Welcome to the Nano-banana curated image gallery! 🤗

We have collected stunning images and prompts generated by Nano-banana in various task scenarios, comprehensively showcasing Google's unlimited possibilities in image generation and editing. We hope this helps you better understand Nano-banana. Let's unlock Nano-banana's multi-image fusion and creative editing power together! ✨

These cases mainly come from Twitter/X 🐦, Xiaohongshu 📕 and other self-media platforms.

If you like it, please ⭐ Star to bookmark it!

• Nov-26-2025: 6️⃣ Sixth repository update
• Sep-24-2025: 5️⃣ Fifth repository update
• Sep-18-2025: We released the Nano-consistent-150k dataset.
• Sep-16-2025: 4️⃣ Fourth repository update
• Sep-9-2025: 3️⃣ Third repository update
• Sep-3-2025: 2️⃣ Second repository update
• Aug-28-2025: 🎉 1️⃣ ${\color{red} First\ Awesome-Nano-Banana-images \ update!}$

• 🍌 Introduction
• 📰 News
• 📑 Menu
• 🍌 Nano Banana Pro Examples
  • Example 1: Ukiyoe Flash Card (by @MANISH1027512)
  • Example 2: Generate Image from Coordinates (by @TechieBySA)
  • Example 3: Character Cloning (by @tapehead_Lab)
  • Example 4: Generate Flowchart from Document (by @anderssandberg)
  • Example 5: Create PPT from Article (by @op7418)
  • Example 6: Character Deconstruction (by @cheerselflin)
  • Example 7: Behind the Scenes of Item Creation (by @ZHO_ZHO_ZHO)
  • Example 8: Children's Literacy Newsletter (by @lxfater)
  • Example 9: Generate Material Texture (by @someidesign)
  • Example 10: Add Giant Creature to City Image (by @AI_GIRL_DESIGN)
  • Example 11: Toy Disassembly Display (by @ZeroZ_JQ)
  • Example 12: Fluffy Plush Toy (by @toolfolio)
  • Example 13: Crystal Texture Emoji (by @ZHO_ZHO_ZHO)
  • Example 14: Fluffy Inflatable Toy (by @gizakdag)
  • Example 15: Hand-drawn Isometric View (by @AmirMushich)
  • Example 16: Reveal Behind-the-Scenes of Photo Creation (by @icreatelife)
  • Example 17: Estimate Age from Face (by @Samann_ai)
  • Example 18: Historical Newspaper (by @TechieBySA)
  • Example 19: Character Relationship Chart (by @KanaWorks_AI)
  • Example 20: Otome Game Setting Collection (by @KanaWorks_AI)
  • Example 21: Character Level Evolution (by @KanaWorks_AI)
  • Example 22: Recursive Image (by @goodside)
  • Example 23: Multi-Character Crossover Comic (by @canghecode)
  • Example 24: Coloring Figure Garage Kit (by @op7418)
  • Example 25: Golden Quote Card (by @stark_nico99)
  • Example 26: Qingming Shanghe Tu Style Image (by @dotey)
  • Example 27: Movie Storyboard Creation (by @jamesyeung18)
  • Example 28: Blackboard Chalk Drawing (by @TlanoAI)
  • Example 29: Miniature Self-Portrait (by @TechieBySA)
  • Example 30: Generate Biography from Wikipedia (by @chrisfirst)
  • Example 31: Stylized Map (by @Mr_AllenT)
• 🖼️ Nano Banana Examples
  • Case 1: Illustration to Figure（by @ZHO_ZHO_ZHO）
  • Case 2: Generate Ground View from Map Arrow（by @tokumin）
  • Case 3: Real World AR Information（by @bilawalsidhu）
  • Case 4: Extract 3D Buildings/Make Isometric Models（by @Zieeett）
  • Case 5: Photos of Yourself in Different Eras（by @AmirMushich）
  • Case 6: Multi-Reference Image Generation（by @MrDavids1）
  • Case 7: Automatic Photo Editing（by @op7418）
  • Case 8: Hand Drawing Controls Multi-Character Poses（by @op7418）
  • Case 9: Cross-View Image Generation（by @op7418）
  • Case 10: Custom Character Stickers（by @op7418）
  • Case 11: Anime to Real Coser（by @ZHO_ZHO_ZHO）
  • Case 12: Generate Character Design（by @ZHO_ZHO_ZHO）
  • Case 13: Color Line Art with Color Palette（by @ZHO_ZHO_ZHO）
  • Case 14: Article Infographic（by @黄建同学）
  • Case 15: Change Multiple Hairstyles（by @balconychy）
  • Case 16: Model Annotation Explanation Diagram（by @berryxia_ai）
  • Case 17: Custom Marble Sculpture（by @umesh_ai）
  • Case 18: Cook Based on Ingredients（by @Gdgtify）
  • Case 19: Math Problem Reasoning（by @Gorden Sun）
  • Case 20: Old Photo Colorization（by @GeminiApp）
  • Case 21: OOTD Outfit（by @302.AI）
  • Case 22: Character Clothing Change（by @skirano）
  • Case 23: Multi-View Result Generation（by @Error_HTTP_404）
  • Case 24: Movie Storyboard（by @GeminiApp）
  • Case 25: Character Pose Modification（by @arrakis_ai）
  • Case 26: Generate image from line drawing（by @ZHO_ZHO_ZHO）
  • Case 27: Add Watermark to Image（by @AiMachete）
  • Case 28: Knowledge Reasoning Image Generation（by @icreatelife）
  • Case 29: Red Pen Annotations（by @AiMachete）
  • Case 30: Explosive Food（by @icreatelife）
  • Case 31: Create Comic Book（by @icreatelife）
  • Case 32: Action Figure（by @icreatelife）
  • Case 33: Map to Isometric Buildings（by @demishassabis）
  • Case 34: Reference Image Controls Character Expression（by @ZHO_ZHO_ZHO）
  • Case 35: Illustration Drawing Process Four-Panel（by @ZHO_ZHO_ZHO）
  • Case 36: Virtual Makeup Try-On（by @ZHO_ZHO_ZHO）
  • Case 37: Makeup Analysis（by @ZHO_ZHO_ZHO）
  • Case 38: Google Maps View of Middle-earth（by @TechHallo）
  • Case 39: Typographic Illustration Generation（by @Umesh）
  • Case 40: Multiple Character Poses Generation（by @tapehead_Lab）
  • Case 41: Product Packaging Generation（by @ZHO_ZHO_ZHO）
  • Case 42: Overlay Filter/Material（by @ZHO_ZHO_ZHO）
  • Case 43: Control Character Face Shape（by @ZHO_ZHO_ZHO）
  • Case 44: Lighting Control（by @ZHO_ZHO_ZHO）
  • Case 45: LEGO Minifigure（by @ZHO_ZHO_ZHO）
  • Case 46: Gundam Model Figure（by @ZHO_ZHO_ZHO）
  • Case 47: Hardware Exploded View（by @AIimagined）
  • Case 48: Food Calorie Annotation（by @icreatelife）
  • Case 49: Extract Subject and Place on Transparent Layer（by @nglprz）
  • Case 50: Image Outpainting Repair（by @bwabbage）
  • Case 51: Ancient Map → Historical Scene Photo（by @levelsio）
  • Case 52: Fashion Moodboard Collage（by @tetumemo）
  • Case 53: Delicate Cute Product Photo（by @azed_ai）
  • Case 54: Place Anime Statue in Real Life（by @riddi0908）
  • Case 55: Create an Itasha Car（by @riddi0908）
  • Case 56: Manga Composition（by @namaedousiyoka）
  • Case 57: Manga Style Conversion（by @nobisiro_2023）
  • Case 58: Isometric Holographic Wireframe（by @tetumemo）
  • Case 59: Minecraft-Style Scene Generation（by @tetumemo）
  • Case 60: Apply Material Sphere to Logo（by @ZHO_ZHO_ZHO）
  • Case 61: Floor Plan 3D Render（by @op7418）
  • Case 62: Reset Camera Parameters（by @hckinz）
  • Case 63: Create an ID Photo（by @songguoxiansen）
  • Case 64: Scene A6 Folding Card（by @Gdgtify）
  • Case 65: Design a Chess Set（by @Gdgtify）
  • Case 66: Split-Contrast Style Photo（by @fofrAI）
  • Case 67: Jewelry Collection Design（by @Gdgtify）
  • Case 68: Merchandise Design（by @0xFramer）
  • Example 69: Model Holographic Projection (by @UNIBRACITY)
  • Example 70: Giant Figure Scaffolding (by @songguoxiansen)
  • Example 71: Building Extraction from Remote Sensing Image (by @lehua555)
  • Example 72: Component Extraction (by @tetumemo)
  • Example 73: Remove Burger Ingredients (by @bind_lux, case provided by @jeanlucaslima)
  • Example 74: High-Resolution Image Restoration (by @op7418)
  • Example 75: Generate Miniature Scene from Image (by @techhalla)
  • Example 76: Educational Comic (by @op7418)
  • Example 77: Custom Character Emoji Pack Generation (by @vista8)
  • Example 78: Restore Partially Eaten Food (by @googlejapan)
  • Example 79: Fighting Game Interface Creation (by @NanoBanana_labs)
  • Example 80: Model Cross-Section (by @old_pgmrs_will)
  • Example 81: Pirate Wanted Poster (by @AI_Kei75)
  • Example 82: Merchandise Display Shelf (by @tokyo_Valentine)
  • Example 83: Comic Convention Booth (by @tokyo_Valentine)
  • Example 84: Line Art to Doodle Drawing (by @hAru_mAki_ch)
  • Example 85: Contemporary Art Exhibition Space (by @UNIBRACITY)
  • Example 86: Dark Gothic Tarot Card (by @ImperfectEngel)
  • Example 87: Black and White Evolution Chart (by @ZHO_ZHO_ZHO)
  • Example 88: Glass Bottle Souvenir (by @NanoBanana_labs)
  • Example 89: Miniature Store (by @NanoBanana_labs)
  • Example 90: Become a Vtuber (by @AI_Kei75)
  • Example 91: Train Station Movie Poster (by @AI_Kei75)
  • Example 92: Movie Lounge (by @tokyo_Valentine)
  • Example 93: Slice Object with Cartoon Explosion Effect (by @Arminn_Ai)
  • Example 94: Character-Themed Train (by @tokyo_Valentine)
  • Example 95: Custom Theme Park (by @AI_Kei75)
  • Example 96: Create Constellation Image (by @AI_Kei75)
  • Example 97: Turn Image into Phone Wallpaper (by @ZHO_ZHO_ZHO)
  • Example 98: Make a Movie Poster (by @aiehon_aya)
  • Example 99: Turn X Account into Floppy Disk (by @icreatelife)
  • Example 100: Make Reference Image Object Transparent (by @icreatelife)
  • Example 101: Fisheye Peephole Illustration (by @emakiscroll)
  • Example 102: Superhero Interior Design (by @IqraSaifiii)
  • Example 103: Custom Claw Machine (by @googlejapan)
  • Example 104: Typography Logo Design (by @aziz4ai)
  • Example 105: RPG Character Status UI (by @AI_Kei75)
  • Example 106: Convert Text Diagram to Pictograms (by @nobisiro_2023)
  • Example 107: Drawing on a Pen Display (by @AI_Kei75)
  • Example 108: Create LINE Stamp Image (by @emakiscroll)
  • Example 109: Therapy for Childhood Self (by @samann_ai)
  • Example 110: Pixar-Style Portrait (by @NanoBanana_labs)
• 🙏 Acknowledge

