Type | |
Stats | 793 68 |
Reviews | (65) |
Published | Aug 11, 2024 |
Base Model | |
Training | Steps: 1,500 |
Trigger Words | none |
Hash | AutoV2 1FE67ABAC8 |
This lora was trained on Pop art painting styles, to bring more vibrant colors and a painterly effect. It also does some nice vector style black lines.
Because flux is so new, this is a beta lora. I have noticed that t5 text encoder messes with it a bit. If prompted for realism, it fights the lora style and burns out the image. Looking into the cause of this, but in the meantime; no trigger word is necessary. I would just prompt for the style and steer clear of realism.
Make sure to use "Lora Loader Model Only" and use with Flux "Dev" model.
I find depending on the prompt it starts working at 0.8 and cooks at 3/3.5
If you find out any better info on this- feel free to reach out!
Big shoutout to Ostris for his awesome work with this training script!
-Syntax