I wanted to create images in FLUX of women with innocent yet strong eyes—eyes that are captivating and pure—so I developed this LoRA. Most of the training was based on images of Japanese women. As a result, it may not fully align with other ethnological interpretations or aesthetics, but I hope this delicate charm can be reflected in FLUX, even just a little.
For this training, I used only one trigger word: 'midjourney_whisper_innocent_eyes'. While I aim to make this more apparent in the character’s eyes during image generation, I’m also curious to experiment and see how it influences the results.
【Attention】
Reposting this LoRA on other image generation services without prior written consent is strictly prohibited and may result in legal action. This LoRA is protected by copyright law, and unauthorized use may lead to legal consequences.
Description
FAQ
Comments (4)
Produces images of quite stunning beauty. In terms of aesthetics this seems to work best on its own, but I've been playing with mixing it with other LoRAs and it still seems to maintain the overall look
Just curious how to use clip skip 2 with Flux in Comfyui. I get a float error if I try to do this.
just fyi, i didn't use trigger word in any of my images. only adjusted lora weight. one of my favorite flux loras.
just so you know, i love this lora. created hundreds of images with it. now that hunyuan video has an image to video model, i'll be putting life into some of the images. i'll tag your lora so they show up here.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.