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.

Cozy Christmas Market Portrait with Identity Preservation — AI Image Template for nano-banana-2

Minimalist Tech Advertisement Poster

A clean tech advertisement poster. A stylish young woman in a white minimalist outfit tilts her head with eyes closed enjoying music beside a giant white wireless earbud case 2.5x her height open and glowing softly, "{argument name="engraved text" default="AURA"}" engraved on the case lid in silver. Pure clean white background with subtle soft shadows and faint sound wave lines. Ultra minimal thin sans-serif typography "{argument name="background font" default="AURA"}" in light grey filling the background. Tagline bottom: "{argument name="tagline" default="Hear only what matters."}" Small text top-right corner reads "Designed with GPT Image 2" in grey. Photorealistic, Apple-style minimal tech commercial, soft diffused white studio lighting.

Creepy VHS Bedroom Doorway Figure

Create a creepy found-footage still from a degraded 1990s VHS home video, showing a dark messy bedroom at night viewed from a low handheld camera angle. The room has dim reddish-brown walls, heavy black shadows, a white metal bed frame and rumpled bed on the left, a few indistinct posters on the wall, and an open wooden door on the right with hanging fabric or clothing. In the center doorway stands {argument name="subject" default="a motionless humanoid figure"} wearing {argument name="costume" default="a pale rabbit-eared hood or bunny mask silhouette"}, a patterned light jacket, dark high-waisted pants, and small pale shoes; the face is deliberately obscured by a flat rectangular censor-like blur, making the figure feel anonymous and unnatural. Use {argument name="lighting" default="very low light with weak camera flash falloff"}, muddy colors, crushed blacks, soft focus, film grain, analog scanlines, chromatic noise, slight lens distortion, vignette, and a black VHS border around the frame. The composition should feel accidental, eerie, and documentary rather than cinematic, like a single unsettling frame from a lost tape, with the doorway figure centered but partially swallowed by darkness.

Three-Panel Fashion Campaign

Ultra-realistic Hollywood male model with a stylish beard and confident masculine aura, perfectly consistent in every panel. Three-panel {argument name="style" default="fashion campaign"} showcasing: futuristic premium streetwear, monochrome high-fashion editorial styling, and luxury leather designer fashion. Bold creative backgrounds, dramatic studio lighting, fashion week atmosphere, premium textures, layered accessories, photorealistic details, cinematic editorial photography.

Photoreal ML Developer Desktop

A photorealistic macOS desktop screenshot of a machine learning engineer’s workspace at night, shown straight-on with a dark blue macOS menu bar and the dock visible along the bottom. The desktop contains exactly 2 main application windows side by side. On the left, a large Visual Studio Code window in dark theme occupies about two-thirds of the screen. The VS Code project is named "VISIONCLASSIFIER" in the Explorer sidebar, with a realistic Python ML folder tree including exactly 11 visible top-level or expanded items: .venv, data, raw, processed, images, notebooks, src, utils, config.yaml, requirements.txt, README.md. Inside notebooks, show exactly 2 visible files: 01_data_exploration.ipynb and 02_model_training.ipynb. Inside src, show a realistic ML code structure with dataset.py, transforms.py, models, resnet.py, train, engine.py, trainer.py, utils.py. The editor area has exactly 4 tabs open: trainer.py, engine.py, resnet.py, config.yaml. The active tab is trainer.py. Display clean, believable Python training code for a ResNet image classification pipeline, including a class Trainer, methods train(self) and train_epoch(self, epoch: int) -> Dict[str, float], references to self.cfg.training.epochs, train_metrics, val_metrics, scheduler.step, save_checkpoint, self.model.train(), batch["image"], batch["label"], optimizer.zero_grad, criterion, loss.backward, optimizer.step, accuracy(outputs, targets, topk=(1,))[0]. Make the code sharp but naturally screen-like, with line numbers visible around lines 24 to 52. At the bottom of the VS Code window, the integrated terminal is open on the TERMINAL tab and shows realistic training logs for exactly 4 epochs in view: Epoch 12/50, Epoch 13/50, Epoch 14/50, Epoch 15/50, each with train and val lines listing Loss, Acc@1, and Acc@5, plus a final line saying a new best checkpoint was saved. Keep the numbers plausible for a successful training run, with top-1 accuracy around 0.88 to 0.91 and top-5 around 0.97 to 0.98. Include the usual VS Code status bar along the bottom with Python environment details. On the right, place exactly 1 dark-themed web browser window showing a local dashboard at localhost:8000 with the page title "VisionClassifier | Dashboard" and the app header "VisionClassifier" plus subtitle "Image Classification Model". The dashboard contains exactly 3 stacked sections. The first section is "Model Overview" with exactly 4 metric cards: Top-1 Accuracy 91.23%, Top-5 Accuracy 98.30%, Total Parameters 23.51M, Model ResNet-50. The second section is "Recent Training" with a dark line chart of accuracy over 50 epochs, showing exactly 2 colored curves labeled Train (Top-1) and Val (Top-1), both rising quickly and stabilizing around the low 90s. The third section is "Confusion Matrix" showing a 10x10 heatmap with a bright diagonal and axes labeled True Label and Predicted Label. Use subtle reflections, crisp typography, realistic UI spacing, and believable screen glow. The macOS top menu bar should show common menus like Code, File, Edit, Selection, View, Go, Run, Terminal, Window, Help on the left and system icons with the time reading Tue May 13 9:41 AM on the right. The dock should contain many recognizable app icons and feel authentic but not distracting. Overall style: ultra-realistic screenshot, professional developer workstation, polished dark mode interfaces, no stylization, no illustration, indistinguishable from a real screen capture.

