AI Image-Generator Prompts Brief

Unfovi 7-Pack Makeup Sponges (Soft Puppy E1075) — 7 paired prompts + post-prod specs

ASIN B0F912WG5P · amazon.com · brief date 2026-05-25

Paired Nano Banana 2 + GPT-Image prompts · Two-part principle: AI for the photo, humans add headlines & badges in post

1 · Overview

This brief is the bridge from the image audit + A+ Content brief into actual rendered images. Each entry below has:

  • Reference image (the current state, embedded from the product folder)
  • Nano Banana prompt — natural-language descriptive prompt for Gemini 3.1 Flash Image (AI Studio, "Nano Banana" model). Best for photography + lifestyle + product-in-context.
  • GPT-Image prompt — structured prompt for OpenAI's image generator. Best for graphic-design compositions (callouts, comparison charts, infographics).
  • Post-production overlay — headline, badge text, alt text. Added after the AI render in Canva or Photoshop. Two-part principle: AI for the photo, humans add headlines & badges in post.
  • Filename — drop the final composite into the product folder using this name.

Run on: Nano Banana 2 (gemini-3.1-flash-image-preview) at 2K square aspect. GPT-Image at 1024×1024. Auto-driveable via Claude in Chrome MCP if requested.

What this brief does NOT cover

  • Slot 1 hero refresh (diagonal isometric). Designer task — repositioning 7 existing sponges on a diagonal axis + micro-shadow grounding is a Photoshop composite, not an AI render.
  • Slot 7 comparison chart. Native designer task — table layout + checkmarks + brand mark. AI image generators can do passable comparison charts but the typography hygiene is fragile.
  • Slot 3 + Slot 4. Keep as-is per the audit.
  • A+ Module 4 (comparison) + Module 6 (Q&A). Both are native Amazon module types — no external image needed.

2 · Image prompts (paired Nano Banana + GPT-Image)

1. Slot 2 keystone — Latex-Free objection pre-empt (rebuild)

Current slot 2 scores 37/80 (Generic tier). Mechanism #1 (category shortcut) is replaced with mechanism #3 (objection pre-empt).

Render size2000×2000 px square (Amazon zoom-eligible)

Current state (reference)

Nano Banana 2 prompt (Gemini 3.1 Flash Image)

A premium beauty product photograph on a soft lavender-to-cream gradient background. Center-right: a single ultra-soft lavender-pink teardrop makeup sponge, pristine, with a faint cast shadow grounding it on a smooth surface. Center-left: a circular zoom-in inset showing extreme macro detail of the sponge's interior pore structure — fine, tight, even pores. Top-left corner: a real Unfovi product box with floral pattern (cardboard sleeve packaging, soft puppy motif, lavender/pink/yellow palette). Bottom-right corner: a small cluster of three additional teardrop sponges in soft pink, mint green, and pale yellow, slightly out of focus, suggesting the rest of the 7-pack. Lighting: bright, diffused, north-window daylight, no harsh shadows. Style: editorial cosmetic still life, magazine-grade, very soft pastel palette dominated by lavender, pink, and warm white. No on-image text — the headline and badges will be added in post-production.

GPT-Image prompt (OpenAI)

Beauty product hero composition, 1:1 aspect ratio, soft pastel lavender + warm white background. Subject 1 (center-right, 45% of frame): single hyperreal teardrop makeup sponge, lavender-pink color, soft suede-like foam texture, pristine, faint contact shadow beneath. Subject 2 (center-left, circular inset 30% of frame): extreme macro zoom showing the sponge's internal fine-pore structure, with thin label arrows. Subject 3 (top-left, 15%): cardboard product packaging box in matching pastel palette, floral pattern, small puppy mascot. Subject 4 (bottom-right, 10%): three smaller teardrop sponges in pink, mint, and yellow, soft focus. Lighting: bright diffused daylight, no hard shadows. Mood: clean, premium, sensitive-skin-safe. Reserve a clear empty band at the top of the frame for headline overlay. No text in the image.

Post-production overlay (Canva / Photoshop)

  • TOP HEADLINE (post-production, 80px+ Serif): "Latex-Free • Won't Drink Your Foundation"
  • SUBLINE (40px Sans, below headline): "100% non-latex polyurethane foam. Hypoallergenic. Micro-pore structure for less absorption."
  • BOTTOM-RIGHT BADGE TRIO (pill-shape, white background): • Latex-Free • Hypoallergenic • 7-Month Supply
  • MACRO INSET LABEL: arrow pointing into the macro circle with text "Micro-fine pores — holds less foundation"
  • FILENAME after composite: Images/slot2_final.jpg
  • ALT TEXT (≤100 chars): "Latex-free Unfovi makeup sponge with micro-pore structure - hypoallergenic foundation blender for sensitive skin"

2. Slot 5 — Feature/benefit swap (replace duplicate)

Current slot 5 duplicates slot 3's anatomy callouts. Keep the model + sponge-to-cheek scene; swap the callouts to the three material-and-care benefits.

