[Qwen Image] Asian Mix Lora

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

1,531 downloads · 85 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

hinablue

on Civitai

by hinablue - [Qwen Image] Asian Mix Lora - v3.0 - Q21 - rank64 Trained using a custom-built trainer with a dataset of 6,000 images, using Rank 64, and merged with v2.0 via SVD to create this LoRA. It is more stable at a weight below 0.8. Limb/anatomy issues may still occasionally occur, so please use at your own discretion.

Creator notes

v3.0 - Q21 - rank64 使用自行製作的訓練器訓練（），資料集為 6,000 筆，使用 Rank 64 做訓練，與 v2.0 做 SVD 融合而成的 Lora。權重在 0.8 以下較為穩定，肢體可能還是會有異常狀況，請自行斟酌使用。 Trained using a custom-built trainer () with a dataset of 6,000 images, using Rank 64, and merged with v2.0 via SVD to create this LoRA. It is more stable at a weight below 0.8. Limb/anatomy issues may still occasionally occur, so please use at your own discretion. 自作のトレーナー () を使用し、6,000枚のデータセット、Rank 64にて学習を行いました。その後、v2.0とSVDマージして作成したLoRAです。適用ウェイトは0.8以下が比較的安定します。手足などの四肢に乱れが生じる場合がありますので、各自調整の上ご使用ください。 자체 제작한 ()트레이너로 6,000장의 데이터셋을 활용해 Rank 64로 학습시켰으며, v2.0과 SVD 병합하여 제작한 LoRA입니다. 가중치는 0.8 이하에서 비교적 안정적입니다. 사지(손발) 묘사에 일부 불안정한 현상이 발생할 수 있으니, 적절히 조절하여 사용해 주시기 바랍니다. v2.0 - Q21 使用 Krea2 資料集，訓練 Qwen Image 2.1 的 Lora。目前僅使用 2,000 筆資料做實驗性的訓練，不保證使用效果。 Lora for Qwen Image 2.1 was trained using the Krea2 dataset. Currently, only 2,000 dataset are used for experimental training, and the results are not guaranteed. Krea2 データセットを使用して、Qwen Image 2.1 の Lora をトレーニングします。現在、実験トレーニングに使用されるデータは 2,000 件のみであり、結果は保証されていません。 Krea2 데이터 세트를 사용하여 Qwen Image 2.1의 Lora를 훈련합니다. 현재 실험 훈련에는 2,000개의 데이터만 사용되며 결과는 보장되지 않습니다. v2.0 使用與 Flux/SD3.5 相同資料集，增加 4000 張正規化資料重新訓練。 Retrain using the same dataset as Flux/SD3.5, with an additional 4000 regularization images. Flux/SD3.5と同じデータセットを使用し、さらに4000枚の正則化画像を追加して再学習を行う。 Flux/SD3.5와 동일한 데이터셋을 사용하되, 4000개의 추가적인 정규화 이미지를 포함하여 모델을 재학습시킵니다. v1.0-alpha 使用與 Flux/SD3.5 相同資料集訓練的 Qwen-Image Lora，這是前期測試版本。 Qwen-Image Lora, trained using the same dataset as Flux/SD3.5, is an early testing version. Qwen-Image Lora は、Flux/SD3.5 と同じデータセットを使用してトレーニングされた、初期のテストバージョンです。 Flux/SD3.5와 동일한 데이터 세트를 사용하여 학습된 Qwen-Image Lora는 초기 테스트 버전입니다.

Trigger words

asian woman

SHA256

A1B34A8832D8446CD2486C80EDFEA262846A977DCE6818A7B810FCE8FA093997

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: #181 Hottest AI model · #4 Hottest Qwen2 model · #4 Hottest Qwen2 LoRA

Not this creator?

Get your own badge

[Qwen Image] Asian Mix Lora Popularity Trend

Heat score since 1 Oct 2026

Heat score

8,499°

This week

▲

37.6%

8,436° then, 8,499° now

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.

+976°

Civitai downloads

1,531 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.

+290°

Likes

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

+133°

Adoption rate

About 58 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 8,499°, 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.
1,531 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.
+976°
7,976°
running total
3
Add the likes.
85 likes and thumbs up, at half the weight of a download.
+290°
8,266°
running total
4
Add the adoption rate.
About 58 downloads a day right now, measured between two readings, at a quarter of the weight.
+133°
8,399°
running total
5
Family boost.
An open, bounded nudge for LoRAs of a family this site is pushing forward right now.
+100°
8,499°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,499°