Handmade Collectible Male Doll

Use the uploaded photo as the sole reference for identity. Maintain maximum facial resemblance, preserving facial features, proportions, expression, hairstyle, skin tone, and natural asymmetries with extreme accuracy. Create an adorable handmade premium collectible male doll with a slightly oversized head, a small slender body, soft felt and fabric textures, realistic 3D facial details, lifelike glass eyes, and handcrafted stitching. The tiny doll tightly hugs a giant {argument name="candy bar" default="KitKat bar"} almost as large as himself, with several bite marks already taken from it. He wears a playful, satisfied smile with {argument name="detail" default="chocolate smudges"} around his lips, cheeks, and fingertips. A few drops of melted chocolate are scattered on the floor beneath him. A giant human finger gently lifts him by the back of his shirt collar, but he stubbornly refuses to let go of the KitKat, creating a humorous and adorable scene. Emphasize dramatic size contrast, warm bright lighting, a clean minimalist background, premium diorama craftsmanship, macro photography, shallow depth of field, ultra-realistic textures, and exceptional facial fidelity to the uploaded reference photo.

High-Fidelity Portrait with Extreme Identity Mapping and Technical Rib-Knit Texture

[Header] (9:16) Raw high-fidelity photograph, iPhone 17 Pro sensor simulation, indoor ambient lighting with soft front-fill flash, zero bokeh, SHARP focus from the foreground subject to the background tiled wall, f/5.6 aperture for structural depth, authentic digital grain. [Subject & Identity Inheritance] Identity Mapping: Absolute physical inheritance from Reference Image A. The generated subject must inherit the exact facial geometry, specific eye shape, lip volume, chin structure, and all original hair characteristics (texture, length, volume, and part) directly from Image A without manual descriptor intervention. Bio-Fidelity: Detailed skin physics including micro-pores, satin-finish hydration, and visible fine vellus hair along the jawline. High-definition rendering of the shoulders and neck architecture. Expression: Magnetic presence; inheriting the self-assured gaze and facial resting-state directly from Image A, looking back over the shoulder. [Outfit & Physicality] Technical Description: High-impact technical rib-knit body-conscious set in muted {argument name="outfit color" default="earth-tone"} horizontal stripes (terracotta, tan, and beige). Textile Geometry: Off-the-shoulder neckline architecture with full-length compression-fit sleeves featuring technical distressed/frayed cuff detailing. Surface Physics: High-tensile material-to-skin surface compression. The textile must exhibit realistic physical tension lines as it contours the anatomical gluteal proportions, pelvic symmetry, and an emphasized waist-to-hip ratio. Physicality: Athletic-to-lean build; extreme torso torsion and symmetrical proximal limb geometry. [Pose & Composition] Geometry: Extreme S-curve torsion pose. The subject is standing in a rear-profile perspective, rotating her upper torso 180 degrees to face the camera directly. Interaction: Left hand is subtly raised, fingers interacting with a hair strand near the shoulder, showing realistic finger-joint articulation and skin texture. Framing: Medium shot, vertical focus. The subject is positioned on the left side of the frame, angled to lead the viewer’s eye toward the background hallway. [Environment & Lighting] Atmosphere: Modern domestic or hotel interior hallway. Interior Details: Foreground features a high-detail tiled wall with horizontal tan/beige rectangular