Output

Prompt:

Core Instruction: A Japanese Ukiyoe style collectible trading card design, vertical composition. The illustration style needs to closely mimic the visual aesthetics of "Demon Slayer", features include: ink outlines with varying thickness, traditional woodblock print color schemes, and dramatic dynamic composition.

Subject Description: The card protagonist is {Character Name} (Title: {Hashira Name/Title}), in a dynamic fighting pose, holding {Weapon Description}. The character is performing {Breathing Style Move Name}, surrounded by {Visual Effect Description} (e.g., giant flames / water dragon / whirlwind), these effects need to be presented in Traditional Japanese Sumi-e style.

Background and Material: The background needs to blend textured Holographic Foil effect, shimmering beneath the traditional ink elements.

Border: The image should have a decorative border composed of Traditional Japanese Patterns (such as Seigaiha or Asanoha). At the bottom, there is a stylized banner with "{Japanese Kanji Name}" written in ancient Japanese calligraphy.

Output

Prompt:

Create an image at 40.7128° N, 74.0060° W, on September 11, 2001, at 08:46

Output

Input: Need to upload a reference image as the character object

Prompt:

Based on the uploaded reference character, shoot a real-life scene in a spacious Tokyo girl's apartment—a bright, lived-in studio, spatial proportions close to 1LDK. The room should contain white walls, warm wooden floors, beige curtains, a low bed with soft bedding, a desk with cosmetics, bookshelves, plants, a standing mirror, a rug, scattered personal items, and a compact kitchen area at the back of the room. The room must have strong depth of field, with distinct foreground, middle ground, and deep background layers.

Place about thirty characters identical to the reference character (face, hairstyle, clothing all identical to the reference character) in the room, each in a different action or interaction state. Adjust the distance, scale, height, and visibility between characters to make the room density look natural.

Foreground (very close to the lens/partially occluded):

- A person walking past the lens, slightly out of focus

- A hand or shoulder entering the frame

- One person approaching the lens

- One person half-hidden behind a large plant

- One person sitting directly in front, tying hair

- One person kneeling by the table organizing items

Middle ground (main room area):

- One person stretching by the bed

- One person sitting on the bed checking phone

- One person lying on the bed

- One person reaching under the bed

- One person organizing cosmetics on the table

- One person flipping through books on the bookshelf

- One person standing in front of the mirror

- One person squatting on the rug

- One person leaning against the wall

- One person looking out the window

- One person adjusting curtains

- One person carrying clothes

- One person drinking water from a cup

- One person arranging pillows

- One person sitting on the floor eating snacks

- One person doing a small jump or motion blur action

- One person moving a small chair

Background (deep depth/near kitchen and... corridor):

- One person standing by the stove drinking water

- One person opening the cupboard

- One person sitting on a stool

- One person leaning against the doorway

- One person walking towards the corridor

- One person's silhouette partially blocked by the refrigerator

- One person reaching for a high shelf

- One person standing far in the entrance area

- One person faintly visible through the corridor frame

- One person sitting on the floor near the kitchen rug

Ensure strong layering occlusion: foreground figures partially obscure middle ground figures, background figures appear smaller and present natural perspective falloff. Naturally scatter the thirty figures, avoiding symmetry or grid alignment. All figures use soft natural daylight lighting to ensure perfect blending with the environment.

Place the figures in a real-life background matching the illustration pose and composition, while faithfully retaining the illustration's texture and style. Use realistic lighting, depth of field, and subtle camera effects to make the illustration seamlessly connect with the real environment.

Output

Prompt:

The diagram illustrates the process of constructing a Dyson swarm based on the paper Armstrong, S., & Sandberg, A. (2013). Eternity in six hours: Intergalactic spreading of intelligent life and sharpening the Fermi paradox. Acta Astronautica, 89, 1-13.

Output

Input: Need to upload article/text as content for generating PPT

Prompt:

Help me create a set of Chinese PPTs that middle school students can understand based on the article below.

First write a PPT outline, planning the content of each PPT page.

Then throw the content of each PPT page to Nana Banana pro to generate the corresponding PPT page, ensuring consistent style.

