VOGUE BY STX

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

694 downloads · 71 likes on Civitai

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

STXai

on Civitai

by STXai - VOGUE BY STX V3 - This LoRA is an incredibly versatile utility tool for high-end lifestyle lookbooks, authentic candid street photography, and intimate character-driven editorial portraits. It serves as an ultimate "humanizer and depth fixer," allowing creators to feed in images plagued by flat digital skin smoothing, static or rigid poses, and generic lighting setups, and seamlessly transform them into deeply textured, lifelike, and visually stunning masterworks.

Creator notes

VOGUE 🌟 BY STX - Core Artistic Identity VOGUE 🌟 BY STX is a master-tier analog texture enrichment and cinematic lifestyle enhancement LoRA designed to breathe raw, human presence into character generations. Rather than trapping your concepts within a rigid style, this model adapts fluidly to the underlying intent of your prompt—whether it is authentic candid street photography, intimate indoor lifestyle portraits, or warm editorial fashion looks. It acts as an aesthetic engine that strips away artificial digital perfection and plastic AI glazes, delivering breathtakingly tangible skin complexions, rich environmental depth, and highly professional, humanistic compositional framing. - Visual Character and Atmosphere Strengths The model specializes in creating atmospheric, high-impact visuals with a profound sense of emotional nuance, warmth, and cinematic storytelling. It exhibits an extraordinary command over natural and ambient lighting physics, easily rendering complex phenomena like soft golden hour sunlight cutting through bedroom windows, volumetric cigarette smoke trails drifting in dim rooms, or dynamic motion blur that isolates the subject within a bustling urban crowd. It frames subjects with an organic, candid lens, capturing genuine facial expressions, relaxed bodily postures, and lifelike interactions with everyday environments that elevate the overall realism and believability of the scene. - Rendering, Detail, and Finish Surface execution is where VOGUE shifts generations into high-fidelity status. In photographic modes, it introduces beautifully hyper-real skin textures, showcasing naturally scattered freckles, fine pores, organic facial lines, and crisp, un-stylized individual hair strands. For wardrobe and setting details, it handles fabric physics with absolute precision, rendering the coarse weave of knit turtlenecks, heavy textured wool sweaters, and the authentic grain of denim jeans. When applied to everyday scenes, it completely eliminates digital artifacts, beautifully mimicking the soft grain, organic color falloff, and nostalgic tonal palette of premium vintage 35mm film stock. - Practical Use Cases This LoRA is an incredibly versatile utility tool for high-end lifestyle lookbooks, authentic candid street photography, and intimate character-driven editorial portraits. It serves as an ultimate "humanizer and depth fixer," allowing creators to feed in images plagued by flat digital skin smoothing, static or rigid poses, and generic lighting setups, and seamlessly transform them into deeply textured, lifelike, and visually stunning masterworks. - Workflow and Creative Direction Best results are achieved at weights between 0.8 and 1.2, where the model's comprehensive skin texture overhaul and advanced ambient light integration can fully take control of the frame. It responds exceptionally well to detailed descriptors of surface finishes (such as high-detail freckled skin, cozy knit textures, volumetric smoke, or fine film grain) and precise lighting environments (warm window light, golden afternoon sun, or cinematic motion-blurred backgrounds). Overall, VOGUE 🌟 BY STX is a premium artistic tool designed to turn predictable, flat AI generations into deeply immersive, texture-heavy masterpieces. STXai

SHA256

13E303591D9AFC943CA33506645275679713D3588D347D5DF30E5FC77873C0FC

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: #49 Hottest Krea2 model · #48 Hottest Krea2 LoRA

Not this creator?

Get your own badge

VOGUE BY STX Popularity Trend

Heat score since 23 Sep 2026

Heat score

8,322°

This week

n/a

Wasn't released/tracked

This month

n/a

Wasn't released/tracked

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.

+871°

Civitai downloads

694 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.

+279°

Likes

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

+72°

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.

+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 8,322°, 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.
694 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.
+871°
7,871°
running total
3
Add the likes.
71 likes and thumbs up, at half the weight of a download.
+279°
8,150°
running total
4
Add the adoption rate.
About 8 downloads a day right now, measured between two readings, at a quarter of the weight.
+72°
8,222°
running total
5
Family boost.
An open, bounded nudge for LoRAs of a family this site is pushing forward right now.
+100°
8,322°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,322°

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

NSFW

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.

NSFW render, blurred. Turn NSFW on to see it.

