Impermanence_Anime beauty veil F.1

Introduction to the selected LORA model: This model is based on the F.1-dev-fp8 base model training and features a style of anime beauty with a veil.

Recommendation: Highly recommend using Flux document generation workflow to create with just 3 units of computing power per image. What are you waiting for?

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

Generation suggestions: LORB basic algorithm model can be run online on LiBu platform,

Sampling method: Euler

LORA weight: Recommended 0.8-1.0

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

Iterations: 15-30, but even 10 steps can produce good results according to experiments.

Prompt word correlation coefficient: 3.5.

HD restoration: R-ESRGAN_4x + Anime6B

Creative overview: Try using the newly launched FLUX-trained LORA model to train an anime beauty veiled style LORA, unexpected surprises of anime characters under the FLUX large model? Recommend using the F.1 model of document generation to save a significant amount of computing power.

Trigger words: veil, mouth veil,