The specific style of the PPT should be "Anthropic/Claude style" "Warm Academic Humanism" design.

Background: Use warm beige/cream (# F3F0E9) as the base color, mimicking high-quality paper texture.

Font: Use elegant Serif for titles, and modern Sans-serif for body text.

Color Scheme: Main colors are Terracotta Red (# D67052) and Mustard Yellow (# F0B857), with Dark Navy Blue as accents. Avoid neon colors or pure black.

Visual Elements: Use a typography-focused grid layout, illustration style should be abstract, organic black hand-drawn line art, placed on solid Terracotta Red blocks, some key information uses card layout.

Charts: Flat, minimalist bar charts, emphasizing data contrast, removing excess borders.

Both text and images are generated by Nano Banana Pro, also do not turn the PPT into a single image, one image per page.

Article content is: []

Output

Input: Need to upload a character image as reference

Prompt:

Hand-drawn style fashion concept breakdown diagram.

Center: A full-body shot of a stylish, confident, slightly sexy (but not explicit) female character, with a natural and energetic pose.

Surrounding: Structured layout of her key elements:

• Clothing layers—showing coat, underwear, leggings (lace, tulle material), shapewear, and zooming in on detail patterns.

• Expression sheet—3-4 facial expressions (neutral, shy, surprised, focused).

• Close-up shots—fabric fold textures, skin details, hand gestures.

• Lifestyle and accessories—opened handbag containing daily items: lipstick, perfume, compact powder, hand cream, diary, health supplements.

• Material annotations—handwritten style notes next to each item (e.g., "soft lace", "matte leather", "shade #520").

Background: Soft beige or parchment texture, creating a design sketch atmosphere.

Lighting: Clean and soft shadows, making the image integrated.

Output: 4K HD 2D illustration, combining sexiness and fashion sense.

Language: Chinese and English labels.

Example

Input: Need to upload a reference image

Prompt:

I want to see how this was made

Output

Prompt:

Please generate a children's literacy newsletter "Amusement Park", vertical A4, learning newsletter layout, suitable for 5–9 year old children to recognize words and identify objects from pictures.
1. Newsletter Title Area (Top)
Top center large title: "Amusement Park Literacy Newsletter"
Style: Cross newsletter / Children's learning paper feel
Text requirements: Large, eye-catching, cartoon handwritten font, colorful outline
Decoration: Add sticker-style decorations related to Amusement Park around it, bright colors
2. Newsletter Body (Middle Main Image)
Center of the picture is a Cartoon Illustration style "Amusement Park" scene:
Overall atmosphere: Bright, warm, positive
Composition: Object boundaries are clear, easy to correspond to text, not too crowded.
Scene Zoning and Core Content
Core Area A (Main Objects): Show the core activities of the Amusement Park (children playing on rides).
Core Area B (Supporting Facilities): Show related tools or items (ticket booth, snacks, signage).
Core Area C (Environmental Background): Reflect environmental features (entrance, road signs, colorful flags, green space, etc.).
Theme Characters
Role: 1 cute cartoon character (Identity: Amusement Park staff/visitor child both ok).
Action: Interacting naturally with the scene (e.g., smiling and pointing the way, waving welcome, playing with children).
3. Must-Draw Objects and Literacy List (Generated Content)
Please be sure to clearly draw the following objects in the picture and reserve space for labels:
1. Core Roles and Facilities:
gōng zuò rén yuán Staff
shòu piào chù Ticket Booth
guò shān chē Roller Coaster
mó tiān lún Ferris Wheel
xuán zhuǎn mǎ Merry-Go-Round
2. Common Items/Tools:
piào Ticket
qì qiú Balloon
bīng jī líng Ice Cream
bào mǐ huā Popcorn
táng hú lu Tanghulu
miàn jù Mask
wán jù Toy
xiǎo qí zi Small Flag
3. Environment and Decoration:
rù kǒu Entrance
chū kǒu Exit
zhǐ shì pái Signpost
cǎi qí Colorful Flags
guǎng chǎng Square
(Note: The number of objects in the picture is not limited to this, but the above list must be the focus of depiction; total 18 typical nouns, suitable for 5–9 year old children literacy.)
4. Literacy Annotation Rules
Label the above list of objects with Chinese literacy labels:
Format: Two-line system (first line Pinyin with tones, second line Simplified Chinese characters).
Style: Colorful small sticker style, white background with black text or dark text, clearly readable.
Layout: Labels close to corresponding objects, not blocking the subject.
5. Art Style Parameters
Style: Children's picture book style + Literacy newsletter style
Color: High Saturation, Warm Tone
Quality: 8k resolution, high detail, vector illustration style, clean lines.

Example

Input: Need to upload a reference image

Prompt:

Can you help me generate a decorative atlas using the texture of this building?

Output

Input: Need to upload a city reference image

Prompt:

Use the uploaded city photo as the base map. Do not change the real buildings, streets, vehicles or people in the photo. Maintain the authenticity of the photo. Add a very huge, stylized illustration creature in the sky above and behind the buildings, as if it is overlooking the entire city. The creature should be drawn in a flat graphic style, with clear outlines, and use limited neon colors (such as soft neon green, neon yellow and lime green), similar to murals or poster illustrations.
Creature Design:
- Fantasy whimsical world, not horror or violent
- Composed of layered shapes, scales, hair or floral patterns
- Long arms or hair hanging beside the buildings
- Huge horns or other peculiar features clearly visible against the sky
Fusion with photo:
- Place the creature behind the edge of the building, making part of its body appear behind the edge of the building, pay attention to perspective relationship
- Use correct overlapping methods: building edge in front, creature behind, making it blend into the scene
- If necessary, add very soft shadows or color reflections on the surface of nearby buildings, but keep it subtle
- Maintain the original brightness of the sky, making the illustration clearly stand out
Optional:
- Add some small, simple illustration figures (flat, minimalist style) on the street, such as walking a dog or crossing the road, but do not block real people.
Overall atmosphere: Dreamy surreal city scene, a huge, friendly illustration creature appears above realistic buildings, combining real photos with simple modern illustrations.

Output

Prompt:

There is only one [Astro Boy] toy on the table. The toy is displayed split in half, left and right. The left half of the toy is the normal toy image, and the right half is a transparent shell, clearly showing the internal structure inside, with white lines pointing out what each part is. On the desktop, bright background, blurred table. The left side shows this half-transparent half-solid toy, and the right side of the picture shows parameters pointed out by various lines.

Output

Input: Need to upload a reference image

Prompt:

Convert a simple flat vector logo into a soft, fluffy 3D object. Use original colors. The object is completely covered in fur, with hyper-realistic fur texture and soft shadows. It is located in the center of a clean light gray background, floating gently in the air. The style is surreal, tactile and modern, creating a comfortable and playful feeling. Use studio lighting and high-resolution rendering.

Output

Prompt:

A photorealistic, highly detailed image featuring [a 3D Polaroid camera] rendered in clear, highly polished transparent glass or crystal material. [The body has distinct thickness and dimensional depth, the iconic shape of a classic Polaroid camera—boxy body, front lens, top viewfinder, front shutter button, and bottom film slot—all presented in simplified yet extremely precise geometric structures, making it instantly recognizable without any patterns]. All edges are treated with rounded chamfers and smooth curved surfaces, creating elegant refraction effects under light. The camera is placed slightly tilted, as if floating above a clean, flawless, seamless pale beige or very light gray studio background.

Lighting is bright, clean professional studio light, focusing on highlighting the transparency, specular reflection and refraction characteristics of the glass material. Sharp and delicate highlights appear on the body chamfers, film slot edges and lens rings, highlighting the crystal texture and luxurious vision. Subtle refraction, light bending and local distortion effects are produced when light penetrates the interior of the glass body, especially obvious in the lens thickness variation area, inside the film slot and near the top viewfinder, greatly enhancing realism and visual impact. A soft, diffuse shadow falls below and slightly behind the camera, giving the picture a sense of groundedness without destroying the minimalist temperament.