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 hinablue on

Settings

Sampler

res_multistep

Steps

Guidance

Seed

494722953551345

Size

1440x2160

Prompt

Create a Japanese adult girl pouting in theatrical lovely with lips and wearing lipgloss as the central figure. Closeup, Set against a cinematic backdrop with soft focus and dreamy Pro-Mist diffusion filter. Capture the essence of vintage charm with flash photography, enhanced by ultrarealistic photography and hyper-realistic details. The lighting is carefully composed to evoke a sense of depth and emotion, with motion blur from camera panning adding a dynamic touch. Render the final image in ultra-HD and 8k resolution with high detail and best quality, capturing the realism of her skin and the vibrant, emotive atmosphere. Handwritin, free-style, strong, bold, golden text on the bottom of the photo "AsianMix Q2.1"

Render by hinablue on

Settings

Sampler

res_multistep

Steps

Guidance

Seed

685607139373673

Size

1440x2160

Prompt

A striking avant-garde graphic portrait inspired by 1920s Bauhaus constructivism and Russian avant-garde aesthetics, featuring a sharp, statuesque East Asian woman. The composition is built upon rigid, asymmetrical geometric forms, primary color blocking, and dynamic diagonal axes. She wears a structured, architectural wool-crepe garment combining intersecting panels of cobalt blue, cadmium red, and stark ivory white, finished with a stiff, high-cut cylindrical collar. Her jet-black hair is cut into an ultra-sharp geometric bob with ruler-straight blunt bangs that align mathematically with the frame's diagonal composition lines. Harsh, non-diffused theatrical spotlights cast razor-sharp, angular cast shadows across her pale porcelain face and the stark concrete background, transforming light and shadow into hard physical shapes. Minimalist, bold graphic tension, poster-art precision, matte surface textures, and an unapologetic, emotionless editorial gaze looking directly down the lens.

Render by hinablue on

Settings

Sampler

res_multistep

Steps

Guidance

Seed

449311593581211

Size

1440x2160

Prompt

A lavish 1920s Art Deco luxury portrait of a sophisticated East Asian woman standing inside the grand foyer of a stylized Manhattan skyscraper ballroom, channeling Tamara de Lempicka’s bold geometric glamour. She wears a body-skimming bias-cut champagne silk evening gown dripping with intricate rows of hand-strung golden glass bugle beads and trailing black ostrich feathers over her bare shoulders. Her dark finger-waved flapper bob is immaculately sculpted with glossy pomade, set off by dangling geometric platinum-and-onyx earrings. Symmetrical, tiered chevron light sconces and polished brass fixtures cast dramatic upward and downward fans of radiant, warm tungsten illumination, throwing sweeping angular shadows across marble pillars behind her. Strong, streamlined curves, sharp planar highlights sculpting her cheekbones, rich metallic reflections, and an intoxicating atmosphere of opulent Jazz Age decadence and aristocratic mystery.

Render by hinablue on

Settings

Sampler

res_multistep

Steps

Guidance

Seed

50547666238583

Size

1440x2160

Prompt

A nostalgic, warm-toned Japanese summer cinema still of a 20-year-old Japanese woman walking freely through a sprawling, wind-swept golden wheat field at late afternoon. She is captured mid-stride, gracefully twisting her upper torso back toward the camera with a squinting, serene smile, holding her vintage woven straw hat in one hand while the other grazes the ripening stalks. She wears a breezy, ankle-length off-white linen sundress featuring delicate shoulder ties, complemented by natural canvas tote bag resting against her hip. The composition is utterly dominated by intense, low-angle golden hour backlighting pouring from the horizon, casting colossal volumetric sunbeams and honeyed anamorphic lens flares directly into the camera. Brilliant golden rim light traces every loose, wind-blown strand of her chestnut-tinted hair and the natural fibers of her cotton dress. Floating dandelion seeds and shimmering airborne pollen glow like micro-embers in the sunbeams, creating an authentic 35mm film aesthetic with pastel highlight blooming, rich earthy undertones, and profound pastoral warmth.

Render by hinablue on

Settings

Sampler

res_multistep

Steps

Guidance

Seed

749415146116850

Size

1440x2160

Prompt

A fine-art masterpiece portrait of a poised East Asian woman rendered in the grand classical tradition of Baroque oil painting, reminiscent of Caravaggio. She sits in three-quarter profile against an impenetrable, pitch-black void, her body draped in an opulent midnight-crimson velvet robe with voluminous, sculpted folds and antique gold-threaded embroidery along the cuffs. Her raven hair is coiled into a textured, painterly braided crown pinned with a solitary, matte pearl ornament. Extreme, theatrical single-source chiaroscuro light pours aggressively from an unseen upper-left aperture, carving the delicate topography of her cheekbone, bridge of the nose, and exposed collarbone out of absolute darkness with luminous impasto highlights. The surrounding shadows remain deep, warm, and velvety, preserving subtle umber and burnt-sienna glazes. Visible oil-on-canvas craquelure, buttery pigment textures, tactile brushstrokes, and a profound, solemn stillness evoke an authentic museum-grade archival oil painting.

