start ~1 and adjust according to what you want.
The LoRA mixes really well with others and add unique effect in the 0.4 - 1 range.

Above 1.5 strange distortions start to appear.

If you're using a low-end machine with 6/8 GB of VRAM, check out my guide:
https://civitai.com/articles/6846/running-flux-on-68-gb-vram-using-comfyui

All images in the Showcase Gallery were created using this workflow and the Flux Q4 Dev model on a machine with 8GB VRAM:
https://civitai.com/models/658639/super-simple-gguf-quantized-flux-lora-workflow

训练词语: ArsWorld, Doodle