Get this prompt

Render by STXai on

Settings

Sampler

Euler

Steps

Guidance

Seed

1128205222

Size

2176x3840

Prompt

trucker hat, red cap, blonde bob, playful grimace, winking eye, showing teeth, y2k aesthetic, casual portrait, gold necklaces, lip gloss, youth culture, candid style, quirky expression, simple background, bright lighting, urban fashion, confident vibe, close up

Render by Gorfou on

Settings

Sampler

euler

Steps

Guidance

Seed

3623368227

Size

2048x1792

Prompt

<lora:Krea2 - STYLE - VOGUE BY STX (V3):1>,Artistic style: Ultra-detailed cinematic photograph,photorealistic,vintage aesthetic,Main subject and actions: Young Asian woman leans against weathered stone wall,gazing directly at camera,Facial expressions: Her eyes harden with resentment,mouth drawn into a slight grimace,Environment: Vintage European alleyway,faded pinkish-beige walls,peeling posters including partial red "AT" poster,Lighting and colors: Warm golden-hour lighting,soft shadows,dramatic contrast,rich saturated tones,Atmosphere: Nostalgic,cinematic,textured,intimate,Camera and composition: Low-angle perspective,tight composition focusing on upper body and textured wall,Quality modifiers: Shallow depth of field,8k resolution,high detail,sharp focus,detailed textures of fabric,skin,and wall

Negative prompt

Worst quality, Normal quality, Low quality, Low res, Blurry, Jpeg artifacts, Grainy, text, logo, watermark, banner, extra digits, signature, Poorly drawn face, missing fingers, extra fingers, elongated fingers

Render by _Ni3_Zgoda_ on

Settings

Sampler

Euler

Steps

Guidance

Seed

1900164389

Size

1280x1792

Prompt

masterpiece, Kani2reR, dARk_Fntsy A breathtakingly aesthetic anime scene viewed from inside a cozy vintage café during a quiet rainy evening. The composition follows a cinematic rule of thirds: a beautiful young woman is positioned on the far right side of the image, shown mostly from behind and in three-quarter profile, gazing thoughtfully through a large rain-covered window. She is NOT centered and does NOT dominate the composition. She has long, slightly tousled dark-brown hair with warm caramel highlights, a few loose strands framing her face, and soft expressive emerald-green eyes. She wears an oversized cream sweater, a muted dusty-rose scarf and a delicate little hair clip shaped like a flower. Her expression is peaceful and slightly dreamy, as if she has completely lost herself in watching the world outside. The majority of the image is devoted to the beautiful environment: enormous foggy café windows covered with tiny raindrops, warm amber pendant lights reflected in the glass, wooden tables with little candles, delicate ceramic cups, stacks of books, tiny plants, hanging dried flowers and soft knitted blankets draped over chairs. Outside the window, a charming old European-inspired street glows under the rain. Warm storefronts, tiny umbrellas, bicycles, flower boxes and glowing street lamps are reflected beautifully on the wet cobblestones. In the distance, barely visible through the mist, a tiny orange cat sits beneath an awning watching the rain. The woman is quietly observing the street, while the viewer's eye is drawn through the entire composition from the glowing café interior toward the rainy world outside. Strong environmental storytelling, cinematic depth, foreground objects slightly blurred, character placed naturally on the right third, large negative space on the left filled with atmospheric details. Soft rainy-day color palette: warm cream, caramel, muted sage green, dusty rose, chocolate brown and hints of golden amber. Cozy, intimate, wholesome and nostalgic atmosphere. Gentle anime linework, gorgeous expressive eyes, subtle blush, highly detailed hair, realistic fabric textures, delicate reflections in the window, soft bokeh, cinematic lighting, volumetric glow, atmospheric perspective, dreamy color grading, beautifully balanced composition, sophisticated anime illustration, whimsical slice-of-life aesthetic, incredibly detailed environment, elegant and heartwarming, masterpiece, 4k.

Render by STXai on

Render by HugeBlob on Civitai

Settings

Sampler

Euler

Steps

Guidance

Seed

2069801752

Size

2176x3840

Prompt

gulf stream, roaring twenties, gatsby style, vintage elegance, luxury party, evening gown, silk dress, tailored vest, bow tie, champagne glass, cinematic lighting, golden hour, expressive brushstrokes, digital painting, sophisticated mood, romantic gaze, retro glamour, architectural details

Render by Nysheep55 on Civitai

Settings

Sampler

euler

Steps

Guidance

Seed

1901851961

Size

928x1152

Weight used

Prompt

Side view photo, capturing a group sex scene, during a sorority party, messy bedroom. Women wearing pink flannel pyjamas and tight cropped tank tops, in the background, having fun, drinking and dancing, holding red plastic cups, and champaign, bottles, sorority party,, at a party, night time, dressed party girls in background watching the scene, messy and dimly lit bedroom. Man standing face out of frame, white tee, jeans pulled down, erect penis, three adult women are on their knees, kneeling around him, all very youthful and beautiful, with lip gloss, large breasts, // woman1 has long blonde hair, slim body and medium breasts, penis in mouth, wrapping her lip around penis, with her arms behind her back, looking up at the man, cute, worried, saliva string dipping from her mouth, tears rolling on her cheek // woman2 has short black single braid, small breasts, looking up confidently at the man, cute, cheerful. the man have his massive manly hand resting against the cheek of woman2. hand caressing woman2's cheek // woman3 has sleek copper hair, bob cut with blunt bangs, hands on the head and neck of woman1, helping her, pushing her head, laughing,