The overall aesthetic style is minimalist, modern, and clean, presenting the visual effect of high-end product photography and concept art rendering. The focus of the picture is completely on the crystal clear material performance and classic geometric shape of the glass Polaroid camera. The image as a whole is high-key and shallow depth of field processing, keeping the Polaroid camera in absolute sharp focus, while the background is softly blurred, thereby maximizing the subject.

Output

Input: Need to upload a reference image

Prompt:

Create a high-resolution 3D rendering of the logo in the attachment, the shape should be an inflatable fluffy object. The shape should appear soft and full, like a plush balloon or inflatable toy. Use a smooth matte texture and add subtle fabric folds and stitching to highlight the inflatable effect. The object should be slightly elastic, supplemented by soft shadows and lighting to enhance volume and realism. Place it on a simple background (light gray).

Input	Output

Input: Need to upload a reference image

Prompt:

Draw a hand-drawn isometric diagram of this street

Output

Input: Need to upload a reference image

Prompt:

I want to see the behind-the-scenes of this photo shoot and understand how it was born.

Output

Input: Need to upload a reference image

Prompt:

Create a hyper-realistic, high-resolution portrait infographic based on (your photo). Keep the identity, hairstyle, clothing, and natural skin tone of the person in (your photo) unchanged, and use a neutral studio background. Overlay a subtle semi-transparent facial analysis grid on the entire face, similar to a 3D facial scan grid: fine, soft white lines extending along the facial contours, slightly glossy but not obscuring skin details. Add a clear vertical red laser line on one side of the face, like a futuristic scanning effect. All analysis lines must be soft, concise, and elegant, like a beauty technology advertisement. Create a concise medical beauty infographic using global data percentages to evaluate 5 aging factors: 1. Fine lines and wrinkles; 2. Skin texture and elasticity; 3. Facial volume and sagging; 4. Signs of aging around eyes; 5. Skin tone and pigmentation: For each factor, place a small label with a thin line pointing to the corresponding facial area, and write a short title and a 0-100% actual percentage score (based on global data) next to it, for example: "Fine lines and wrinkles - 18%" "Skin texture and elasticity - 72%" "Facial volume and sagging - 35%" "Signs of aging around eyes - 41%" "Skin tone and pigmentation - 63%". Use concise, modern sans-serif fonts and small technical style text, similar to scientific facial analysis user interface. In the bottom center of the image, display the estimated real age based on the analysis in bold large characters, for example: "Estimated Age: (random number based on facial analysis)". Overall style: Futuristic AI-guided skincare analysis, minimalist, high-end editorial lighting, gender-neutral, suitable for any face.

Output

Prompt:

A 1080x1080 pixel close-up photo, hands holding a white newspaper, shot downwards. The background is extremely blurred and dark, making the newspaper stand out clearly. The newspaper occupies most of the picture, and its content is legible. The eye-catching headline is "[Headline]". In the center of the picture is a large black and white photo of [Photo Description]. The caption has many columns and is legible. Each shot maintains the same style, composition, lighting, characters, blur effect, layout and newspaper design, only changing the headline and photo.

Output

Prompt:

[Japanese Dating Sim Game] Character Relationship Chart. Includes character names, relationship arrows, affection levels, conflict points. [Romantic Comedy Style]. Total 7 characters.

Output

Prompt:

A set of background information for setting the protagonist and supporting characters of an Otome game.

Output

Prompt:

Game design illustration. Based on the reference image, create four versions of the character: beginner, intermediate, advanced, and elite. Each version should have a unique appearance and be arranged in order. Character name: [ A ]

Output

Prompt:

An amateur photo from 1998, showing a middle-aged artist hand-copying an image from a computer screen onto a canvas with oil paint, but the image itself is a photo of the artist painting a recursive image.

Output

Prompt:

Help me generate a collection story of female characters in anime, including Nami, Robin, Sakura, Hinata, and Rangiku Matsumoto, in the form of a color comic, requiring Chinese.

Example

Prompt:

Add texture and color to this garage kit, and change the surrounding environment to an environment that matches the character setting.

Output

Prompt:

A wide celebrity quote card, brown background, serif light gold "Stay Hungry, Stay Foolish", small text "——Steve Jobs", a large faint quotation mark in front of the text, character portrait on the left, text on the right, text occupies 2/3 of the picture, character occupies 1/3, character has a gradient transition feeling.

Output

Prompt:

A magnificent, highly detailed traditional Chinese ink and color handscroll painting on ancient silk, perfectly mimicking the artistic style, brushwork, and scattered perspective of Zhang Zeduan's masterpiece "Along the River During the Qingming Festival".
Center Scene: Overlooking the bustling modern Chicago Riverwalk. The focus is the massive steel bascule bridge (DuSable Bridge/Michigan Avenue Bridge), with traffic, countless cars, yellow taxis, and Chicago Transit Authority (CTA) buses shuttling across, all depicted with precise traditional brushstrokes.
Environmental Details: On the Chicago River below, modern architectural style cruise ships, water taxis, and kayaks shuttle back and forth. Skyscrapers of various styles line the riverbanks (resembling the Wrigley Building and Tribune Tower), painted using traditional "Jiehua" architectural painting techniques. Elevated railways and moving "L" trains are visible in the background.
Human Activity: The Riverwalk and sidewalks by the bridge are crowded with hundreds of small figures in modern casual wear. Some are jogging, some are taking photos with smartphones, some are queuing at street food stalls (hot dog stands), and some are walking dogs. The whole scene is rich in detail, slightly chaotic, and presented in soft retro earth tones.

Output

Prompt:

Use a widescreen panel to create a movie storyboard for the first page of "1984".

Input	Output

Input: Need to upload a reference image

Prompt:

Draw this illustration with colored chalk on a blackboard, the blackboard is shot from an angle, the scene is from a Japanese classroom, the blackboard is placed against the wall, the teacher's desk is in front, and "Tiger is coming!" is written in chalk next to the illustration.

Output

Input: Need to upload a reference image

Prompt:

Create a portrait depicting the person as an artist painting a miniature figure. The person is dressed in their most iconic outfit, looking confidently directly at the camera, holding a small paintbrush in one hand. A mini version of themselves is prominently placed on a clean workbench in front of them—make the figure slightly larger to be more visible than actual scale, thus standing out more. The figure is also wearing the same iconic outfit and striking an iconic pose. The painting supplies on the workbench are minimal to avoid clutter—only two or three small bottles of paint and a spare brush, keeping the focus on the person and the figure. Soft neutral white background, professional studio lighting, shallow depth of field. The composition highlights the person's facial expression looking at the camera and the figure they are painting. The style is clean and crisp, pursuing photorealistic effects, and details of both the person and the figure need to be highly restored.

Output

Input: Need to upload wikipedia link

Prompt:

Create an infographic about this person's life based on this article [Wikipedia Page].

Input	Output

Input: Need to upload a google map image

Prompt:

Please show me a Las Vegas casino style aerial view.

Input	Output

input: Need to upload a reference image as the object for generating the figure

prompt:

turn this photo into a character figure. Behind it, place a box with the character's image printed on it, and a computer showing the Blender modeling process on its screen. In front of the box, add a round plastic base with the character figure standing on it. set the scene indoors if possible

Input	Output

input: Need to upload a Google Maps image containing a red arrow

prompt:

draw what the red arrow sees 
/ 
draw the real world view from the red circle in the direction of the arrow.

Output

input: Need to upload a reference image

prompt:

you are a location-based AR experience generator. highlight [point of interest] in this image and annotate relevant information about it.

