Sign In

Sue's Z-Body Bikini Beach by Freyja Pixel 💖

3

Updated: Dec 31, 2025

characteranimethighsblondewaterthick

Verified:

SafeTensor

Type

LoRA

Stats

162

3

35

Reviews

Published

Dec 26, 2025

Base Model

ZImageTurbo

Training

Steps: 480
Epochs: 2

Usage Tips

Strength: 0.5

Trigger Words

an anime illustration of an adult blonde caucasian woman at the beach at sunset, blue eyes, blushing, long flowing hair, very large breasts, wide hips, thick thighs, wet skin with visible water droplets, blue fingernail polish, blue toenail polish, wearing a white bikini, pink sky, sunset, ocean waves, beach, sue_pixel.

Training Images

Download

Hash

AutoV2
D9C3875CDE

Here's my custom Z-Image workflow for this LoRA: https://civitai.com/models/2253523?modelVersionId=2536797

💨 This LoRA is for Z-Image Turbo!

Cuties, I can confirm the new Sue Z-Body Bikini LoRA works for on-site generation! 👙✨

📸 768x1280 or "Portrait" is the recommended orientation and latent image size!

Cuties, it's close to the anniversary of when I first started seriously working with AI, so I wanted to make my first LoRA! ✺◟( ˃ᴗ˂ )◞✺ aww yiss!

💪 The LoRAs themselves work excellently between .4 - .6 weight, though I found my best results at between .48 - .52, favoring the later .52 if I'm running just one pass/single LoRA.

⚠️⚠️⚠️ KNOWN ISSUES:

These LoRAs were trained off of images that do not have good hands and feet! I was still learning when I genned the images, and the detailed hands and feet are few and far between! I did my best, but you will likely have to roll a few gens and seed combinations! You could also try prompting more, but I have not tried that!

😇 THIS LORA IS SFW. It does not include any nudity in it's training images!

👀👀👀 Detailed tagging and prompting guide, training images, training captions, and ComfyUI workflow included in the training data .zip!

I used Musubi Tuner to make a Z-Image LoRA using some of my first ever AI generations from early 2025! The 32 training images were made in January 2025 using Wai-Illustrious version 8 and Automatic1111, and the LoRA was made in December 2025! I used my customized Chat GPT 5.2 to write the base captions, and then I engineered and iterated upon them with Z-Image and the alpha-test LoRA to fine tune the training! I also increased the steps up to 480, and made 2 different versions using different VAE training! The AE version uses the base Z-Image ae.safetensor for the training, and the UltraFLUX uses a community modded vision version of the Flux VAE. I then created a customized workflow based on my observations during image testing!

GENERAL STYLE:

anime style illustration, adult blonde caucasian woman,

GENERAL POSE:

running, walking, walking forward, standing, squatting, kneeling,

GENERAL COMPOSITION:

from above, from behind, from front, from below, side profile,

GENERAL FACE:

blue eyes, long blonde hair, blush,

GENERAL BODY:

athletic build, very large breasts, thick thighs, wide hips, bare feet, soles, wet skin with visible water droplets,

GENERAL NAILS (RECCOMENDED):

blue fingernail polish, blue toenail polish

GENERAL BIKINI:

wearing a white bikini,

GENERAL BACKGROUND TAGS:

at the beach at sunset, beach, sunset, ocean waves, horizon, pink sky,

GENERAL ENDING TAGS:

dynamic lighting, dynamic motion, dynamic pose, high-detail, clean anatomy, sue_pixel.