Negative prompt

child, chibi, underage

Render by HugeBlob on Civitai

Settings

Sampler

euler

Steps

Guidance

Seed

1548564111

Size

2048x2048

Weight used

0.2

Prompt

Cleo, Two fictional 21-year-old adult women and one adult male in a private apartment living room, realistic candid adult photo style. A blonde adult woman with mature facial features, long straight blonde hair, soft makeup, glossy lips, and a playful teasing expression is sitting upright backwards on the adult male viewer’s lap on a couch. She is sitting straight with her back upright, shoulders lifted, chest forward, and hips lowered onto his lap. She is not leaning forward. Her torso stays vertical and balanced while she turns her head over her shoulder to look back at the camera with a flirty smile. Her face has been made darker by shadows. She is wearing an adult cosplay-style outfit: a loose white blouse slipping off one shoulder, a short gray pleated skirt lifted over her hips, black lace bra detail partly visible, and a tiny pink thong. Her butt is very close to the camera and centered in the frame, with large round hips, thick thighs, soft realistic skin texture, and the pink thong pulled to the side. The thong strap is visibly shifted away from the center, exposing the intimate contact point. She is sitting down on the adult male viewer’s penis in a reverse cowgirl lap position while still sitting upright and facing the television. His body is mostly hidden underneath her and partly visible in the foreground. His legs, lower torso, and one hand holding a black game controller are visible from the first-person couch POV. His face is not visible. The penetration is partly visible between her thighs and under her shifted pink thong, but partially obscured by her butt, the couch angle, and her body sitting on his lap. The alignment is physically plausible: her hips are lowered onto him, her thighs are spread slightly over his lap, her butt presses against his pelvis, and her torso remains upright. She is holding colorful game controllers in both hands, as if playing a console game while sitting on him. Her posture is straight and confident, hips resting on his lap, back vertical, upper body not bent forward, only her neck and head turned back toward the camera. A second adult woman with short dark hair is sitting on the left side of the couch facing the television, holding a game controller and playing the same game. She is slightly out of focus in the background, turned away from the camera. The living room has a large TV showing a colorful racing game, speakers beside the TV, a coffee table with papers and controllers, a gray couch, pillows, and soft daylight. The scene feels like a candid intimate gaming hangout at home. Realistic smartphone photo, first-person POV from the couch, natural indoor daylight, shallow depth of field, realistic skin texture, subtle pores, tiny imperfections, soft shadows, natural fabric texture, detailed hair, realistic body contact, realistic anatomy, raw candid realism, high detail, sharp focus, not airbrushed, not plastic

Render by HugeBlob on Civitai

Settings

Sampler

euler

Steps

Guidance

Seed

415249373

Size

768x1376

Weight used

Prompt

Male pov perspective. Male nude legs visible in the bottom of the frame. Large, massive erect penis erected from the bottom of the frame, going to the left side in the blonde woman's mouth. Male arms entering from both sides, grabbing the heads of the women. Very large and manly hands. Viewer forcefully stuffing his cock down the blonde's woman mouth while the brunette waits for her turn. A candid, unposed photo capturing a young women kneeling on the sand, with her ass, visible. The woman kneel, wearing bikinis, their backs arched prominently, ass up. Face in the foreground, asse in the background. blonde, pale skin, nude-pink lips, wearing a red polka dot bikini, giving blowjob, Penis is penetrating the blonde's mouth. Blonde is deepthroating the penis. Penis deeply penetrating her mouth. Face close to the man. She looks in pain, suffering expression, crying expression, looking at viewer. Kneeling just next to her, on the right side, an other woman adopts the same pose: brown hair, tan skin, brown eyes, sharp brown lips, arab-indian, white bikini, mouth closed, waiting for her turn. submissive, vulnerable, cute, worried. Large male hand covering their heads, pushing their heads down in a dominant, forceful and humiliating way. Skin covered in a glossy sheen from sweating and sea salt, highlighting the soft contours of their gently rounded faces, freckles visible. The setting is a sandy beach at sunset, with warm, golden hour light filtering through, casting long shadows and creating a warm, off-white color balance typical of older smartphone cameras. The lighting reflects off the sweat on their skin, creating specular highlights. The image quality mimics a high-ISO digital phone camera: slightly visible digital noise, low resolution, and distinct JPEG compression artifacts. The autofocus is slightly soft or missed, giving it an authentic, unpolished, casual aesthetic. The framing is awkward and unposed, capturing the raw energy of the unposed moment without any studio staging.