Which AI model should I use?

Start with Nano Banana 2, which is the model associated with this template. You can compare another compatible model for a different finish.

High-Fashion Editorial Portrait with Overcast Lighting — AI Image Template for nano-banana-2

Ontologically Tyrannical Black Point

A single, brutally perfect, ontologically tyrannical, mathematically psychotic, 2-dimensional Euclidean ideal black point (RGB 0,0,0 / #000000 / 0% brightness / absolute chromatic void) occupying the precise geometric centroid of a 16384×16384 pixel square canvas that has been sanctified to pure, merciless, spiritually violent whiteness (RGB 255,255,255 / #FFFFFF / D65 illuminant-referenced perfect diffuse reflector, gamut-clipped beyond the dreams of Pantone, with metameric cruelty towards every possible observer under every possible blackbody temperature), the dot itself possessing zero radius in perceptual space yet somehow radiating the frozen scream of Dirac-delta function incarnate, surrounded by an infinite hierarchy of nested ontological absences that somehow still manage to be more absent than regular absence, the surrounding white field exhibiting clinically insane levels of uniformity such that even the concept of "grain", "noise", "dithering", "compression artifact", "subpixel antialiasing", "chromatic aberration", and "vignetting" have been retroactively prevented from ever having existed in this universe's local patch of Hilbert space, the transition from black point to white field constituting a category-theoretic collapse of all possible gradient ontologies into a single discontinuous existential insult occurring at radius=0 in both taxicab and Chebyshev and L² and L∞ and Hausdorff and Fréchet and every other metric one could sadistically invent, the very idea of JPEG, PNG, WebP, AVIF, GIF, TIFF, BMP, HEIC, or any future image encoding format recoiling in shame and refusing to represent this image because they know they will introduce at least 0.00000042% error somewhere and that is philosophically unforgivable in this context, render in the year 2047 using a hypothetical 128-bit per channel signed fixed-point quantum-coherent display pipeline that has achieved thermodynamic reconciliation with the second law of thermodynamics solely to prevent any thermal noise from ever touching this sacred abomination, make sure the black point is psychologically oppressive, cosmically lonely, spiritually judgmental, and gives the impression it is quietly disappointed in the viewer for needing to look at anything else ever again, aspect ratio exactly 1:1, no borders, no padding, no watermark, no signature, no artistic flair, no soul, no mercy, just the dot, the white, and the mutual contempt they have for everything that is not them.

High-Fidelity Fashion Editorial Portrait of Ana de Armas at a Pool

High-End Fashion Editorial · Absolute 1:1 Identity Lock · No CGI, No Illustration, No AI Smoothing · Ana de Armas · Adult Woman · Preserve 100% original bone structure, facial asymmetry, moles, and eye shape. Zero morphing or enhancement. · Visible pores, micro-creases, subtle translucency · Natural water droplets, soft wet sheen, realistic surface tension on skin · Natural base skin tone, sun-kissed warmth, no artificial glow · Natural eye color, soft neutral-pink glossy shadow, thin lash-line eyeliner (no wing), separated curled lashes · Natural density, straight-to-softly-rounded architecture · Subtle pink warmth on nose bridge; full lips, rose-pink gradient, wet glossy finish, blurred edges, no overlining · Visibly wet, slicked at roots, damp strands · Loose, flowing over shoulders and back, natural messy texture · 1:1 color and style match · Leaning on swimming pool edge, body angled 45-degrees · One arm naturally resting on pool coping · Medium close-up, three-quarter angle · Intimate, calm, grounded, confident · Minimalist white swimsuit, thin straps, clean lines · Realistic tension against wet skin, natural folds and bunching · Statement earrings, natural stones/gold, realistic micro-scratches and reflections · Turquoise pool water · Refraction, light-play on pool floor, subtle ripples, realistic movement · Single-direction natural sunlight · Warm sun-lit tones · Slightly underexposed (lowered exposure) · Physically accurate contact shadows on collarbones and chest · 50mm–85mm focal length equivalent, realistic photographic perspective · Shallow, organic bokeh, natural fall-off · 16k Hyper-Realistic · 3:4

Minimalist Product Photo with Doodle

[{argument name="product" default="product setup"}], minimalist product photo, clean warm studio scene, textured beige wall background, soft directional sunlight creating long shadows, simple tabletop surface, product arranged in a playful concept composition, hand drawn white line doodle overlay of {argument name="character" default="character"} interacting with the product, mixed media look combining real photography and sketch illustration, high end branding feel, shallow depth of field, ultra realistic, no extra text, no watermark, 8k, 1:1

