the best open source ai models

Height Slider for Krea 2: age-safe height changes

Topic: Models

By Captain

Published 2026-10-03

Loraholic's Height Slider changes a subject's height in Krea 2 without altering age. Learn the -4 to 3 range, the note about women at high values and ideas for character line-ups.

Overview

The

(

v1) is an age-safe slider

: it makes subjects taller or shorter without pushing them younger or older. On Krea 2 the author recommends -4.0 to 3.0; the

version runs -10 to 10. At values above 2.5, women can start to look more masculine.

Full-body framing is where it shows; the author's prompting guide covers getting the right perspective.

Reference

Name	Type	What it is
LoRA weight	-4 to 3	±2 noticeable.
Trigger	none
Framing	full body	Include a reference object or doorway.
Steps / guidance	8 / 1
Combination	Weight / Age sliders	Stacks.

AD

No install required - run AI models on the cloud

BitVector Prism is the easiest way to start: pick a model, type a prompt and generate in a clean web app, with nothing to configure. BitVector is also available on Discord and on the web (SpyGlass).

Step by step

Full-body prompt with a height reference (a doorway, a friend).
Generate, keep seed.
Slider at +2 for taller, -2 for shorter.
Watch facial masculinity on women above 2.5.
Combine with the Weight slider for a complete build.

Examples

Line-up

A full-body cinematic photograph of a 28-year-old man standing centered in a doorway, calm neutral posture, eye level.

Height Slider -2, 0, +2

Low angle

A low-angle full-body portrait of a woman in a long coat on marble steps, looking up at her.

Height Slider +1.5

Creative idea: fantasy races

Same seed: a traveler in a cloak beside a signpost; -4 for a halfling, +3 for a tall elf.

Tips

Low camera angles exaggerate the effect; eye level shows it honestly.
Use a doorway or counter for scale.
Great for character line-ups in design work.
Keep clothing described so proportions read.

Troubleshooting

Women look masculine

Why it happens

Above 2.5.

How to fix it

Stay at or below 2.5.

No effect

Why it happens

Close framing.

How to fix it

Full body with a reference object.

AD

No install required - run AI models on the cloud

PirateDiffusion is Telegram only and built for pros: thousands of models, LoRAs and workflows driven by chat commands, with unlimited generation on a fixed price plan.

Try PirateDiffusion

Questions

Z-Image version?

Yes, -10 to 10.

Trigger?

None.

Links and sources

Civitai page

Models in this guide

Written by

Captain

Related guides

Aesthetic Amateur Photo Krea V4: everyday phone-photo realism

powerpuff's Aesthetic Amateur Photo LoRA makes Krea 2 images feel like real smartphone and social-media photos: sharper details, brighter colors, casual framing. Learn weight, prompts and ideas.

Krea 2 Weight Slider v2 by alcaitiff: a compact body-weight control

alcaitiff's Weight Slider for Krea 2 adjusts body weight with a simple -3 to 3 range where 2 is usually enough. Learn how it compares with the Loraholic slider and ideas for using it.

Canon UltraReal for Krea 2: the color and bokeh of an old full-frame flagship

Danrisi's Canon UltraReal LoRA reproduces the rich colors, rendering and bokeh of photographs taken with a Canon 1Ds on 28-500mm lenses. Learn the c2n0n trigger, weight and why detailed prompts matter.

Caucasian / Asian ethnicity slider for Krea 2: use the lowest value that works

Loraholic's ethnicity slider shifts facial features between Caucasian and East Asian appearance in Krea 2. Learn the -5 to 4 range, why low values are recommended and how to use it responsibly for character design.

More guides

FLUX.1 Dev: how to prompt it, best settings and creative ideas

A practical guide to FLUX.1 Dev by Black Forest Labs: natural-language prompting, guidance and step settings, LoRA stacking, text rendering and prompt ideas that play to its strengths.

Stable Diffusion XL 1.0: prompts, settings and what it still does best

How to get the most out of the official SDXL 1.0 base model: native resolutions, CFG and sampler settings, the refiner, negative prompts and ideas for styles where SDXL still shines.

Stable Diffusion 1.5: the classic model, prompted properly

Stable Diffusion 1.5 is still worth knowing: the right resolution, CFG and sampler, how to use its huge library of LoRAs and embeddings, and creative prompt ideas suited to a 512-pixel model.

FLUX.2 Dev: prompting the newest Black Forest Labs model

FLUX.2 Dev brings larger prompts, better text, stronger realism and multi-reference editing. This guide covers the turbo workflow, guidance and resolution settings, prompt structure and ideas that use its new strengths.

Qwen-Image: long prompts, perfect text and bilingual posters

Qwen-Image is the model to reach for when the words in the picture matter. Learn how to write its long descriptive prompts, render English and Chinese text accurately, set CFG and steps, and explore layout-heavy creative ideas.

SDXL-Lightning: four-step generation on any SDXL checkpoint

ByteDance's SDXL-Lightning LoRA turns a 30-step SDXL render into a 4-step one. Learn the step counts, the CFG you must use, the sampler, and how to combine it with your favorite checkpoints and style LoRAs.

© ModelTrends.ai

|

Made in Japan

|

© 2026