Impermanence_Anime_Girl F.1

Introduction to the selected LORA model: This model is based on the training of the F.1-dev-fp8 base model and is suitable for a certain style.

Recommendation: Highly recommend using the Flux-generated workflow to create images with 3 computational powers. What are you waiting for?

Workflow link: https://www.liblib.art/modelinfo/9c81aa8555d2425490f7ecdf028f9abd?from=personal_page

Generation suggestion: F.1 basic algorithm model - runnable on LiBu online,

Sampling method: Euler

LORA weight: Recommended 0.8-1.0

Recommended size: This model is trained on a dataset of 1024*1536 training images.

Iterations: 15-30, in practice, 10 steps can also produce good images

Prompt word correlation coefficient: 3.5.

High-definition restoration: R-ESRGAN_4x+ Anime6B

Creative overview: Try training a LORA using the newly launched FLUX-trained model. Recommended to use the F.1 model of Flux in the workflow, which can save a lot of computational power.

Trigger word: anime girl