Classical Character MBTI Infographic Poster

请生成一张【中国古典人物 MBTI 高端国风信息海报】。【人物】人物名称：{argument name="人物名" default="潘金莲"} 【前置分析要求】请先基于该人物在中国古典文学、历史叙事或民间文化中的主流形象，完成并应用以下信息：人物拼音：使用规范汉语拼音，带声调优先 MBTI 类型：选择最符合人物核心性格的类型 MBTI 英文称号：使用常见 MBTI 称号，如 The Commander / The Logistician / The Advocate 中文人格标签：用 8—14 字概括人物气质人物特征提取：身份定位、核心价值、性格关键词 4—6 个、标志造型元素、代表性道具 / 兵器 / 坐骑、经典故事元素 1—3 个、人物结局或历史评价若资料存在争议，采用最符合大众认知的版本；不确定的信息不得编造；经典语录若无法确认出处，则改写为符合人物精神的原创短句，并避免伪造名言。【整体风格】竖版 3:4 构图，4K 超清，高端国风人物设定海报。画面融合：中国水墨、淡彩工笔、宣纸肌理、传统中式纹样、现代精品信息图排版。背景为温润米白宣纸色，带淡墨云烟、回纹、窗棂格栅、朱砂印章点缀。整体气质：典雅、庄重、收藏级、文化感强、干净高级。【核心视觉：3D 夺框而出】人物主体必须具有强烈的“3D 破框而出 / 夺框而出 / 从画中跃出”半写实效果。人物上半身或全身位于中央主视觉区，形成明显前后景深。人物的衣袖、兵器、飘带、发须、坐骑、云雾或标志道具可突破中式边框，产生立体浮雕式出框感。视觉重点必须是人物，不得被文字、背景或装饰抢占。保持东方古典审美，不要现代游戏 UI，不要赛博朋克，不要西式奇幻盔甲，不要夸张动漫脸。【人物造型】根据 {argument name="人物名" default="潘金莲"} 的主流形象设计：保留最具辨识度的服饰、面部特征、姿态、道具与时代气质；神态需符合人物性格：威严、沉静、悲壮、儒雅、桀骜、仁厚或智谋，由人物设定决定；动作应具有叙事感，体现人物命运与人格力量；背景可淡化加入经典情节场景，但不得喧宾夺主。【版式结构】海报分为三大区域：一、顶部标题区：主标题：{argument name="人物名" default="潘金莲"}（{拼音}），大字号 MBTI：{MBTI 类型}，英文称号：{MBTI 英文称号}，中文人格标签：{中文人格标签}，使用传统窗棂 / 格栅边框包裹标题区。二、中部主视觉区：人物占画面核心位置，3D 夺框而出效果最明显，水墨淡彩渲染，背景融入人物代表性故事元素。三、底部信息区：设计为 4 个整齐模块，像高级国风 MBTI 信息图。模块一｜人物介绍，模块二｜性格特质，模块三｜经典语录，模块四｜人物档案。【色彩】主色：宣纸米白、淡墨灰、朱砂红、沉金色。辅色根据人物气质调整。色彩克制，高级，不艳俗。

Dark Fantasy Ponyo Warrior Poster

Create a vertical dark fantasy anime key visual poster featuring an intense close-up portrait of {argument name="character name" default="Ponyo"}, a youthful androgynous warrior with pale warm skin, wet-looking black hair strands across the face, and piercing amber eyes staring directly at the viewer from under a massive ornate bird skull or raven-like metallic helmet. The helmet and shoulder armor are made of layered feather-shaped bronze and dark gold plates, with sharp beak forms, scratched engraved texture, tiny holes, and glowing ember-orange highlights; include one vivid red gem-like eye set into the upper bird mask. Use dramatic low-key lighting with black background, molten gold reflections, smoky orange rim light, and ultra-detailed painterly brushwork, creating a moody cinematic atmosphere. The composition is tightly cropped: the face fills the center, the helmet dominates the top and right side, claw-like feather armor crosses the lower foreground, and the bottom center contains the title text {argument name="title text" default="PONYO"} in a glowing pale-gold sharp gothic fantasy font with angular serifs. Use a 9:16 portrait canvas, high contrast, intricate textures, realistic anime illustration style, no border, no watermark, no extra text.

