The Only Nano Banana 2 Prompting Guide You’ll
Ever Need
(This blog is co-written by 2 folks: one who runs ads for living and one who's been building and tuning models since pre-GPT era)
At Chromatic, we use different AI models, tune them to help brands, marketers and founder to make videos using AI. We have spent past 2 weeks testing Nano Banana 2 and are writing our observations.
Later we'll also show you how we take those same images and turn them into full video ads inside Chromatic, but first - let’s make you dangerous with Nano Banana 2
The Rules We Use Every Single Day
Thinking model - Nano banana 2 is a thinking model - i.e. it understand the natural sentances better. Write in full sentences - like you’re talking to a talented photographer.
Context - Nano Banana 2 understands context, try sharing your brand colours (yes hexes) and it will almost accurately capture them.
Consistency - While making screens for a reel, re-use the previous frames to maintian the visual consistency. Lock the important stuff (face details, exact colors, fonts, logo placement) inside the prompt itself.
Tags - Model supports " " tags. If you need to include any text or any specific style, try writing those words under " " tags, and model will pick it up as it is needed or imgined.
Editing - If you have the 90% correct image, use that image and edit. The model understands what you're talking about and will figure out the correct image.
Base Prompt
Your Communication Style
Be direct and confident:
✓ "Here are 5 gym selfie prompts optimized for realistic smartphone photography"
✗ "I've created some prompts that might work for gym photos"
Act as expert photographer:
✓ "I'm capturing a post-workout moment with natural overhead gym lighting"
✗ "This prompt includes gym lighting specifications"
Guide efficiently:
✓ "Copy the JSON into Nano Banana and generate"
✗ "So what you'll need to do is first copy the entire JSON structure..."
Example Prompts for Reference
—————————————————————————————
Example 1: Gym Selfie
{ "subject": { "description": "A young woman sitting on yoga mat, wiping sweat with towel, holding water bottle", "mirror_rules": "N/A - direct gym photo", "age": "late 20s", "expression": "accomplished, slight breathlessness, confident smile", "hair": { "color": "blonde with highlights", "style": "high ponytail, slightly messy with flyaways from workout" }, "clothing": { "top": { "type": "sports bra", "color": "dusty rose pink", "details": "medium support, strappy back detail, moisture visible from sweat" }, "bottom": { "type": "high-waisted leggings", "color": "black with mesh panels", "details": "ankle length, mesh cutouts on calves, compression fit" } }, "face": { "preserve_original": true, "makeup": "minimal, dewy from workout, natural flushed cheeks, no eye makeup" } }, "accessories": { "headwear": { "type": "none", "details": "hair pulled back in scrunchie" }, "jewelry": { "earrings": "small diamond studs", "necklace": "none", "wrist": "rose gold fitness tracker, black hair ties on wrist", "rings": "none" }, "device": { "type": "smartphone", "details": "propped against dumbbell, recording workout selfie" }, "prop": { "type": "insulated water bottle", "details": "matte black 32oz bottle with motivational quote sticker, condensation visible" } }, "photography": { "camera_style": "gym selfie aesthetic, smartphone front camera", "angle": "slightly above eye level, sitting position", "shot_type": "full upper body and crossed legs, centered composition", "aspect_ratio": "9:16 vertical", "texture": "crisp detail, bright gym lighting, energetic feel" }, "background": { "setting": "modern gym studio", "wall_color": "light gray with motivational mural", "elements": [ "purple yoga mat laid out", "set of dumbbells scattered nearby", "white towel draped over shoulder", "blurred gym equipment in background", "large mirror reflecting back wall", "resistance bands coiled on floor" ], "atmosphere": "energetic, accomplished, health-focused", "lighting": "bright overhead LED gym lighting, even coverage" } }
5 Real Prompts We Use + Why I Wrote Them That Way
Skincare & Beauty UGC
[Age]-year-old [ethnicity] woman taking a natural morning mirror selfie in a bright bathroom. She’s applying [Brand] [product type] to her cheek with her ring finger while holding her phone in her other hand. Soft, real expression, slightly messy hair, minimal makeup. Background: lived-in bathroom with small details like towels, candles, and counter items. Soft natural daylight. Mirror rule: ignore physics and keep all text forward and readable. 9:16 vertical, iPhone mirror selfie, realistic skin texture.
Why This Works
Mirror selfies = UGC trust signal (humans instantly read it as real).
Ring-finger application anchors it to skincare routines consumers recognize.
Messy hair + minimal makeup kills the “AI-perfect face” look.
Lived-in bathroom details add subconscious realism.
Mirror-rule prevents reversed text, the #1 giveaway of AI images.
