Impermanence_Qinghua porcelain style National Day poster F.1

Introduction to the selected LORA model: This model is trained based on the F.1-dev-fp8 base model, in a blue and white porcelain style.

Recommendation: Highly recommend using the Flux document-based graphic workflow generation, 3 computing power for one image, what are you waiting for?

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

Generation suggestion: F.1 basic algorithm model - Li Bu online runnable,

Sampling method: Euler

LORA weight: Recommended 0.8-1.0

Recommended size: This model is trained on a 1024*1024 training image set.

Iterations: 15-30, it has been tested that even 10 steps can produce good images

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 a blue and white porcelain style lora, what would a National Day style poster with a fusion of blue, white, red, and gold colors look like? Recommended to use the F.1 model of the document-based graph in the workflow, which can save a lot of computing power.

Trigger words: blue and white porcelain,