Impermanence_Impermanence_Fantasy Style-Yarn F.1

Introduction to the selected LORA model: This model is trained based on the F.1-dev-fp8 base model, with a whimsical wool style often seen in anime fantasies.

Recommendation: Highly recommend using the Flux-based image generation workflow, where 3 GPUs can create one image. What are you waiting for?

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

Generation suggestions: F.1 basic algorithm model can be run online at Lbu,

Sampling method: Euler

LORA weight: Recommended 0.8-1.0

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

Iteration steps: 15-30, but it's been tested that even 10 steps can produce good results

Relevance coefficient for prompts: 3.5

HD restoration: R-ESRGAN_4x + Anime6B

Creative overview: Try using the newly introduced FLUX-trained LORA model to create a wool-inspired whimsical anime style. What surprises might the anime characters hold under the FLUX large model? It is recommended to use the F.1 model of the workflow to save a significant amount of computational power.

Trigger word: wool