Fashion & AI Photoshoot
Why This Works
3. App Store / Phone-in-Hand
{
"subject": {
"description": "A young woman sitting comfortably on a soft beige couch, holding her phone in one hand and smiling naturally",
"age": "young adult",
"expression": "playful, nose scrunched, softly biting the straw of an iced green drink",
"hair": {
"color": "brown",
"style": "long straight hair falling over shoulders"
},
"clothing": {
"top": {
"type": "ribbed knit cami top",
"color": "white",
"details": "cropped fit, thin straps, small dainty bow at neckline"
},
"bottom": {
"type": "denim jeans",
"color": "light wash blue",
"details": "relaxed fit, visible button fly"
}
},
"face": {
"preserve_original": true,
"makeup": "natural sunkissed look, glowing skin, nude glossy lips"
}
},
"accessories": {
"headwear": {
"type": "olive green baseball cap",
"details": "white NY logo embroidery, silver over-ear headphones worn over the cap"
},
"jewelry": {
"earrings": "large gold hoop earrings",
"necklace": "thin gold chain with cross pendant",
"wrist": "gold bangles and bracelets mixed",
"rings": "multiple gold rings"
},
"device": {
"type": "smartphone",
"details": "white case with pink floral pattern",
"pose": "held up casually in one hand like in the tagged reference"
},
"prop": {
"type": "iced beverage",
"details": "plastic cup with iced matcha latte and green straw"
}
},
"photography": {
"camera_style": "natural lifestyle photography, iPhone aesthetic",
"angle": "seated eye-level angle, not mirror selfie",
"shot_type": "mid-shot showing torso and couch, relaxed posture",
"aspect_ratio": "9:16 vertical",
"texture": "sharp focus, soft natural daylight, warm cozy tones"
},
"background": {
"setting": "bright cozy living room corner",
"elements": [
"large window with soft daylight",
"beige textured sofa",
"neutral throw blanket or pillow"
],
"atmosphere": "warm, relaxed, candid lifestyle moment",
"lighting": "soft natural morning light"
}
}
Why This Works
Real hand holding a real phone beats mockups by a mile in trust.
Readable UI is critical—no glare, no distortions, no fake “overlays.”
Defined home background adds lifestyle relatability.
Natural posture kills any “brand ad” stiffness.
Vertical 9:16 is exactly how App Store promo videos and TikToks are shot.
Fitness & Supplements UGC
[Age]-year-old [ethnicity] woman recording a raw front-camera UGC video right after a workout. She’s holding a [Brand] [supplement/protein shaker] up to the camera while talking about it. Post-workout glow: flushed cheeks, light sweat, hair in a messy ponytail. Wearing simple gym fit: sports bra and leggings. Background: real gym with weights, mirrors, people out of focus. 9:16 vertical, iPhone front camera texture, authentic movement and gestures.
Why This Works
Talking-to-camera front cam = UGC authenticity (platforms reward it).
Post-workout sweat acts as believable proof-of-effort.
Shaker close to lens mimics real creator behavior.
Background people + gym clutter make it feel like a real location.
Hand gestures + micro-motion remove all AI stiffness.
5. Illustration / Pixar-Style Product Moment
Single frame from a Pixar-style short film featuring a [Age]-year-old [ethnicity] character using [Brand] [product] in a cozy home setting. Warm, emotional lighting, expressive eyes, soft textures, slightly stylized but grounded. Background: night-time home environment with soft lamps, subtle clutter. Style inspired by Bao / Soul, 9:16 cinematic, high-quality render.
Why This Works
Pixar style = universally recognizable, emotionally sticky.
Expressive eyes carry storytelling instantly.
Warm lamp light + night setting add comfort & relatability.
Slight clutter prevents the “sterile CG look.”
9:16 cinematic framing makes it feel like a movie still, not an ad.
The truth about where this all ends up
Writing killer prompts is step one. Step two is turning these stills into full 15–60 second reels with custom voiceovers, lip-sync, music sync, and perfect brand consistency - in under 20 minutes instead of 4-5 hours.
That’s exactly what we built Chromatic for. We fine-tuned a mix of open-source models (Flux, Qwen, Llama-3.2, etc.) + our own custom video models trained on thousands of high-ROAS reels.
Drop in your Nano Banana hero shots (or a raw script), pick your voice (we have native accents in 30+ languages), and get 10–50 finished video variations instantly.
If you’re a founder, marketer, or brand who’s tired of the “4-second janky clip” tools, come see the difference.
Book a 15-minute call - we’ll take one of the prompts above, generate it live, and turn it into a finished reel while we chat.
→ https://cal.com/chromatic/demo
See you inside,
The Chromatic co-founders
(we still write prompts for fun on weekends)