v2Enabled by prompts such as anime, manga, etc.It seems that some thought needs to be given to the prompts in order to generate high quality images with Flux.The prompts used in the images posted on this page were generated using LLM based on the contents of the following URL.<a target="_blank" rel="ugc" href="https://huggingface.co/datasets/k-mktr/improved-flux-prompts-photoreal-portrait">https://huggingface.co/datasets/k-mktr/improved-flux-prompts-photoreal-portrait</a><hr />416 x 608, 30 images.No caption.sd-scripts : fine tuningoptimizer : adafactorscheduler : constantLR : 2e-6batch size : 30epochs : 400repeats : 1I initially trained on a datasets of 74 images as well, but failed due to anomalies in the appearance of the hands.I then reduced the number of images to 30 and the quality improved.The cause is unknown.<hr />v1Test VersionEnabled by prompts such as anime, manga, etc.

【Style】 Koi - FLUX

FLUX_Style7646888135_Dim16.safetensors

LORA Dim16

v2 LORA Dim16

v2 Unet

LORA Dim8

Unet

<div>Test VersionEnabled by prompts such as anime, manga, etc.

Files with SHA256: 0f408ce9e18b960df9a35881658964fad229349410f4a1433d6e2aa9491e715c