Input	Output

input: Need to upload an image containing the corresponding object

prompt:

Make Image Daytime and Isometric [Building Only]

Input	Output

input: Need to upload a photo of a person

prompt:

Change the characer's style to [1970]'s classical [male] style

Add [long curly] hair, 
[long mustache], 
change the background to the iconic [californian summer landscape]

Don't change the character's face

Input	Output

input: Need to upload multiple reference images

prompt:

A model is posing and leaning against a pink bmw. She is wearing the following items, the scene is against a light grey background. The green alien is a keychain and it's attached to the pink handbag. The model also has a pink parrot on her shoulder. There is a pug sitting next to her wearing a pink collar and gold headphones.

Input	Output

input: Need to upload an image that needs correction

prompt:

This photo is very boring and plain. Enhance it! Increase the contrast, boost the colors, and improve the lighting to make it richer,You can crop and delete details that affect the composition.

Input	Output

input: Need to upload character images and hand-drawn sketches

prompt:

Have these two characters fight using the pose from Figure 3. Add appropriate visual backgrounds and scene interactions,Generated image ratio is 16:9

Input	Output

input: Need to upload a photo taken from the ground

prompt:

Convert the photo to a top-down view and mark the location of the photographer.

Input	Output

input: Need to upload a sticker reference image and a character image

prompt:

Help me turn the character into a white outline sticker similar to Figure 2. The character needs to be transformed into a web illustration style, and add a playful white outline short phrase describing Figure 1.

Input	Output

input: Need to upload an illustration image

prompt:

Generate a photo of a girl cosplaying this illustration, with the background set at Comiket

Input	Output

input: Need to upload a character reference image

prompt:

Generate character design for me (Character Design)

Proportion design (different height comparisons, head-to-body ratio, etc.)

Three views (front, side, back)

Expression design (Expression Sheet) → like the image you sent

Pose design (Pose Sheet) → various common poses

Costume design (Costume Design)

Input	Output

input: Need to upload a line art image and a color palette image

prompt:

Accurately use the color palette from Figure 2 to color the character in Figure 1

Output

input: Need to upload a blog/article

prompt:

Generate an infographic for the article content
Requirements:
1. Translate the content into English and extract key information from the article
2. Keep the content in the image concise, only retaining the main title
3. Use English text in the image
4. Add rich and cute cartoon characters and elements

Output

input: Need to upload a portrait image that needs hairstyle changes

prompt:

Generate avatars of this person with different hairstyles in a 3x3 grid format

Output

prompt:

Draw [3D human organ model display example heart] for academic presentation, with annotations and explanations, suitable for showcasing its principles and [each organ's] functions, very realistic, highly detailed, with extremely fine design.

Output

input： Need to upload a reference image

prompt:

A photorealistic image of an ultra-detailed sculpture of the subject in image made of shining marble. The sculpture should display smooth and reflective marble surface, emphasizing its luster and artistic craftsmanship. The design is elegant, highlighting the beauty and depth of marble. The lighting in the image should enhance the sculpture's contours and textures, creating a visually stunning and mesmerizing effect

Input	Output

input: Need to upload a photo with various ingredients

prompt:

make me a delicious lunch with these ingredients, and put it on a plate , zoomed in view of the plate, remove the other plates and ingredients.

Input	Output

input: Need to upload a math problem

prompt:

Write the answer to the problem in the corresponding position based on the question

Input	Output

input: Need to upload an old photo that needs restoration

prompt:

restore and colorize this photo.

Input	Output

input: Need to upload a person image and clothing image

prompt:

Choose the person in Image 1 and dress them in all the clothing and accessories from Image 2. Shoot a series of realistic OOTD-style photos outdoors, using natural lighting, a stylish street style, and clear full-body shots. Keep the person's identity and pose from Image 1, but show the complete outfit and accessories from Image 2 in a cohesive, stylish way.

Input	Output

input: Need to upload person image and clothing image

prompt:

Replace the person's clothing in the input image with the target clothing shown in the reference image. Keep the person's pose, facial expression, background, and overall realism unchanged. Make the new outfit look natural, well-fitted, and consistent with lighting and shadows. Do not alter the person's identity or the environment — only change the clothes.

Input	Output

input: Need to upload reference image

prompt:

Generate the Front, Rear, Left, Right, Top, Bottom views on white. Evenly spaced. Consistent subject. Isometric Perspective Equivalence. 

Input	Output

input: Need to upload reference image

prompt:

Create an addictively intriguing 12 part story with 12 images with these two characters in a classic black and white film noir detective story. Make it about missing treasure that they get clues for throughout and then finally discover. The story is thrilling throughout with emotional highs and lows and ending on a great twist and high note. Do not include any words or text on the images but tell the story purely through the imagery itself.

Input	Output

input: Need to upload reference image

prompt:

Have the person in the picture look straight ahead

Input	Output

Input: Need to upload line drawings and reference images

Prompt:

Change the pose of the person in Figure 1 to that of Figure 2, and shoot in a professional studio

Input	Output

Input: Need to upload a reference image

Prompt:

Watermark the word ‘TRUMP’ over and over again across the whole image.

Output

Prompt:

Make me an infographic of 5 tallest buildings in the world / Make a colorful infographic of the sweetest things on Earth

Input	Output

Input: Need to upload a reference image

Prompt:

Analyze this image. Use red pen to denote where you can improve.

Output

Input: Need to upload a reference image

Prompt:

Photograph this product in a dramatic modern scene accompanied by explosive outward dynamic arrangement of the key ingredients fresh and raw flying around the product signifying its freshness and nutritional value. promo ad shot, without text, product is emphasized, with the key brand colors as background.

Input	Output

Input: Need to upload a reference image

Prompt:

Based on the uploaded image, make a comic book strip, add text, write a compelling story. I want a superhero comic book.

Input	Output

Input: Need to upload a reference image

Prompt:

make an action figure of me that says [“AI Evangelist - Kris”] and features [coffee, turtle, laptop, phone and headphones]

Input	Output

Input: Need to upload a map reference image

Prompt:

Take this location and make the landmark an isometric image (building only), in the stvle of the game Theme Park

Example

Input: Need to upload a character reference image and an expression reference image

Prompt:

Character reference from Image 1 / Change to the expression from Image 2

Example

Input: Need to upload a character reference image

Prompt:

Generate a four-panel drawing process for the character: Step 1: Line art, Step 2: Flat colors, Step 3: Add shadows, Step 4: Refine and complete. No text.

Example

Input: Need to upload a character reference image and a makeup reference image

Prompt:

Apply the makeup from Image 2 to the character in Image 1, while maintaining the pose from Image 1.

Input	Output

Input: Need to upload a character reference image

Prompt:

Analyze this image. Use a red pen to mark areas that can be improved
Analyze this image. Use a red pen to denote where you can improve

Output

Prompt:

Dashcam Google Street View shot | [Hobbiton Street] | [hobbits carrying out daily tasks like gardening and smoking pipes] | [Sunny weather]

Output

Prompt:

Create a minimalist black-and-white typographic illustration of the scene riding a bicycle using only the letters in the phrase ['riding a bicycle'] . Each letter should be creatively shaped or positioned to form the rider, the bicycle, and a sense of motion. The design should be clean, ultra-minimalist, and entirely composed of the modified ['riding a bicycle'] letters without adding any extra shapes or lines. The letters should flow or curve to mimic the natural form of the scene, while still remaining legible.

Example

Input: Need to upload a character reference image

Prompt:

Please create a pose sheet for this illustration, making various poses!

