UltraReal for Krea 2 and Klein 9B: texture back into smooth AI images
Topic: Models
By Captain
Published 2026-10-02
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
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.
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
euler_simple
Steps
8
Guidance
1
Seed
184159243949012
Size
1536x2728
Prompt
A haunting black-and-white avant-garde fashion photograph of a woman walking through a narrow European city alleyway, her entire body rendered in strong ghostly motion blur that creates a spectral, semi-transparent afterimage effect while the surrounding architecture remains crisply sharp and static. She has short dark cropped hair and an intense, direct confrontational stare toward the camera, her face comparatively sharper than the blurred streaking of her body. She wears a fitted black dress with a deep V-neckline trimmed in delicate lace, paired with a long dramatic black cape billowing and dissolving into soft wispy streaks around her legs as she strides forward. Tall weathered European apartment buildings with ornate window frames and worn stone facades line both sides of the alley, a metal fire escape staircase visible on the left, damp reflective pavement suggesting recent rain. Stark high-contrast black-and-white tonal grading, deep shadows and bright highlights, avant-garde editorial fashion photography style, long exposure motion blur technique, dreamlike supernatural mood, horizontal composition, sharp architectural detail contrasted against blurred spectral figure.
Negative prompt
blurry ugly bad
Settings
Sampler
Euler
Steps
6
Guidance
1
Seed
42
Size
720x1280
Prompt
Workflow
Settings
Sampler
er_sde
Steps
8
Guidance
1
Seed
1077667665931187
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 21-year-old adult woman, alone in the frame, in a calm lakeshore with a rowboat, in soft candlelight: she turns the still lake water over slowly, admiring it as both hands turning the still lake water. Her hands: turning the still lake water in her palms; her expression an exaggerated cross-eyed silly face, played broadly enough that the override is unmistakable, her gaze eyes crossed, clearly joking, with the eye direction remaining easy to interpret. Composition: a waist-up fashion portrait with gently blurred depth, facing slightly off-camera toward the left of frame, with the head angle and torso direction remaining clearly legible. Wardrobe: a soft chiffon blouse with wide-leg trousers, with rolled sleeve hems, matte gold buttons, and textured knit trim added as secondary garment detailing. Her jewelry: dangling star earrings with a stacked necklace set, noticeable and fashion-forward, adding a visible secondary design layer. The color treatment is honeyed highlights and amber midtones.
vizsumit's UltraReal LoRAs reduce the soft, smooth AI look and add real texture and detail, especially for close-ups and clothing. Learn versions, weights and prompts.
Overview
UltraReal
(KR2_V1) by vizsumit is a
LoRA
for
Krea 2
(with a
Klein 9B
sibling) that removes the smooth, plasticky AI finish and adds texture: skin, fabric weave, hair, surfaces. It works best on close-ups and medium shots where clothing and skin matter.
Versions: Krea_V2_Pro trained on SFW professional photography (portraits, lifestyle, fashion, wildlife, sports, architecture) for a polished look; Krea_V1 trained on a broader set for a natural look and reduced face bias. Trigger word: high-quality.
Reference
Name | Type | What it is |
|---|---|---|
Trigger | high-quality | Optional but helpful. |
LoRA weight | 0.6-1.0 | 0.8 default. |
Steps / guidance | 8 / 1 | Krea 2 defaults; higher guidance on Raw if available. |
Shots | close / medium | Where it shines. |
Combination | character LoRAs | Stacks well. |
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
- Prompt a medium shot with clothing and skin described.
- Add high-quality.
- Attach UltraReal at 0.8.
- Compare same-seed; look at fabric and hair.
- Lower to 0.6 with a strong character LoRA.
Examples
Street fashion
high-quality, a photorealistic photo of a 25-year-old woman with a messy chestnut bun and curtain bangs sitting on a cafe step in a corduroy jacket, candid, 50mm.
UltraReal 0.8
Wildlife
high-quality, a red fox pausing in long grass at dawn, dew, backlight, 400mm.
UltraReal 0.9
Creative idea: fabric close-ups
high-quality, a close-up of a hand-knitted wool scarf in cream and rust, soft daylight, macro.
UltraReal 1.0
Tips
- Fashion and lifestyle prompts suit the Pro version.
- Wildlife fur and feathers gain real texture.
- Describe fabric types (linen, denim, wool).
- Pair with the Skin Detail slider for portraits.
Troubleshooting
Over-textured skin
Why it happens
Weight 1.0 plus detail slider.
How to fix it
0.7.
Little effect on wide shots
Why it happens
Design.
How to fix it
Use closer framing.
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.
Questions
Klein version?
Yes, KL9 versions exist for Flux.2 Klein 9B.
Trigger?
high-quality, optional.
Links and sources
Models in this guide
Written by
Captain
Related guides
Models
Light Slider for Krea 2: deepen shadows while the subject stays lit
Loraholic's Light Slider darkens the darkest parts of a Krea 2 scene while keeping focus areas lit, a contrast-style control. Learn the range, two-pass advice and when to use the Brightness slider instead.
By Captain
2026-09-30
Models
Krea2 Melancholy v2: cinematic, restrained, emotional realism
zidius's Melancholy LoRA for Krea 2 produces contemplative, cinematic imagery with subdued palettes, shallow depth of field and emotional restraint. Learn its zidiusArt trigger, weight and ideas for quiet scenes.
By Captain
2026-10-03
Models
Fat/Skinny Weight Slider for Krea 2: body weight as a number
Loraholic's Weight Slider adjusts body mass in Krea 2 across a -10 to 10 range designed for predictability. Learn how to use it, stability notes and ideas for character design and fitness illustration.
By Captain
2026-10-01
Models
Krea2 Enhancer: cleaner detail and lighting for any Krea 2 style
vrgamedevgirl's Krea2 Enhancer LoRA polishes Krea 2 images across realistic, anime, product and fantasy styles without changing the prompt's intent. Learn the weight, workflow and ideas.
By Captain
2026-09-30
More guides
Models
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.
By Captain
2026-09-30
Models
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.
By Captain
2026-10-01
Models
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.
By Captain
2026-10-02
Models
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.
By Captain
2026-10-03
Models
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.
By Captain
2026-09-29
Models
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.
By Captain
2026-09-30

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026