UltraReal Krea2, Klein9b KR2_V1
8804°
<ultrareal-krea2>
Apps that support ModelTrends tags let you run/install models by copying this code in your prompt with no setup. Look for our icon in apps that support it, like Prism (below).
Run this model
Offers / Ads
Easy Creator (Prism) Web
Unlimited · flat fee
Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.
PirateDiffusion Telegram
Unlimited · flat fee
Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.
Pro studio (SpyGlass) Web
Unlimited · flat fee
Best for power users. Full control over models, settings and workflows in a browser studio.
Discord bot (Vector)
Unlimited · flat fee
Best for communities. Add it to your own server and run any workflow from a channel.
Unified Editor Web
Unlimited · flat fee
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.
Guides for this model
All guides
by vizsumit - UltraReal - Krea2
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
SHA256
083EDC5BF8B333DC1859DFD5FF937EAD86F2977A4167E3BAFD0C761AD3B24108
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.
Also ranked: #8 Hottest Krea2 model · #7 Hottest Krea2 LoRA
Not this creator?
Get your own badge
UltraReal Krea2, Klein9b KR2_V1 Popularity Trend
Heat score since 2 Jul 2026
Heat score
8,804°
This week
▲
1.3%
8,800° then, 8,804° now
This month
▲
6.8%
8,786° then, 8,804° 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.
+1,211°
Civitai downloads
9,323 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.
+388°
Likes
386 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.
+105°
Adoption rate
About 24 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.
+100°
Family boost
+100° because this is a LoRA of a family this site is nudging forward right now. It is a bounded nudge inside the score and is listed here openly; it can never hide a model or outweigh a thousandfold difference in downloads.
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 8,804°, 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.
- 1Start 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
- 2Add the downloads.9,323 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.+1,211°8,211°running total
- 3Add the likes.386 likes and thumbs up, at half the weight of a download.+388°8,599°running total
- 4Add the adoption rate.About 24 downloads a day right now, measured between two readings, at a quarter of the weight.+105°8,704°running total
- 5Family boost.An open, bounded nudge for LoRAs of a family this site is pushing forward right now.+100°8,804°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,804°
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.
NSFW render, blurred. Turn NSFW on to see it.
NSFW render, blurred. Turn NSFW on to see it.
NSFW render, blurred. Turn NSFW on to see it.
No prompt was shared with this render.
Settings
Sampler
er_sde
Steps
8
Guidance
1
Seed
753514596078583
Size
1080x1920
Weight used
0.4
Prompt
AnnabelleX, dark chestnut-brown hair in a loose messy high bun with wispy curtain bangs and face-framing strands, braces. A photorealistic photo of a 20-year-old adult woman in candid street-fashion corner. She sits backward on a transparent acrylic cube, arms folded over the backrest, making an exaggerated deadpan expression. Her expression is caught mid-yawn, eyes watering slightly, with soft facial tension and readable nuance around the eyes and mouth, her gaze heavy-lidded and sleepy, with the eye direction remaining easy to interpret. She wears a experimental fisheye model-inspired costume: graphic bodysuit under oversized jacket and platform boots, with molded shoulder panels. Her character look is completed with camera-ready editorial makeup matched to the lighting style, with clean skin texture and precise detail. She also wears an oversized hoop set with a chunky ring, noticeable and fashion-forward, adding a visible secondary design layer.
No prompt was shared with this render.
Settings
Sampler
er_sde
Steps
8
Guidance
1
Seed
656988693863257
Size
832x1216
Weight used
0.2
Prompt
SiennaX, shoulder-length voluminous platinum-blonde hair with darker roots, styled in tight natural curls with a deep side part and softly defined ringlets around the face. A photorealistic photo of a 22-year-old adult woman in a private art gallery opening, featuring polished metal, reflective finishes, and draped textiles, with a fully described visual identity rather than a generic empty backdrop, at golden hour over the water, with the space still quiet and undisturbed. She angles her torso toward a champagne tray and curls her fingers around it with gentle deliberate control. Her expression is wide-eyed astonishment, with the emotion clearly visible at first glance, her gaze eyebrows shot up, completely caught off guard, with the eye direction remaining easy to interpret. She wears a detail-rich draped halter gown in opera gloves, finished with fitted bodices, strappy heels, and beaded trim, with a softly gathered train. Her jewelry: layered star and moon pendant necklaces with a stack of colorful rings, noticeable and fashion-forward, adding a visible secondary design layer.
Settings
Sampler
Euler
Steps
10
Guidance
1
Seed
928441652735771
Size
2000x3200
Prompt
Ċ assistant Ċ detailed uncensored description: n0vuschr0ma style, "digital artifacts", "glitch art", "dispersion effect", "disintegrating into fragments", or "holographic".
ESTHETIC AND SHOT: 1980s retro school yearbook portrait, funny anthropomorphic animal concept, vintage analog studio photography, soft-focus lens effect, subtle film grain texture, gentle front-left studio lighting, nostalgic color grading.
FOREGROUND OBJECT (ANTHROPOMORPHIC CAT):
- QUANTITY: One domestic cat.
- SHAPE: A fluffy orange tabby cat head with a soft rounded face, a small pink nose, and a warm, pleasant expression. The cat is wearing large, iconic 1980s aviator-style eyeglasses with thick, translucent tortoise-shell or light brown plastic frames and oversized square-oval lenses.
