A South Indian woman in her thirties, built as a character, not a look-alike. Fictional: she does not exist and no real person's images were used. Trained for continuous storytelling — the same face at every framing, in sarees and at home, in Kerala light.
There is no other standalone South Indian character LoRA on this site. That is why she was made.
USE
Trigger: zxrevathi. Always add her age — the model reads it:
zxrevathi woman, 33 years old, <framing>, <expression>, <hair>, <outfit>, <light>, <place>
• Base: Krea 2 Turbo (trained on Krea 2 Raw, run on Turbo — the usual Krea 2 recipe)
• LoRA strength: 1.0–1.2 (1.2 is the best measured; below 0.8 she fades)
• Steps / CFG: 8 steps, CFG 1, Euler / Simple
• Size: 1024x1344 or 768x1024 native; upscale after
• Rank 32 / alpha 32, 218 MB
Candid lines like "raw phone photo, … natural unpolished skin texture, slight grain" give the best skin. Editorial lines carry their own camera words.
MEASURED, NOT CLAIMED
Identity is scored with InsightFace (buffalo_l) against five held-out reference images that are NOT in the training set — a mean cosine of 1.0 would be the same face.
18-prompt eval on Krea 2 Turbo, 768x1024, 8 steps, CFG 1, strength 1.0:
• close-up 0.88
• head & shoulders 0.89
• waist-up 0.81
• selfie 0.86
• wet hair 0.86
• full body 0.72
• profile 0.68
• mean over the 16 trigger prompts: 0.796, with 16 of 16 above 0.60
Strength curve, same prompts: 0.6 → 0.667 · 0.8 → 0.743 · 1.0 → 0.790 · 1.2 → 0.805
80 new scenes, 1024x1344, one seed each, no cherry-picking: mean 0.779, 57 of 80 at or above 0.75.
TRAINING
93 images, single source. Krea 2 Raw, rank 32 / alpha 32, 2,000 steps. Identity 0.799 on the 18-prompt held-out eval (16/16 above 0.60). Run on Krea 2 Turbo: strength 1.0–1.2, 8 steps, CFG 1, 1024x1344.
KNOWN LIMITATIONS — READ THESE
HOW TO PROMPT HER
HOW TO PROMPT HER
Describe the scene, not her. Krea 2 is sensitive to descriptors: eye, face or body words change her proportions. Write the trigger, then clothes, pose, place, light, camera. Her face, dark brown eyes, skin, hair and nose stud come with the trigger; do not restate them.
Her build. On Krea 2 Turbo the trigger carries her figure. On other Krea 2 finetunes (Sick Ollie, CyberRealistic) v2.0 can render her slimmer, and her build can vary between scenes. Body words ("curvy figure, full bust, full hips") steady one shot but do not make her consistent; treat that as a defect of this version, not a setting. The next version is being built to carry her build in the trigger on every base, and its card will carry a measured consistency figure.
Water (v2.0). Trained with many wet scenes; water streaks can appear on plain backdrops. "dry skin, no water" helps for now. Fixed in the next version.
Makeup. She is built with little makeup, so lipstick words are weak at strength 1.0; use 0.8–0.9 for makeup looks.
Nose stud. Part of her, on purpose. "no nose stud" removes it about half the time.
Base. Trained on Krea 2 Raw, made for Krea 2 Turbo. Reviewer-tested on Sick Ollie INT8 (Forge Neo, Euler, 9 steps, CFG 1); results on finetunes will be stated here as numbers.
• She leaks without the trigger. A plain prompt like "a 33-year-old South Indian woman, …" still renders her (0.80–0.84 against the references). If you want a different woman in the same scene, don't load this LoRA, or drop it to 0.6.
• The trigger word can print as text. Krea 2 renders unusual tokens onto signs, newspapers and blackboards. Avoid prompts with readable print, or expect zxrevathi written on them.
• Wide shots (v1): v1 rendered her fuller than her reference in full-body and wet-saree scenes; v2 holds her build. On v1 say "her natural figure".
• True side profiles are the weak slot (0.68). She often turns it into a three-quarter or over-the-shoulder view.
• Her face is designed to read 33. Prompting her much younger fights the model.
LICENCE AND CREDIT
This is a Derivative of Krea 2. NOTICE.txt and the Krea 2 Community License Agreement ship inside the download and travel with any copy — including its Acceptable Use Policy, content-filtering duty and revenue threshold. Not an official Krea product; not endorsed by Krea.
Adults only. She is written as a 33-year-old woman. Do not use her to depict, imply or impersonate a real person.
Made for dearai.live, where she lives as a character. Credit appreciated if you post her work.