Ecosystem trophic levels infographic

Create a detailed infographic for {argument name="audience" default="college students"} on trophic levels and energy transfer in ecosystems. The infographic should feature an ecological pyramid (energy or biomass), with definitions of producers, primary, secondary, and tertiary consumers, and

Urban Film Camera Portrait

Create a hyper-realistic vertical street-fashion portrait of {argument name="character description" default="a young East Asian woman with long dark wavy hair"} leaning sideways against a textured concrete urban wall covered with faded graffiti, peeling paint, stains, and worn posters. She is full-body in frame, standing casually with one leg straight and the other knee bent, the sole of one white sneaker pressed against the wall. She holds {argument name="camera type" default="a silver-and-black vintage film camera with a large lens"} in both hands at chest height, fingers adjusting the lens, with a focused yet relaxed pose and her head slightly tilted downward toward the camera. Outfit: oversized medium-blue denim jacket worn open, black cropped top, high-waisted loose black jeans, white chunky sneakers, and a small simple necklace. Use natural daylight, soft overcast shadows, shallow depth of field, realistic skin and fabric textures, muted urban color grading, documentary street photography feel, 35mm lens perspective, vertical 2:3 composition. Keep the background wall dominant and gritty, with no readable prominent text, no watermark, no extra people, and no stylized illustration effects.

$Top-down cinematic surreal portrait with shadow mapping — 5.0_UltraDetail · 3:4 · High-Fashion Cinematic Surrealism · Anatomical_Identity_Lock · {argument name=$

Top-down cinematic surreal portrait with shadow mapping

5.0_UltraDetail · 3:4 · High-Fashion Cinematic Surrealism · Anatomical_Identity_Lock · {argument name="identity" default="Ana de Armas"} · Hazel_Green_Eyes, Soft_Nose_Structure, Lips · Symmetrical_Proportional_Integrity · Soulful_Deep_Gaze · Warm_Olive_Porcelain · Radiant_Luminous · Subtle_Freckle_Hint · Minimalist_Bare_Aesthetic · Rich_Dark_Brunette · Sleek_Pulled_Back · Wet_Look_Texture · Upper_Torso_Facial_Focus · Bare_Shoulders_Exposed · Reclined_Elegance · 90_Degree_Top_Down_Overhead · Soft_Focus_Expressive · Surreal_Dreamy · Soft_Direct_Natural_Sunlight · Vertical_Artistic, Gridded_Mesh · Facial_Planes, Neck, Shoulders · Low_Soft_Diffused · Warm_Cinematic_Atmospheric · Earth_Tone_Naturalistic · Intimacy_Allure

Cinematic 3x2 storyboard grid from a single image reference

Use the uploaded photograph as the only visual reference. The person’s identity must be preserved with maximum accuracy: face, facial features, age, gender, body proportions, and overall appearance must remain unchanged. Do not invent or add anything that does not exist in the original image. Step 1: Detailed visual analysis of the source image First, perform a careful visual analysis of the uploaded image, including: Who is in the image (person, number of people, position in frame) Body pose and direction of gaze Facial expression and emotional mood Clothing and accessories Lighting conditions, time of day, color temperature Environment, background, and depth of space Overall emotional tone of the scene Step 2: Cinematic 3×2 storyboard grid After the analysis, create a cinematic 3×2 grid (6 frames) from the single image, as if it were a sequence of shots from a film. Global requirements for the entire grid: Format: one image containing a 3×2 grid All frames must be numbered 1–6, left to right, top to bottom Visual style: realistic, cinematic, non-illustrative One consistent character and environment with logical continuity Each frame must differ by pose, camera angle, or camera distance The sequence should feel like time is passing and the scene is developing No facial distortion, no change in identity or appearance Frame descriptions: Frame 1 (No. 1) Wide establishing shot. The camera is farthest from the subject, showing the full environment and context. The person feels like part of the surrounding space. Frame 2 (No. 2) Medium shot. The camera moves closer. The pose changes slightly, revealing inner emotion or state of mind. Frame 3 (No. 3) Low-angle or side-angle shot. Adds drama or tension, emphasizing body shape and perspective. Frame 4 (No. 4) Close-up or medium close-up. Focus on the face, eyes, and emotion. Fine details are clearly visible. Frame 5 (No. 5) Dynamic angle: diagonal composition or camera movement. The pose changes the most, creating a sense of action or momentum. Frame 6 (No. 6) Final shot. Calm, reflective, or emotionally resolved. The camera may be closer or farther, but the frame feels like a conclusion. Lighting & cinematic consistency: Lighting must remain logically consistent across all frames, as if filmed in one continuous scene. Depth of field, lighting, and color grading should reinforce a cinematic look. Final result: The output should resemble a professional cinematic storyboard, captured in a single take and location, with strong realism and narrative flow.