porcelain tiles and precise grout lines. Background includes a dark-wood door with a white technical signage card. Neutral grey stone-tile flooring with realistic specular reflections. Lighting: Diffused 3000K warm indoor light supplemented by a soft front-fill flash. This creates brilliant illumination on the subject’s skin and the rib-knit texture, while casting clean, defined shadows on the tiled background. [Failure Prevention Rule] Command: "Identity Mapping: Inherit all facial and hair traits from Reference Image A onto the subject." Use "Technical rib-knit body-conscious set" and "Anatomical gluteal proportions" to ensure high-fidelity

$Cinematic Portrait of Iggy Azalea in a Low-Light Arena Setting — { “meta”: { “quality”: “ultra_photorealistic, raw style, 8k”, “camera”: “A profession$

Cinematic Portrait of Iggy Azalea in a Low-Light Arena Setting

{ “meta”: { “quality”: “ultra_photorealistic, raw style, 8k”, “camera”: “A professional portrait setup with an 85mm lens, capturing an intimate, close-up composition.”, “lighting”: “Low-light, moody purple and blue ambient lighting from overhead and below, casting atmospheric shadows, with focused light on the subject’s face.”, “style”: “cinematic portrait, high-fashion editorial, close-up focus”, “aspect_ratio”: “9:16” }, “scene”: { “location”: “Seated intimately in an arena seat with rows of stacked purple-blue plastic seats in the background, dimly lit and cold.”, “atmosphere”: “Mysterious, cool, and confident.” }, “subject”: { “gender”: “female”, “name”: “Iggy Azalea”, “body”: { “type”: “Realistic, naturally proportioned fit figure, shown in an upper-body close-up.” }, “face”: { “features”: “Iggy Azalea’s distinct facial features, with her characteristic platinum blonde hair styled in the short, blunt bob with straight bangs (fringe). Bold makeup with dark, defined eyes and deep red lipstick.”, “expression”: “Confident and intense, with a direct and piercing gaze toward the camera.” }, “outfit”: { “description”: “Black velvet off-the-shoulder corset-style dress with a lace-trimmed sweetheart neckline and long bell sleeves. The silver cross pendant necklace is present. The focus is on the upper body.”, “fit”: “Tailored, bold, and form-fitting.”, “accessory”: “None.” }, “legwear”: { “description”: “Seated with upper legs together, showing the tops of black thigh-high stockings with a fishnet pattern that extend up her thighs, disappearing beneath the dress hem. The tops of the stockings are finished with a clean, simple, integrated black band, completely smooth and presenting a sleek, seamless look against her upper thigh. The focus is on the proximity of the socks to the hem, not the full leg length. There are absolutely no visible complex hardware, external straps, or clips.”, “fit”: “A secure, sleek transition.” }, “pose”: “Sitting centered on an arena seat with her legs together, hands resting on the seat beside her. The pose is symmetrical and direct, creating a tighter framing. The focus is sharp on the face, shoulders, and the transition of the thigh-high sock tops below the hem.” }, “composition”: “Close-up portrait framing, focusing on the face, shoulders, and upper thighs. Sharp focus on Iggy Azalea and the detailed textures of her clothing, especially the velvet, lace, and the intricate fishnet pattern. The purple and blue ambient lighting defines her features and the textures.”, “additional_details”: [ “The texture of the velvet dress is detailed and clear.”, “The intricate details of the lace trim are sharp.”, “The texture of the fishnet pattern on the new thigh-high socks is clear and detailed.”, “The silver cross necklace is cle” ] }