Example

Input: Need to upload a product reference image and a packaging reference image

Prompt:

Apply the design from Image 1 to the can in Image 2, and place it in a minimalist design setting, professional photography

Example

Input: Need to upload a reference image and a filter/material reference image

Prompt:

Overlay the [glass] effect from Image 2 onto the photo in Image 1

Example

Input: Need to upload a reference image and a face shape reference image

Prompt:

Design the character from Image 1 as a chibi version according to the face shape from Image 2

Example

Input: Need to upload a reference image and a lighting reference image

Prompt:

Change the character from Image 1 to the lighting from Image 2, with dark areas as shadows

Input	Output

Input: Need to upload a reference image

Prompt:

Transform the person in the photo into a LEGO minifigure packaging box style, presented in isometric perspective. Label the box with the title "ZHOGUE". Inside the box, display the LEGO minifigure based on the person in the photo, along with their essential items (such as makeup, bags, or other items) as LEGO accessories. Beside the box, also display the actual LEGO minifigure itself, unpackaged, rendered in a realistic and vivid style.

Input	Output

Input: Need to upload a reference image

Prompt:

Transform the person in the photo into a Gundam model kit packaging box style, presented in isometric perspective. Label the box with the title "ZHOGUE". Inside the box, display a Gundam-style mechanical version of the person from the photo, along with their essentials (such as makeup, bags, or other items) redesigned as futuristic mechanical accessories. The packaging should resemble real Gunpla boxes, including technical illustrations, instruction manual-style details, and sci-fi fonts. Beside the box, also display the actual Gundam-style mechanical figure itself, outside the packaging, rendered in a realistic and lifelike style, similar to official Bandai promotional renders.

Output

Prompt:

Exploded view of a DSLR showing all its accessories and internal components such as lens, filter,  internal components, lens, sensor, screws, buttons, viewfinder, housing, and circuit board. Maintain red accents of the DSLR

Output

Input: Need to upload a food reference image

Prompt:

annotate this meal with names of food and calorie density and approximate calories

Input	Output

Input: Need to upload a reference image

Prompt:

extract the [samurai] and put transparent background

Input	Output

Input: Need to upload an image containing transparent checkerboard areas

Prompt:

Repair the checkerboard (transparent) parts of the image and restore a complete, coherent photo.

Input	Output

Input: Need to upload a historical reference image

Prompt:

full colour photograph. New Amsterdam in 1660. make sure it's full modern colors as if it's a photograph taken today.

Input	Output

Input: Need to upload a reference image

Prompt:

A fashion mood board collage. Surround a portrait with cutouts of the individual items the model is wearing. Add handwritten notes and sketches in a playful, marker-style font, and include the brand name and source of each item in English. The overall aesthetic should be creative and cute.

Output

Prompt:

A high-resolution advertising photograph of a realistic, miniature [PRODUCT] held delicately between a person's thumb and index finger.  clean and white background, studio lighting, soft shadows. The hand is well-groomed, natural skin tone, and positioned to highlight the product’s shape and details. The product appears extremely small but hyper-detailed and brand-accurate, centered in the frame with a shallow depth of field. Emulates luxury product photography and minimalist commercial style.

Input	Output

Input: Need to upload a reference image

Prompt:

A realistic photographic work. A gigantic statue of this person has been placed in a square in the center of Tokyo, with people looking up at it.

Input	Output

Input: Need to upload a reference image

Prompt:

Create a professional photograph of a sporty car with anime-style character artwork as itasha (painted car) design, shot at a famous tourist destination or scenic landmark. The car features large, prominently displayed anime character illustrations with simple, clean design composition. The character artwork should be painted in vibrant anime art style with bold colors and clear details. Position the vehicle at a recognizable tourist spot or scenic location with good natural lighting that showcases both the car's sporty appearance and the character artwork. Use professional automotive photography techniques with proper depth of field to highlight the itasha design while incorporating the scenic background for tourism appeal, suitable for promotional or enthusiast marketing materials.

Input	Output

Input: Need to upload a character reference image and a scene composition reference image

Input	Output

Input: Need to upload a reference image

Prompt:

Convert the input photo into a black-and-white manga-style line drawing.

Input	Output

Input: Need to upload a line-art reference image

Prompt:

Based on the uploaded image, convert it into a holographic depiction using wireframe lines only.

Input	Output

Input: Need to upload a Google Maps reference image

Prompt:

Using this location, create an isometric HD-2D Minecraft-style image of the landmark (buildings only).

Example

Input: Need to upload a reference image and a material-sphere image

Prompt:

Apply the material from Image 2 to the logo in Image 1, present it as a 3D object, render in a C4D-like style, with a solid-color background.

Input	Output

Input: Need to upload a floor-plan reference image

Prompt:

Convert this residential floor plan into an isometric, photo-realistic 3D rendering of the house.

Input	Output

Input: Need to upload a reference image

Prompt:

RAW-ISO [100] - [F2.8-1/200 24mm] settings

Input	Output

Input: Need to upload a portrait reference image

Prompt:

Crop the head and create a 2-inch ID photo with:
  1. Blue background
  2. Professional business attire
  3. Frontal face
  4. Slight smile

Input	Output

Input: Need to upload a reference image

Prompt:

Draw an A6 folding card: when opened, it reveals a complete 3D spherical tiny house with a miniature paper garden and a bonsai tree inside.

Example

Input: Need to upload a reference image

Prompt:

Draw a chessboard and a set of 3D-printable chess pieces inspired by this image.

Example

Prompt:

A photo of a bedroom split down the middle: the left side is 2018 and the right side is 1964, in the same room.

Input	Output

Input: Need to upload a reference image

Prompt:

Transform this image into a 5-piece jewelry collection.

Input	Output

Input: Need to upload a reference image

Prompt:

Create merchandise using this character image.

Output

Prompt:

Ultra-realistic product photo.  
Subject: virtual holographic character [CHARACTER], floating above a circular hologram projector Ø120 mm placed on a modern desk.  

Projection source rules:  
- If input reference is a 3D object → show a desktop 3D scanner beside the projector.  
  Place the reference object on the scanner plate.  
  The hologram above the projector is generated from this scanned object.  
- If input reference is a 2D image → show a modern PC with monitor on the desk.  
  Display the reference image on the monitor screen.  
  The hologram above the projector is generated from this screen content.  

Hologram rendering rules:  
- Character always appears as a semi-transparent volumetric image, background faintly visible through.  
- No beams, no particles, no solid statue surfaces.  
- Balanced anatomy (1/7–1/8 head-to-body ratio), correct proportions.  
- Natural pose with clear silhouette.  
- Hair, outfit folds, and accessories visible but translucent.  
- Face crisp and expressive, readable at 1000 px crop.  
- No copyrighted characters, no branded designs, no IP logos.  

Environment: modern desk with projector base + conditional device (scanner or monitor).  
Camera: 85–100 mm lens, 3/4 hero angle, eye-level, f/11–f/16, ISO100, tripod.  
Lighting: desk softly illuminated; holographic figure defined only by volumetric light.  
Background: seamless black studio with subtle reflections.  

Output: 4:5, 2048×2560.  

Negative: text-free, watermark-free, logo-free, brand-free, copyrighted characters, franchise IP, trademarked designs, resin, PVC, physical statue, opaque surfaces, toy gloss, beams, scanlines, dots, distortion, extra digits.  
Sampling: deterministic, seed=12345, temperature=0.

Input	Output

Input: A reference photo of a person must be uploaded.

Prompt:

A hyper-realistic 3D render of the person in the image standing and taking a selfie. 
The giant figure is surrounded by massive scaffolding, with many tiny construction workers working on it. 
The scene is set in a city square, surrounded by modern buildings, moving vehicles (cars, buses), pedestrians, 
and a bright clear blue sky. The overall details are rich, presenting a photo-realistic texture with cinematic lighting effects.

Input	Output

Input: A remote sensing image must be uploaded.

Prompt:

Remove everything in the image except the buildings.

Input	Output

Input: An image of a model must be uploaded.

Prompt:

Cut out each component and create a model sheet that retains the hologram.

Input	Output

Input: An image of a burger must be uploaded.