Render size2000×2000 px square

Current state (reference)

Nano Banana 2 prompt (Gemini 3.1 Flash Image)

A young woman, mid-20s, light makeup, looking just off-camera with a soft natural smile, holding a soft pink teardrop makeup sponge gently against her cheekbone. Soft side-lighting from a window, slight rim light catching her hair. Background: out-of-focus soft pastel pink with a hint of plant foliage on the far right. Model has clear glowing skin, no visible makeup application stage shown — finished look. Lavender or pale pink top visible at shoulder line. Composition: model occupies right two-thirds of frame; left third is clean negative space for callouts. Style: natural beauty editorial, magazine-quality, soft pastel palette, NOT a high-glamour fashion shot. No on-image text.

GPT-Image prompt (OpenAI)

Beauty editorial portrait, 1:1 aspect ratio. Subject: young woman 22-28, soft natural makeup, light skin tone or warm tan, holding a pink teardrop makeup sponge against her right cheekbone, gentle smile, looking just off-camera. Lighting: soft window light from camera left, warm rim from camera right, even fill, no harsh shadows. Background: out-of-focus soft pastel pink + warm white, hint of greenery far right corner. Composition: model in right 2/3 of frame; left 1/3 is clean negative space reserved for callout labels (will be added in post). Mood: approachable, everyday-beauty, drugstore-real. No on-image text.

Post-production overlay (Canva / Photoshop)

  • TOP HEADLINE (post-production, 60px Serif): "Engineered for Your Skin"
  • LEFT-SIDE CALLOUTS (3 stacked, with arrows pointing to model/sponge): "Non-latex polyurethane — sensitive-skin safe" · "Micro-pore structure — absorbs less foundation" · "Damp-and-go — 30-second prep"
  • FILENAME: Images/slot5_final.jpg
  • ALT TEXT: "Latex-free hypoallergenic makeup sponge with micro-pore structure for sensitive skin and quick prep"

3. Slot 6 — Proof-of-outcome reframe (move macro inset to slot 2; reframe this slot)

Macro pore visual moves to slot 2 (where it does more work). Slot 6 reframes around the aspirational endpoint.

Render size2000×2000 px square

Current state (reference)

Nano Banana 2 prompt (Gemini 3.1 Flash Image)

A clean, simple beauty image showing the difference a sponge-applied foundation makes. Left half of frame: a bare-skin forearm or back-of-hand, light skin tone, no makeup, natural texture visible. Right half: same forearm/hand area but with foundation perfectly blended in, no streaks, no patches, smooth even tone, slight luminous finish. Between them, a small teardrop pink makeup sponge resting on a clean surface. Background: soft warm-white. Lighting: even, soft, neutral daylight — both halves lit identically so the only visible difference is the foundation application. No on-image text. Composition: 60/40 split or full-width single-arm shot with subtle gradient transition. Looks editorial, not medical. NO claims about acne, scars, or skin conditions.

GPT-Image prompt (OpenAI)

Beauty product proof-of-outcome composition, 1:1 aspect ratio. Layout: horizontal split. Left half: bare forearm or back-of-hand of light-medium skin tone, no makeup, natural skin texture visible. Right half: same arm area with foundation evenly blended, smooth even tone, no streaks, healthy luminous finish. Center foreground: small pink teardrop makeup sponge on a clean surface, slight contact shadow. Background: soft warm-white, very subtle gradient. Lighting: identical on both halves — soft diffused daylight, no shadows. Mood: clean, real, achievable everyday makeup look. No on-image text. Strictly cosmetic positioning — not medical, not a skin-condition treatment.

Post-production overlay (Canva / Photoshop)

  • TOP HEADLINE (post-production, 60px Serif): "Bare to Blended. Effortless."
  • SUBLINE (32px Sans): "Streak-free finish for liquid foundation, BB cream, and concealer."
  • OPTIONAL LABEL on the left half: "Bare" · on the right half: "Sponge-applied"
  • FILENAME: Images/slot6_final.jpg
  • ALT TEXT: "Bare skin versus sponge-applied foundation showing streak-free blending finish with Unfovi makeup sponge"

4. A+ Module 1 — Premium Hero (3000×600 wide canvas)

A+ Content is currently parked. This is the new module 1 hero — wide canvas Premium Hero, the brand-promise frame.