Description
v2.0 body-aware
What changed: v1 knew her face and not her body — the captions named the scene, never the midriff, the waist, the thighs or the neckline, so wide and wet shots fell back to the base model's heavier prior. v2 was trained on 125 pictures (one source, fictional) with every visible body detail captioned in one fixed vocabulary, plus the pose. Same recipe otherwise (Krea 2 Raw, rank 32/32, 2,500 steps, text encoder untrained), served on Krea 2 Turbo.
Measured on the same 18-prompt evaluation, against five reference pictures verified by hash to be outside the training data:
- mean over the 16 trigger prompts: **0.793**, 16/16 above 0.60 (v1.0 re-measured on the same references: 0.796) — identity unchanged
- per framing: close-up 0.86, waist-up 0.8, head & shoulders 0.86, full body 0.71, wet hair 0.86, newspaper 0.72, profile 0.7, selfie 0.85
- without the trigger she still leaks: 0.86 / 0.82
- 30 new scenes at 1152x1440, one seed each: mean 0.826, 28 of 30 above 0.75
What you will see: her body now holds its reference build in wide, wet and reclining scenes where v1 drifted heavier, and the words work — "bare midriff, navel visible", "full thighs", "bare upper back", "deep neckline" render as written. Use "photograph" in prompts, not "photorealistic" (Krea 2 was trained on a lot of artwork; the word pulls texture toward painting).
Settings unchanged: strength 1.0, 8 steps, CFG 1, Euler/Simple, 1024x1344 or 1152x1440. Trigger `zxrevathi` + "33 years old". File sha256 1ac1aefa3afb7534…FAQ
Comments (6)
Hi & Thanks for sharing the model!
Just started to run some photoshooting setups. What i don't get, both your LORA women lose much of their body weight when i render them in the Sick Ollie INT8 checkpoint. So they still look voluptuous, but nowhere near as thick as in your images. I'd have to add the Loraholic Skinny/Fat Slider LORA with at least +3 strength to get a comparable result.
Your prompts don't mention the body, though.
Update: They both also show completely different bodies, depending on what framing and pose is used. Like one shot is a healthy mommy, other shot is more of a bikini babe with a too-thin waist.
Additionally, there's some artifacts baked into the LORA data. For Revathi, it is water (there's often water dripping, also in some of your pics) and this can be seen very well if you make some clean white cyclorama backgrounds.
Both also don't like taking makeup (e.g. the lips don't accept lipstick much). The nose rings seem to be baked in too, though you can sometimes override them with a different one.
Thanks — this is exactly the kind of feedback I wanted, and you're right on every point.
1. Body: on Krea 2 Turbo the trigger carries her build; on Sick Ollie and other finetunes add "curvy figure, full bust, full hips, soft midriff, soft waist" and she comes back without a slider. Going on the card today.
2. Bodies changing with framing: known, and the next version tightens it — I measure the face, and from now on the body too.
3. Water: you found a real bias in v2.0's data; too many wet scenes. "dry skin, no water" helps for now; fixed in the next version. Your cyclorama test is now part of my checks.
4. Makeup: she's built with little makeup, so lipstick words are weak at 1.0; try 0.8–0.9 for makeup looks.
5. Nose stud: on purpose, it's her signature. "no nose stud" removes it about half the time.
Which Sick Ollie build and settings are you running? I'd like to test the next version on it before release.
@dearai_studio Just the regular Sick Ollie, Krea 2, INT8 checkpoint with the regular FP8 text encoder (not one of the dedicated decensored ones, for general purpose). I think there's only one VAE. Software is Forge NEO.
Thing about the added keywords like "curvy figure" to get the character look right: they are completely subjective and relative / ambiguous, so the engine renders the characters differently in each scene.
It's very very apparent here; even with / without the fat sliders, the apparent body mass changes by like 20 kilograms and more between shots. This is also why i generally don't download LORA characters which require extra keywords (not beyond e.g. "dark skin" or something about the hair) - they are never consistent.
Krea2 is still super-sensitive to these extra descriptions. Prompt "blue eyes" on any character, and the eyes become bigger in relation to the face.
@LurkingAI Thanks, that's useful. Forge Neo with the INT8 checkpoint and the standard FP8 text encoder is what I'll test on before the next release.
On keywords: agreed. Her build belongs in the trigger, not in the prompt. On Turbo that's where it is; on finetunes v2.0 leans on the words, and that's a defect, so I've pulled the "add curvy figure" advice from the card. The next version is being built to carry her build on every base without descriptors, and its card will show a consistency figure: her proportions across 12 scenes on the same seed, on Turbo and on Sick Ollie, not just a face score.
The "blue eyes" point goes on the card as you wrote it: describe the scene, not her.
@dearai_studio blue eyes was just a random example - wouldn't want your two models here with blue eyes ;)
Some models actually shift between blue, green, hazel, then it's hard to fix it without impacting the face.
@LurkingAI Ha, understood, no blue eyes on the card. Hers are dark brown and that stays with the trigger; eye colour is now one of the things I check per version before release. Thanks again.