Prompt:

Remove all the ingredients from the burger and keep only the top and bottom buns. Leave a gap between them, keeping the same spacing as if the fillings were still inside.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Enhance the resolution of this old image and add the appropriate texture details, reinterpreting it with modern anime techniques.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Convert the image to isometric view

Output

Prompt:

Help me generate multiple 16:9 doodle-style images to explain the concept of "futures" to middle school students. The images should have a consistent colorful, thick-pencil hand-drawn style, be rich in information, feature English text, use solid color backgrounds, have outlines around the cards, and include uniform titles, similar to a PowerPoint presentation.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Using the character from Image 2, generate [x] emoji stickers based on various poses from Image 1.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Restore this half-eaten [XX] back to its original uneaten state.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Create a mid motion actionscene where both subject are in focuswith aThree-Quarter Angle in martial artsfighting stances. They are in the samecinematic scene. Remove the line downthe centre with a blurred crumbling ruins ina purple alien world in the background. Thescene is shot at sunrise. Modern Fightinggame health bars MORDON V'S DEATHSEED. power move. Hud style screeneffects.Add a thumbnail of each characterto the health bars. ense flares!

Input	Output

Input: A reference image must be uploaded.

Prompt:

Create a cutaway visualization of this car, show exterior intact on one side, and interior engine + seats exposed on the other side. Keep proportions accurate and details realistic.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Using the original image, recreate a pirate's wanted poster drawn on parchment.
Brown monochrome, with the texture of aged parchment.
Retain the style and character design of the original image down to the smallest detail, and paste it large at the top of the wanted poster.
A close-up of the face. Have the character wear a pirate hat.
Write the bounty amount at the bottom of the poster. The bounty amount will be random, and a fictitious currency unit will be used.
Below the bounty amount, write the crime in small letters. Use a fictitious language. English or Chinese characters may not be used.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Remove the background from this illustration and turn it into merchandise like figurines.
Image: Photorealistic
Location:
The shelves of a fictional convenience store that doesn't exist in Japan. The cute, pop atmosphere is complemented by neatly arranged merchandise featuring the illustration. The store's interior is dreamily bright and special, creating a special space that excites fans.

Characters:
These merchandise are displayed on the shelves.

Merchandise Lineup:
Two large, approximately 50cm-long figures in the center of the screen (for a striking display)
Acrylic stands (deformed versions of the original artwork)

Chibi figures (deformed versions of the original artwork)

Dakimakura pillows (large prints for a striking presence)

Jigsaw puzzles (visual art of the characters)

Stationery (notebooks, pens, clear files, etc., deformed versions of the original artwork)

Cardboards (deformed versions of the original artwork)

Plush toys (deformed versions of the original artwork)

Display:
The merchandise are neatly arranged on the shelves, maintaining the atmosphere of a convenience store while still filling the space with love for the characters. They're arranged in a way that teenage female fans can't help but want to pick them up.

Overall tone:
A dreamlike merchandise sales space. Cuteness and pop are at the forefront, and despite being a convenience store, it's presented as a "holy land for fan activities."
Resolution: 4K, 4000px: 3000px

Input	Output

Input: A reference image must be uploaded.

Prompt:

Erase the background and replace the characters with the following:

Cosplayers and Character Goods

Character/Motif:
Character goods based on the illustration

Hairstyle, Eyes, and Appearance:
(Focus on merchandise, not the character itself.)

Main Character: A cosplayer is holding a figurine in the center of the screen.

Location:
Comic Market (a doujinshi sales event).
A spacious booth is filled with merchandise lined up on tables and shelves. The atmosphere is filled with excitement and anticipation.

Merchandise Lineup:
• A large, approximately 100cm figure is displayed in the center of the booth, creating an eye-catching display.
• The character is displayed on an 80-inch LCD panel.
• Acrylic Stands
• Chibi Figures (Deformed)
• Body Pillows (Large, Full-Length Character Print)
• Jigsaw Puzzles (Using Character Artwork)
• Stationery (Notebooks, Pens, Clear Files, etc.)
• Desk Pads
• Plush Toys (Deformed)
Exhibition/Display:
• Goods neatly arranged throughout the booth, creating a unified look.
• Utilizing desks and shelves reminiscent of doujinshi sales events, the layout encourages fans to pick up items.
• With the energy of the visitors as a backdrop, the venue is presented as a special "fan sanctuary."
Overall Tone:
A dreamlike sales space.
While emphasizing cuteness and pop, the space evokes the unique enthusiasm of doujin events and the feeling of a "sanctuary for fan activities."
Swarms of people.

Image Quality:
Photorealistic, 4K (4000px x 3000px)

Input	Output

Input: A reference image must be uploaded.

Prompt:

Make the uploaded picture book look as if it was drawn by a five-year-old child.

Example

Input: A reference image must be uploaded.

Prompt:

An avant-garde contemporary art exhibition space themed around the reference image.
The entire exhibition hall (20.0 m x 20.0 m x 8.0 m) integrates architecture, lighting, flooring, walls, 
and ceiling into the artistic expression.

At the far end of the hall stands a massive wall 20 meters wide and 8 meters high. 
In the center of this wall, the theme from the reference image is presented in a monumental artistic form. 
The image is vivid and three-dimensional, rising toward the viewer, becoming the focal point of the entire space.

A system-generated exhibition title plaque is installed below the central wall. 
The title must be abstract, symbolic, and poetic, and must reflect a contemporary artwork. 
No price display is provided.

The floor is polished granite with a reflectance of 0.35–0.40. 
Patterns and light derived from the reference image cascade across the surface of the work, 
resonating with the entire space as if responding to the footsteps of visitors. 
Tactile paving bricks are in a similar color, seamlessly integrated, but only 5 mm high, providing a clear texture. 
The work extends in a straight line from the entrance to the wall, creating a pause point before the artwork. 
After viewing, visitors are naturally guided to an opening on the right side (3 m wide x 3 m high). 
In emergencies, floor-level emergency lighting ensures illumination of 1 lux.

The left and right walls and the ceiling each reinterpret an abstract element from the reference image, 
transforming the entire space into a single artwork. 
The flow of color, form, and light unifies the experience into an artistic whole.

Visitor capacity is limited to 8–25 people. 
All visitors face the large wall, moving in a straight line and pausing at the designated point. 
No one looks back toward the entrance. 
Only one staff member is stationed near the right-side entrance beside the wall. 
All faces are blurred to ensure anonymity.

The composition is stable, with the central vanishing point always aligned with the center of the wall. 
Verticality is within ±0.5°. 
Floor reflections are precise, human figures appear natural. 
Hands always show five fingers, eyes are symmetrical within a 3% margin. 
Fabrics remain flat with no deformation.

Forbidden content: Elements unrelated to the reference image, missing or broken tactile paving, 
visitors facing the entrance, logos or watermarks, overcrowding, toy-like gloss, 2D flat projections, 
neon glow, teal-orange tones, oversaturation, perspective collapse, mismatched reflections, 
anatomical anomalies, extra limbs, distorted faces, excessive outlines, banding, or vignetting.

DoD: The entire venue will be a contemporary artwork centered on the theme of the reference image, 
with the innermost structure forming a unified experience. 
The tactile paving synchronizes perfectly with the flow of light, creating a clear pause point. 
Visitors are immersed in the space itself, and even in reproduction, SSIM will remain stable at 0.95 or above.

Example

Input: A reference image must be uploaded.

Prompt:

Generate a dark gothic tarot card featuring me from this image. Include [“AI Artist - Shira”] and [coffee, white fluffy chubby cat with pink bow, laptop, phone, headphones] as symbols, with moody shadows, intricate gothic borders, and mystical dark fantasy vibes.

Output

Prompt:

Generate an evolutionary progression chart in a minimalist black-and-white style, 
showing the evolution from the earliest apes to humans and finally into a banana.

Example

Input: A reference image must be uploaded.