Dramatic Devil Costume Portrait Prompt (JSON)

{ "scene": "Dramatic evening scene of a woman in a devil costume sitting on the corner ledge of a burning brick building.", "subject": { "character": "Young woman dressed as a devil, looking remarkably serene amidst a roaring fire.", "face": { "structure": "Soft features, defined jawline, softly smiling.", "skin": "Smooth, intensely illuminated by warm firelight.", "eyes": { "shape": "Almond.", "color": "Dark.", "expression": "Closed or looking down peacefully." }, "mouth": { "lips": "Closed, gentle and subtle smile." }, "makeup": "Natural look enhanced by striking warm highlights from the flames." }, "hair": { "color": "Black.", "length": "Shoulder-length with straight front bangs.", "texture": "Straight.", "style": "Worn down.", "shine": "High reflective shine catching the orange glow of the fire." }, "accessories": { "headwear": "Shiny red devil horns attached to a thin headband.", "prop": "Long black pitchfork with a red trident tip held across her lap.", "tail": "Red devil tail with a pointed arrow tip hanging down the side of the building." } }, "pose": { "overall": "Sitting calmly on the absolute corner edge of a roof, legs dangling, holding a pitchfork.", "position": { "base": "Sitting on the white concrete ledge.", "orientation": "Body angled slightly to the right, facing forward." }, "torso": { "direction": "Forward.", "posture": "Relaxed, upright." }, "arms": { "position": "Resting across her lap, hands loosely gripping the handle of the pitchfork.", "other": "Elbows slightly bent and relaxed." }, "legs": { "position": "Dangling down the side of the building, right leg crossed gracefully over the left ankle.", "visible": "Exposed from the mid-thigh down to the feet." }, "head": { "turn": "Tilted slightly downward.", "expression": "Peaceful, serene, contrasting with the chaotic background." } }, "outfit": { "dress": { "type": "Mini dress.", "color": "Bright red.", "style": "Long-sleeve, V-neck, flared skirt.", "details": { "material": "Velvet or velour-like texture with a visible front zipper or seam.", "fit": "Form-fitting bodice." } }, "shoes": { "type": "Heels.", "color": "Black.", "style": "Chunky heel, closed round toe, ankle strap (Mary Jane style).", "details": { "design": "Classic, slightly vintage aesthetic." } } }, "body": { "type": "Slim.", "skin": "Warm tone enhanced by the heavy ambient firelight.", "midriff": "Covered.", "moles": "" }, "environment": { "location": "Corner ledge of a flat roof on a red brick building.", "foreground": { "building": "Exterior walls made

Gym Besties Mirror Selfie

"title": "", "caption": "Strong together, glowing forever 💪✨ Fitness is better with besties by your side.", "description": "A powerful mirror selfie of three confident friends standing close together in a gym after their workout session. Their smiles reflect friendship, strength, and self-love. The gym equipment in the background adds an authentic fitness atmosphere.", "location": { "place": "Modern Gym Studio", "environment": "Indoor fitness space with weights and workout machines" }, "subjects": { "count": 3, "gender": "Female", "pose": "Standing close together, mirror selfie pose", "expression": "Soft smiles, relaxed and confident" }, "outfits": [ { "color": "Black", "style": "Sports bra and fitted shorts", "vibe": "Bold and strong" }, { "color": "Beige", "style": "Minimal sports set", "vibe": "Soft and aesthetic" }, { "color": "Olive Green", "style": "Athletic coordinated set", "vibe": "Natural and sporty" } ], "lighting": "Bright indoor lighting with natural gym ambiance", "mood": "Energetic, Happy, Confident", "theme": "Fitness, Friendship, Self-confidence", "hashtags": [ "#GymBesties", "#StrongGirls", "#FitnessVibes", "#WorkoutGlow", "#Confidence" ] }