UltraReal Krea2, Klein9b KL9_V4

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Pro studio (SpyGlass) Web

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.

Civitai Web

Pay per use

Generate on Civitai's own site; every image is paid for with Buzz credits.

Local apps

Requires setup

Set up local programs if your computer has capable hardware.

ModelDuel Web

Pay per use

Generate the same prompt on up to 50 checkpoint/base models at a time.

Rent a GPU on the cloud

Graydient Cloud GPU

New to LoRAs? Step-by-step guide: how to use Flux and Flux 2 LoRAs on Graydient

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Created by

vizsumit

on Civitai

by vizsumit - Ultra Real - Klein 9b V4

Creator notes

LoRAs for reducing the soft & smooth AI look and adds more texture and details to images. It works especially well for close-ups and medium shots where clothing details and skin texture plays an important role. Stop prompting from scratch, explore 10,000+ Prompts for free 👉 Run this exact workflow instantly on , no installation, no setup required. Use my promo code 'vizsumit' to get one month free. Version Comparison Krea_V2_Pro is trained on high-qulality SFW Professional Photography images with wide variety like portraits, lifestyle, fashion, wildlife, sports fitness, architecutre, nature and more. Prefer this for professional looking high-quality images. Krea_V1 is trained on high-qulality SFW and NSFW images so it can handle both. Besides making images more detailed it also reduces asian face bias. Prefer this for natural looking high-quality images. KL9_V5_Pro is trained on high-qulality SFW Professional Photography images with wide variety like portraits, lifestyle, fashion, wildlife, sports fitness, architecutre, nature and more. KL9_V4 is trained on more refined and 40% nsfw dataset, so besides better quality it has NSFW detailing capabilities too. KL9_V3 is trained on professional 4K quality images with higher steps. It applies very subtle skin texture which looks more realistic, without producing freckles and burnes. KL9_V2 for more natural looking skin texture than V1, can produce freckles and moles for some time. It is good at preserving skin tone and lighting also. KL9_V1 tends to produce overdone skin texture like more pores and freckles, and it can change lighting and skin tone also. 🖼️ Generation Settings Weight: 0.6-0.8 Krea_V2_Pro Trigger: no trigger needed Krea_V1 Trigger: no trigger needed KL9_V5_Pro Trigger: This is a high-quality photograph of a (your subject...) KL9_V4 Trigger: This is a high-quality photograph of a (your subject...) KL9_V3 Trigger: A high-quality photograph of a (your subject...) KL9_V2 Trigger: A high-quality medium close-up photo with realistic skin texture featuring a (your subject...) KL9_V1 Trigger: This is a high-quality photo with realistic skin texture and details of a (your subject...) 🛠️ Editing / Upscaling (Klein9b) Resoluton: 1.5MP - 2MP Weight: 1.0 For V5, 0.5 for later versions KL9_V5_Pro Prompt: Make this photo high-quality. Preserve subject's face, expression, figure and pose. Preserve overall composition of this photo. KL9_V4 Prompt: Make this photo high-quality. Preserve subject's face, expression, figure and pose. Preserve overall composition of this photo. KL9_V3 Prompt: Make this photo high-quality. Preserve subject's face, expression, figure and pose. Preserve overall composition of this photo. KL9_V2 Prompt: Make this photo high-quality with natural skin texture. Preserve subject's facial features, expression, figure and pose. Preserve overall composition of this photo. KL9_V1 Prompt: Make this photo high-quality featuring realstic skin texture. Preserve subject's facial features, expression, figure and pose. Preserve overall composition of this photo. Feel free to try it and share results or feedback. 🙂

Trigger words

High-quality photograph of a.

Make this photo high-quality.

13,895 downloads · 431 likes on Civitai

SHA256

DF2307852D99E103917E6BC60E58DA8971769BF716DEE443F10B201FCEE6CA18

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Also ranked: #138 Hottest AI model · #4 Hottest Flux 2 / Klein model

Not this creator?

Get your own badge

UltraReal Krea2, Klein9b KL9_V4 Popularity Trend

Heat score since 13 Apr 2026

Heat score

8,580°

This week

▼

0.2%

8,582° then, 8,580° now

This month

▼

0.8%

8,589° then, 8,580° now

Past year

n/a

Wasn't released/tracked

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+1,261°

Civitai downloads

13,895 downloads of this exact version on Civitai. Downloads are the heaviest ingredient and are counted on a log scale: ten times the downloads adds the same 300°, so a model with a million downloads is not a thousand times hotter than one with a thousand. The six download sources share that one term, split between them in proportion to their counts.

+395°

Likes

431 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.

+70°

Adoption rate

About 8 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.

−146°

Age

−146° because the Flux2 weights came out in 2025. Every model inherits the age of the weights it is built on: 150° a year, up to 750°, and it keeps growing until then. Without it the top of the list would be 2022 and 2023 checkpoints on the strength of downloads that had years to pile up.

