Run Locally
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.
About This Model
QWEN2 · LoRAs
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
ModelTrends.ai Model ID
#28038
Flag content
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
res_multistep
Steps
20
Guidance
1
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"
Settings
Sampler
res_multistep
Steps
20
Guidance
1
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.
Settings
Sampler
res_multistep
Steps
20
Guidance
1
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.
Settings
Sampler
res_multistep
Steps
20
Guidance
1
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.
Settings
Sampler
res_multistep
Steps
20
Guidance
1
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.
Settings
Sampler
res_multistep
Steps
20
Guidance
1
Seed
264674189322294
Size
1440x2160
Prompt
A contemplative, high-contrast fine-art portrait of a graceful Japanese woman seated in disciplined seiza posture on aged, woven tatami mats inside a secluded Kyoto machiya tea pavilion. She is draped in a minimalist charcoal-gray raw silk kimono robe, fastened loosely with a textured slate-blue obi sash, revealing the elegant curve of her nape. Her glossy black hair is gathered into a clean, low chignon secured by a single polished ebony hairpin. Her fingertips rest deliberately upon the coarse, unglazed rim of a handmade ceramic matcha bowl resting on a dark lacquer low table. Bright morning sunlight pierces through sliding translucent paper shoji screens, casting razor-sharp, geometric grid shadows diagonally across her pale profile, collarbones, and the woven floorboards. The visual tone is shaped by serene chiaroscuro, featuring deep, velvety shadows and stark illuminated bands that highlight the quiet micro-textures of wood grain and silk fibers, capturing an enigmatic, time-suspended silence devoid of modern distractions.
Settings
Sampler
res_multistep
Steps
20
Guidance
1
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.
Settings
Sampler
res_multistep
Steps
20
Guidance
1
Seed
514556773112827
Size
1440x2160
Prompt
A vibrant, nostalgic 1980s City Pop-inspired environmental portrait of an energetic young Japanese woman dancing freely on an open commercial rooftop overlooking the panoramic Shinjuku skyline at dusk. She is caught in joyful, spontaneous movement, throwing her head back in carefree laughter while lightly adjusting a pair of classic silver-banded headphones with vibrant orange foam cushions. Her retro ensemble consists of an oversized color-blocked nylon windbreaker in pastel yellow, teal, and magenta, worn over a striped knit polo shirt and high-waisted acid-wash denim jeans. The sky behind her is an explosive gradient of blazing tangerine, pastel violet, and neon fuchsia as the sun dips below the smog horizon. Searing, low-angled golden backlighting wraps around her silhouette, creating an iconic spherical lens flare ring and luminous chromatic rim light that highlights her bouncing hair and fluttering jacket. Rendered with vivid, punchy Kodachrome color science, tactile analog grain, and infectious vintage summer euphoria.
Similar Models
AI Models for Image, Video & Text Generation
asian mix3 qwen2 is a LoRA for the Qwen2 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Qwen2 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
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919
Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026