- SIZE: Centered shoulder-up portrait shot of the cat, occupying the central vertical axis of the frame.
- COLOR: Vibrant orange and ginger tabby fur with white patches around the chin, muzzle, and neck. Beautiful, striking, wide-open yellowish-green eyes with vertical slit pupils looking through the glasses. Wearing a clean, bright white collared polo shirt or button-down blouse with a wide open V-neck collar.
- TEXTURE: Ultra-soft, detailed, fluffy cat fur, long white stiff whiskers projecting outward, smooth cotton fabric of the white shirt, and glossy reflective plastic on the eyeglass frames.
- TEXT: None.
HAIRSTYLE & DETAILS (PRESERVED):
- Shape: A surreal, comedic integration of a quintessential 1980s voluminous mallet or shag haircut seamlessly blended onto the cat's head. The top section of brown hair is heavily teased and puffed upward into a high, thick dome with short rounded bangs brushing the top of the eyeglass frames, while the cat's orange ears poke through. The sides and back cascade down onto the shirt in dense, crinkled, wavy permed layers that flare outward at the bottom.
BACKGROUND:
- Elements: A classic retro studio portrait backdrop canvas with a subtle, painterly, textured finish resembling soft blue paint clouds.
- Lighting: Soft, diffused key lighting coming from the upper-left, evenly illuminating the cat's face and casting very gentle, faint shadows under the jaw line.
- Colors: Solid, muted sky-blue (#87CEEB) and soft steel-gray tones, creating a calming, low-contrast background that makes the white shirt and orange fur stand out.
SPATIAL RELATIONSHIPS:
- Placement: The anthropomorphic cat is positioned strictly in the center, angled at a subtle three-quarter turn to the right, but with its head turned back slightly to face and look directly into the camera lens.
- Interaction: The large eyeglasses rest squarely on the bridge of the cat's furry nose, with the top frame edge perfectly aligned under the full, dense human-like bangs. The wide white collar folds neatly over its furry shoulders.
- Depth: Pronounced shallow depth of field; the cat's green eyes, long whiskers, eyeglasses, and pink nose are in razor-sharp focus, while the voluminous hair curls on the sides and the textured blue background softly recede into a smooth, gentle blur.
Settings
Sampler
er_sde
Steps
8
Guidance
1
Seed
918631015679852
Size
864x1536
Weight used
0.4
Prompt
LexiX, long platinum-blonde hair styled in high twin ponytails with a center part, blue hair ties, two loose face-framing strands, and dip-dyed ends fading into pastel pink on one side and bright cyan-blue on the other. A striking conceptual photo-manipulation artwork: set against stained off-grey plaster under weak practical light, a 21-year-old adult woman: dramatic shadow bands radiate through and around her silhouette, rendered as an unsettling practical-horror effect built from shadow bands. Render the effect strongly and clearly, dominating the frame rather than fading into the background. Her expression is a dramatic, playful pout, interpreted in a varied professional and experimental photography styles portrait and her gaze is briefly caught mid-glance away from camera. A 35mm rear-curtain-flash motion portrait at 1/15 second, body sharply flashed while colored ambient trails streak behind, extreme low 20mm fashion angle from pavement level.
Settings
Sampler
er_sde
Steps
8
Guidance
1
Seed
1083509763509471
Size
864x1536
Weight used
0.4
Prompt
SeleneX, long honey-blonde hair with darker roots, center-parted and worn loose in smooth softly layered lengths. A photorealistic cinematic photograph of a 22-year-old adult woman, alone in the frame. The core image idea is this: sitting at the edge of a platform with the legs apart while a shadow line hides the pubic area, with the nearest thigh creating natural visual coverage. At the same moment, a lamp flickers repeatedly, so the event feels central rather than decorative. Her body is stretched along a long diagonal, reinforcing the selected action and its direction of movement. Her hands are one hand lifting hair away from the face. Her expression is dropping the shoulders in fatigue, with the head angle supporting the emotion. Her gaze is looking through a doorway or opening, with the head angle supporting the gaze. Frame the moment as a wide-lens crouching portrait at eye level, with strong foreground-to-background separation. Fully nude, styled with a pair of statement earrings and a bracelet, with realistic material contrast against natural skin. Use minimal makeup with subtle contouring. The legs remain visibly open while the chosen angle, thigh overlap, hands, shadow, or nearby surface keeps the pubic area fully concealed in a non-explicit fine-art composition. Skin keeps a natural human tone and realistic uncoated texture, with decorative color limited to separate garments, makeup, props, and accessories. Use a cool silver and blue palette.
Settings
Sampler
er_sde
Steps
8
Guidance
1
Seed
147103032485002
Size
864x1536
Weight used
0.4
Prompt
ElodieX, light ash-brown hair with subtle blonde highlights, center-parted and gathered into a low braided bun at the nape, with two long loose face-framing strands. She’s on all fours, shown in a full-body side view, with her butt being devoured by a transparent slime monster. She’s wet; you can see her bare breasts and nipples. Her face shows ecstasy because the monster is satisfying her vagina at the same time.
Run Locally
ultra_real_krea2_v1.safetensors
Downloads are served by Civitai. Some creators ask for a Civitai login first.
UltraReal Krea2, Klein9b KR2_V1 is a LoRA for the Krea2 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Krea2 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153