Тип
LORA
Время публикации
2024-09-14
Базовая модель
Flux.1 D
Слово-триггер
mad_clrfltrngls
Копировать
Версия введения.
The LoRA was trained on Flux-Dev.
It also works with Flux-Schnell, but I behaves differently.
The showcase images are made with Flux-Dev.
For Flux Dev I recommend the following setting - Lora strength 0.8-1.0, highres fix with denoising 0.3-0.5
For some reason the prompt got lost for the example images, they are the same for all Loras from the colorful series, so please check the images from the other loras