Render size3000×600 px (Premium Hero canvas)

Current state (reference)

(no current image — new module, building from brief)

Nano Banana 2 prompt (Gemini 3.1 Flash Image)

A wide cinematic beauty banner, 5:1 aspect ratio, soft pink-to-lavender gradient background. Center: a hand holding a single soft purple teardrop makeup sponge in mid-air, fingertips visible, frozen elegant motion. Far left: a clean stack of 7 teardrop makeup sponges in different pastel colors (yellow, mint, lavender, marbled-purple, light pink, mid pink, mauve) laid out in a soft fan pattern. Far right: clean empty space reserved for logo and tagline placement. Lighting: bright, airy, soft window light, no harsh shadows. Style: cosmetic brand editorial, magazine-grade. Palette: pastel pink, lavender, warm white, cream. NO text in the image — typography added in post.

GPT-Image prompt (OpenAI)

Beauty brand hero banner, 5:1 aspect ratio (3000×600 px). Left third: 7 pastel teardrop makeup sponges arranged in a soft fan layout (yellow, mint green, lavender, marbled purple, light pink, mid pink, mauve), clean even spacing, soft cast shadows. Center third: a feminine hand from the bottom of the frame, holding a single lavender-purple teardrop sponge between thumb and forefinger, soft elegant grip. Right third: clean negative space for brand logo and tagline overlay. Background: warm pink-to-lavender gradient, very soft. Lighting: bright airy daylight, no hard shadows. Mood: drugstore-everyday premium. No on-image text.

Post-production overlay (Canva / Photoshop)

  • LEFT-ALIGNED HEADLINE (60-80px Serif): "Latex-Free Makeup Sponges. Drugstore Price."
  • SUBHEAD (32px Sans, below): "Seven hypoallergenic blending sponges. For everyday foundation, concealer, and powder."
  • RIGHT-ALIGNED Unfovi logotype + small tagline: "Everyday beauty, no compromise."
  • FILENAME: Images/aplus-module1-hero.jpg
  • ALT TEXT: "Unfovi 7-pack latex-free makeup sponges hero banner with hand holding lavender sponge - drugstore-priced beauty blender alternative"

5. A+ Module 2 — Material / safety deep-dive (970×600)

Latex-free risk-kill module with macro pore visual.

Render size970×600 px

Current state (reference)

(no current image — new module, building from brief)

Nano Banana 2 prompt (Gemini 3.1 Flash Image)

A two-panel beauty product image, 970×600 px, 16:10 aspect. Left 60% of frame: extreme macro zoom (close-up) of the inside surface of a pink makeup sponge showing the fine porous foam structure — even, tight, dense pores. Crisp focus, slight depth-of-field. Right 40% of frame: a single pink teardrop makeup sponge resting on a folded soft white cotton fabric, very soft natural lighting. Background: warm white. Composition: clean cosmetic editorial, premium feel. Palette: pink, white, cream. No on-image text.

GPT-Image prompt (OpenAI)

Beauty product material close-up, 16:10 aspect ratio. Left panel (60%): extreme macro of pink makeup sponge interior showing fine-pore polyurethane foam structure, sharp focus, slight depth blur on edges. Right panel (40%): single pink teardrop makeup sponge resting on folded soft white cotton, natural soft daylight, gentle shadow. Background warm white. Mood: clinical-meets-cosmetic, premium materials story. No on-image text.

Post-production overlay (Canva / Photoshop)

  • TOP HEADLINE (40px Serif): "Made for Sensitive Skin"
  • BODY TEXT (16px Sans, right panel): "100% non-latex polyurethane foam. Hypoallergenic. Dermatologically friendly."
  • MACRO ARROW LABELS (left panel): "Micro-fine pores" + "Less absorption"
  • FILENAME: Images/aplus-module2-material.jpg
  • ALT TEXT: "Macro view of micro-pore latex-free polyurethane foam interior of Unfovi makeup sponge for sensitive skin"

6. A+ Module 3 — Anatomy + use-case (970×600)

Three application surfaces × three face zones. Collapses what was slot 3 + slot 5.

Render size970×600 px

Current state (reference)

(no current image — new module, building from brief)

Nano Banana 2 prompt (Gemini 3.1 Flash Image)

A two-zone beauty editorial layout, 970×600 px (16:10). Left half: a young woman in soft natural makeup, looking slightly off-camera, holding a pink teardrop sponge to her cheekbone, gentle expression. Right half: clean white background with three numbered annotated diagrams of a teardrop makeup sponge — one highlighting the pointed tip, one highlighting the flat edge, one highlighting the rounded base — each with a thin dotted line connecting to a stylized face outline indicating the relevant face zone. Soft pastel palette overall. No on-image text in the AI render — labels added in post.