Render by hinablue on

Settings

Sampler

res_multistep

Steps

Guidance

Seed

335343098310782

Size

1440x2160

Prompt

A cinematic, emotionally evocative medium shot of a solitary Japanese woman riding an empty Yamanote line commuter train carriage late on a rainy autumn night. She sits quietly by the dark glass window, resting her forehead gently against the cool surface while gazing outside with heavy-lidded, introspective eyes. She is bundled comfortably in a tailored navy-blue wool trench coat with a voluminous, plush oatmeal cashmere scarf wrapped loosely around her neck and chin. The interior of the car is illuminated by cool, low-contrast overhead fluorescent tubes, casting delicate cyan reflections across the polished metal handrails. Through the rain-streaked window, heavy water droplets run down the glass, refracting the blurry, multi-colored neon signs and amber sodium streetlamps of the passing city into creamy, circular bokeh blooms. The atmosphere is soaked in quiet urban melancholy and introspective solitude, featuring soft highlight halation, gentle film grain, and a muted, cinematic color palette dominated by deep blues and wet reflections.

Render by hinablue on

Settings

Sampler

res_multistep

Steps

Guidance

Seed

1051520254864420

Size

1440x2160

Prompt

A cinematic, medium-shot portrait captured on vintage 35mm color film, depicting a 22-year-old Japanese woman standing on the rain-slicked asphalt of a quiet Shimokitazawa backstreet at dusk. She is turning mid-stride to glance over her shoulder toward the lens, her body caught in spontaneous, kinetic movement. Her jet-black, shoulder-length wolf cut tumbles messily across her cheekbones, with stray damp strands catching the ambient glow of amber neon signs and buzzing street lanterns. She wears an eclectic, layered streetwear ensemble: an oversized charcoal wool blazer draped loosely over an olive-drab cropped knit sweater, paired with wide-leg pleated trousers and worn leather ankle boots. The rich weave of the heavy wool and the tactile knit texture contrast against the reflective, mirror-like puddles below her feet. The lighting is shaped by moody urban chiaroscuro. Diffuse cyan-tinted dusk light fills the rainy atmosphere, while a searing, warm tungsten spill from a nearby vintage vinyl shop window casts a dramatic golden rim light along the edge of her jaw, throat, and jacket collar. The background melts into creamy, spherical bokeh formed by wet storefront signs and distant bicycle headlights. The shot is captured with a high-end prime lens at an aperture of f/1.8, creating a delicate depth of field with soft highlight blooming from a Black Pro-Mist filter. The entire frame is enriched with tactile analog film grain, subtle vertical emulsion scratches, glowing airborne mist particles caught in light beams, and a muted, nostalgic Japanese cinema color palette with deep greens and warm honey accents.

Render by hinablue on

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

Settings

Sampler

res_multistep

Steps

Guidance

Seed

916946894158210

Size

1440x2160

Prompt

A high-end, realistic 35mm film portrait of a charming Japanese woman in an intimate, softly lit dressing room, striking a poised and practiced cute pose. Captured from a slightly elevated high-angle perspective in a tight head-and-shoulders composition, her rounded face is tilted gently downward while her expressive dark eyes look up toward the lens with endearing sweetness. Her lips form a controlled, delicate heart-shaped smile. Her glossy, shoulder-length dark brown hair is styled naturally, pinned above one ear with a petite black velvet ribbon clip. One delicate hand is raised beside her cheek, flashing a subtle, playful peace sign. She is dressed in an airy ivory cotton blouse featuring an intricate frilled collar, micro-pleated cuffs, and a faint hint of a muted rose silk camisole underneath. The scene is illuminated by soft, directional afternoon window light that grazes one cheekbone, producing smooth tonal roll-off, luminous eye catchlights, and soft shadows beneath her jawline. The background melts into a dreamy, shallow-depth bokeh showing the warm wooden tones of a vanity mirror, subtle glass cosmetic bottles, and sheer linen curtains. Rendered with authentic analog film texture, visible skin pores, tactile fabric details, and a quiet editorial lifestyle realism.

Run Locally

How to install

Sep 24, 2025

Open Civitai Download

hina_QwenImage2.1_asianMix_Lora_v3.0-rank64.safetensors

320 MB · SafeTensor · bf16

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

More by this creator

[MiniMax H3] AsianMix Lora

MINIMAX H3

Qwen Image 2.1 Restore LoRA

All models by hinablue

Similar Models

zjourney Fantasy Realism Refiner Ideogram 4/Krea 2/Qwen2.1 zjourneyQwen2.1

Watermark removal lora

Qwen Image 2.1 Consistency LoRA