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 8,580°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
13,895 download-equivalents in all, from Civitai downloads. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,261°
8,261°
running total
3
Add the likes.
431 likes and thumbs up, at half the weight of a download.
+395°
8,656°
running total
4
Add the adoption rate.
About 8 downloads a day right now, measured between two readings, at a quarter of the weight.
+70°
8,726°
running total
5
Take off the age.
The Flux2 weights came out in 2025: 150° a year, up to 750°, growing until then.
−146°
8,580°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,580°

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.

Example renders

Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.

Get this prompt

Render by vizsumit on

Settings

Size

1344x1728

Prompt

This is a high-quality close-up photograph of a young woman with fair skin and long, straight, platinum blonde hair that slightly covers her shoulders. She has light blue eyes, long eyelashes, and full, slightly parted pink lips. Her facial features are soft with a subtle blush on her cheeks. She is looking slightly to the right with a neutral, almost contemplative expression. The background is blurred, featuring a green field, leafless trees, suggesting an outdoor setting.

Render by Shojker on

Settings

Sampler

Euler

Steps

Guidance

Seed

1680692969

Size

832x1216

Weight used

0.6

Prompt

High-quality photograph of a young woman. The photo was taken with the woman unnoticed, voyeur candid picture. The woman has messy bun. She is wearing a tight croptop and fluffy pijama pants. She is standing in a very relax manner next to a table, holding a white ceramic cup of coffee she is taking a sip from. the photo is taken on the woman peaceful kitchen while the morning sunrays enter from a nearby window, illuminating the scene to give a warm atmosphere. iPhone photo, candid amateur snapshot, natural lighting, realistic skin texture.

Render by vizsumit on

Settings

Size

2688x1728

Prompt

This is a high-resolution photograph of a young woman with fair skin and long, wavy dark brown hair that falls past her shoulders. She has blue eyes, a slightly parted mouth with natural pink lips, and a focused, serious expression. She is wearing a vintage-style, slightly tattered white blouse with lace trim along the neckline and sleeves. The blouse is low-cut, revealing a significant amount of cleavage, and is adorned with a red ribbon bow at the center. Underneath, she has on a black corset with intricate patterns, which cinches her waist and accentuates her figure. The background is dimly lit room.

Render by Sparthano on

Settings

Sampler

Euler

Steps

Guidance

Seed

742446889

Size

832x1216

Weight used

0.8

Prompt

A close-up of a woman's face, satisfied expressive, wearing fashion oval glasses, with the mouth slightly open about to eat. Thin straight short blonde hair with bangs, Red full glossy lips, small upward nose, blue semi closed eyes, long lashes, thin eyebrows, really beautiful face, hyper detailed skin. Tanned skin. Holding a big slice of 3 layer cake, with white frost and a strawberry on top, partially inside the mouth. Dirty cream on the chin. Left lower perspective view. complex masterpiece, complex physics, Award-wining photo by Slim Aarons, magic realism, Art by Max Rive and Ryan Dyar, kodak style,

Negative prompt

low quality, text,

Render by subotaplaya565 on

Settings

Sampler

Euler

Steps

Guidance

Size

1536x1536

Prompt

transform the image to realistic photograph. add realistic details to the corrupted image, skin with textured detail. restore high frequence details from the corrupted image. Make this photo high-quality. Preserve subject's face, expression, figure and pose. Preserve overall composition of this photo. Realistic style of the image, realistic style, Best Quality, High Quality, Masterpiece, photograph, ultra detailed eyes, detailed face, realistic anatomy, high dynamic range, lucid, rich details, clear shadows and highlights, professional color grading.

Render by vizsumit on

Settings

Size

2688x1728

Prompt

This high-quality photograph features a close-up portrait of a woman with fair skin and light blue eyes. She has long, wavy blonde hair that cascades over her right shoulder, with a slight part on the left. Her eyebrows are well-groomed, and she has a subtle, natural makeup look with a light pink lip color. She is wearing small, silver hoop earrings with a decorative charm on the right earring. Her expression is calm and slightly smiling. She is dressed in a light beige, slightly ruffled blouse with a round neckline. In the background, there are two tall buildings.

Render by vizsumit on

Render by III0III on Civitai

Settings

Size

2688x1728

Prompt

This is a high-quality, close-up photograph of a young man with a medium-brown complexion, short-cropped black hair, and a neatly trimmed beard and mustache. He has dark brown eyes and is smiling warmly at the camera. He is wearing a black suit jacket over a white dress shirt, with the shirt collar slightly open. The background is a plain, solid white, which makes the subject stand out prominently.

How to install a LoRA: folders, file checks and first use in ComfyUI, Forge, Automatic1111 and Draw Things

No prompt was shared with this render.

Run Locally

How to install

Sep 24, 2025

Open Civitai Download

ultra_real_v4.safetensors

158 MB · SafeTensor

Downloads are served by Civitai. Some creators ask for a Civitai login first.

More by this creator

UltraReal Krea2, Klein9b KR2_V1

KREA2

Phone Photography (2000 2025) 2020_KR2

KREA2

Cinematic Dark Lighting KREA2

KREA2

Phone Photography (2000 2025) 2025_KL_9B

All models by vizsumit

The Body [Flux.2.klein.9B] Version H

Taffy Tales Style | Krea . Klein

YFG FutureIsDark [Flux | ZIB | Krea2] Flux.2 Dev v1.2