GPT-Image prompt (OpenAI)

Beauty editorial layout, 16:10 aspect ratio. Left panel (50%): young woman 24-28, soft natural makeup, light skin or warm tan, holding pink teardrop makeup sponge against her cheekbone, soft smile, looking off-camera. Soft window light. Right panel (50%): white background with three stacked annotated diagrams of teardrop makeup sponges, each highlighting a different edge (pointed tip / flat edge / rounded base), with thin dotted lines connecting each to a stylized minimalist face outline marker showing the corresponding face zone. Clean technical-but-warm illustration style. Mood: makeup masterclass. No on-image text.

Post-production overlay (Canva / Photoshop)

  • TOP HEADLINE (40px Serif): "Three Edges. One Sponge. Every Zone."
  • RIGHT-SIDE LABELS (3 stacked, 18px Sans): "1. Pointed Tip — under-eyes & nose" · "2. Flat Edge — contour & jawline" · "3. Rounded Base — full-face coverage"
  • FILENAME: Images/aplus-module3-anatomy.jpg
  • ALT TEXT: "Three application surfaces of teardrop makeup sponge - pointed tip flat edge rounded base for every face zone"

7. A+ Module 5 — Care & replacement cadence (970×600, 4-panel)

Four-panel care + value math module.

Render size970×600 px (split into 4 equal panels of 242×600)

Current state (reference)

(no current image — new module, building from brief)

Nano Banana 2 prompt (Gemini 3.1 Flash Image)

A clean four-panel beauty infographic layout, 970×600 px wide. Each panel has a soft pastel background and clean iconography. Panel 1 (rinse): a stylized water droplet icon hovering over a pink makeup sponge being gently squeezed under running water. Panel 2 (dry): a soft sun icon and a pink makeup sponge on a small wooden drying rack with air circulation lines. Panel 3 (replace monthly): a minimalist calendar icon with one date circled and a small pink makeup sponge beside it. Panel 4 (7-pack supply): a clean box icon with 7 small pastel sponges arrayed beside it. Lighting: soft, clean, uniform across all 4 panels. Palette: matching pastel pink and lavender across the panels. No on-image text — panel titles added in post.

GPT-Image prompt (OpenAI)

Infographic-style beauty care guide, 16:10 aspect ratio, 4 equal vertical panels. Panel 1: water droplet icon + pink sponge being squeezed under running water. Panel 2: soft sun icon + pink sponge on small drying rack. Panel 3: calendar icon with one date circled + pink sponge. Panel 4: open box icon + 7 small pastel sponges arrayed in a row. Soft pastel pink + lavender + warm white background, identical across all 4 panels. Clean minimalist illustration style. No on-image text.

Post-production overlay (Canva / Photoshop)

  • PANEL TITLES (post-production, 24px Sans bold below each panel): "1. Rinse" · "2. Dry" · "3. Replace monthly" · "4. 7-month supply"
  • PANEL CAPTIONS (14px Sans, one line under each title): "...with mild soap." · "Air-dries in 1 hour." · "For skin health & color performance." · "Always a clean sponge in your routine."
  • FILENAME: Images/aplus-module5-care.jpg
  • ALT TEXT: "Four-step care routine for Unfovi makeup sponges - rinse, dry, replace monthly, 7-month supply"

3 · QC checklist

QC checklist (every final composite)

  • 2000×2000 px (gallery slots) or 970×600 / 3000×600 px (A+ modules)
  • sRGB color profile · JPEG · ≤10 MB
  • Headline reads at 100×100 thumbnail (slot 2 priority)
  • All claims substantiated in bullets / description / A+ — no orphan claims
  • No competitor brand names, no banned superlatives ("best", "#1", "top-rated")
  • Filename matches the spec above (lowercase, hyphen-separated, no brand prefix)
  • Alt text added in Seller Central upload step
  • Mobile + desktop preview verified for A+ modules

4 · Auto-generation (optional)

If requested, this brief can drive Gemini / AI Studio in Chrome to auto-generate all seven renders. The flow:

  1. Navigate to aistudio.google.com in the user's main Chrome (via Claude in Chrome MCP).
  2. For each entry above, open a new chat, paste the Nano Banana prompt verbatim, set the model to gemini-3.1-flash-image-preview, resolution 2K, aspect 1:1 (or 5:1 for module 1, 16:10 for modules 2/3/5).
  3. Download each render to Images/ai-image--nano.jpg.
  4. Human-in-the-loop QC: review each render, request re-roll if pass-quality is below 7/10.
  5. Pass the raw renders to Canva/Photoshop for the post-production overlay (headlines, badges, labels).
  6. Save composited finals as Images/slot2_final.jpg, Images/slot5_final.jpg, etc.

Auto-generation is opt-in — requires Claude in Chrome MCP connected + user signed in to Google AI Studio. The default delivery is the brief above, run manually.