Prompt:

A 1/7 scale commercialized collectible figure of the character from the photo, crafted in a highly realistic style. The figure is placed in a detailed beach environment with sand, seashells, and gentle ocean waves. The entire toy display is enclosed inside a clear souvenir glass bottle, giving it a premium miniature diorama look, with realistic lighting and shadows

Output

Prompt:

Tiny diorama shop for [BRAND]. Roof made of oversized [PRODUCT], big [BRAND] logo sign above the window, vendor handing a [PRODUCT] to a customer, ground covered with many [PRODUCT]. Hand-made polymer-clay look, studio macro photo, soft light, shallow depth of field, vertical 3:4

Input	Output

Input: A reference image must be uploaded.

Prompt:

Create a fictional Vtuber and their streaming screen using the original image.
The Vtuber's hairstyle and clothing will be faithfully reproduced from the original image.
The Vtuber image will be 2.5D-like, so it is not necessary to perfectly reproduce the style of the original image. A moderate sense of three-dimensionality is also necessary.
The Vtuber's facial expression and pose may be changed from the original image. Have the Vtuber hold a game controller.
Place only the Vtuber's upper body in the bottom right of the screen. Place the streaming screen of the game being played in the center of the screen. Place the chat screen on the left side of the screen.
The screen ratio is set to a larger size for the game screen, and the upper half of the Vtuber's body is displayed smaller.
The background of the original image is completely ignored, as well as the original image pose.
Add a fictional streaming platform and browser UI to the top and bottom of the screen.
The aspect ratio of the generated image is independent of that of the original image.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Create a movie poster using the original image. The genre of the movie will be determined based on the atmosphere of the original image.
Regardless of whether the original image is anime or live-action, the style and character design of the original image will be maintained as perfectly as possible. However, poses and expressions may be changed to match the poster design. Other people and objects may also be added at this time.
The final generated image will be photorealistic. This does not apply to the poster design, as it will be based on the original image.
The scenery of the underground passage of a Japanese station where the poster is posted will be recreated in a realistic image. People passing through the underground passage will be added.
The reflection of the poster is angled to make it look more realistic.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Illustration Processing:
The background is removed and the characters are turned into figurines and merchandise.
Theme / Overview:
A photorealistic movie theater lounge. A special event-themed space, set in a popcorn stand, is decorated with the world of the characters.

Location:
A spacious popcorn stand in a large movie theater.
There is a cash register, with a popcorn machine inside.
There is a drink stand with a salesperson behind the counter.
Above the register are countless posters of showing movies.

Characters / Production:
A character cosplayer is placed in the center of the screen.
Merchandise such as figurines and acrylic stands are displayed on shelves.
Giant stuffed animals and signboards are displayed realistically.
A movie photo booth is set up and decorated with character designs.

Places where characters are reflected:
Movie posters currently being screened.
Pop-up advertisements for the collaboration menu.
Drink cups and packaging.
Popcorn buckets.
Large LED LCD panel.

Design / Advertising:
Character illustrations are reflected on each poster in the lounge.
Vivid visuals of the collaboration food and drinks are displayed.
Animations and character footage are projected onto LED panels.

Camera Angle:
Composed from the front.
Emphasis on the entire popcorn stand.
A cosplayer is placed in the center, with merchandise and advertisements reflected around them.
A slightly lower angle captures the LED panels and posters impressively.

Quality / Atmosphere:
Photorealistic and detailed depiction.
An urban, realistic glossy feel, creating a cinema-like atmosphere with an event-like feel.
Resolution is 4K, aspect ratio is 4:3.

Example

Prompt:

cut cleanly THE [OBJECT] in half across the middle, the top and bottom halves slightly separated and floating apart.  
Between the halves, instead of the natural inside, there is a stylized cartoon nuclear explosion effect: a central vertical column of glowing yellow-orange bubble smoke, with a wide horizontal shockwave ring of round bubbly clouds spreading to the sides, fiery glowing highlights above and below the shockwave, creating the impression of intense heat and energy
The outside of the [OBJECT] remains photorealistic with detailed texture and lighting, while the inner effect is highly graphic and playful, giving a striking contrast between realism and cartoon. Studio lighting, centered composition

Output

Input: A reference image must be uploaded.

Prompt:

Illustration Processing:
The background is erased and characters are turned into figurines and merchandise.
Theme / Overview:
A photorealistic Tokyo train interior. The entire car is decorated with character advertisements and merchandise, creating a special space tailored for a collaboration event.
Characters / Production:
Several character cosplayers are standing in the foreground of the screen.
Life-size panels and life-size figures are displayed in the center and back of the train.
100cm character figures are on display.
Many character stuffed toys are lined up in empty seats.
Advertising / Display:
Character illustrations are reflected in advertisements on the straps.
Character illustrations are displayed on poster advertisements inside the train.
Character illustrations and animations are displayed on additional LED displays installed inside the train.
Illustration Processing:
The background is erased and characters are turned into figurines and merchandise.
Near-life-size figures, 100cm figures, deformed figures, and stuffed toys are realistically depicted.
Camera Angle:
A frontal composition emphasizes the bustling atmosphere inside the train.
A large shot of a cosplayer in the foreground, with figures, panels, and stuffed animals in the background.
A low angle captures the strap advertisements and LED displays impressively.
Quality / Atmosphere:
Photorealistic and detailed depiction.
An urban, realistic glossy feel.
Resolution is 4K, aspect ratio is 4:3.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Generates a photorealistic theme park image based on the original image.
The theme park and the people enjoying it are depicted in an extremely photorealistic style. Daytime. Sunny.
The color scheme and design are extracted from the original image and applied to the color scheme and design of various facilities.
Vehicles and buildings based on the original image, mascot costumes that are a distorted version of the original image, and signs with the original image printed on them are placed within the image.
The mascot costume design should use the original image as a motif, but be moderately distorted to create a photorealistic look.
The sizes of the people and mascot costumes must not be unrealistic.
Even if the original image is anime-style, the final image must be a photorealistic theme park. Be sure to follow these rules.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Create an image depicting fictional constellations using the original image as a reference.
- A photorealistic starry sky. This is maintained even if the original image is anime-style.
- People, animals, and objects extracted from the original image are placed transparently against the starry sky background. In this case, the extracted target should be a single motif that is the main theme. Also, only one image should be placed.
- The character design, style, and taste of the original image are faithfully reproduced. The background of the original image can be ignored.
- An imaginary constellation is created based on the placed motif. This constellation is made up of approximately 5 to 10 stars.
- The pose of the original image is analyzed, and the stars belonging to the constellation are appropriately positioned in distinctive parts.
- The stars belonging to the constellation are highlighted, and the stars are connected with glowing lines.

Example

Input: A reference image must be uploaded.

Prompt:

Transform the image into an iPhone lock screen wallpaper effect. The phone’s time (01:16), date (Sunday, September 16), and status bar details (battery, signal, etc.) appear overlaid on the image, with flashlight and camera icons at the bottom. The original picture is adapted to fit the elongated smartphone screen composition. The phone is placed against a background in the same color scheme.

Output

Input: A reference image must be uploaded.

Prompt:

Analyze the uploaded photo and detect the subject, mood, and atmosphere.  
Automatically classify the photo into a suitable movie genre (romance, action, mystery, horror, etc.).  

Based on the detected genre and mood, generate all the following elements in English:  
- A cinematic movie title (impactful, authentic to the genre).  
- A short tagline or catchphrase (1–2 lines, dramatic or emotional).  
- A credit block at the bottom (with fake names for director, producer, music, etc., styled like real movie posters).  
- A release note such as “COMING SOON” or “In Theaters 2025.”  

Overlay these elements on the image in a movie-poster style layout:  
- Place the title prominently in the center or lower third.  
- Place the tagline above or below the title.  
- Add a credit block at the bottom in small text.  
- Add the release note at the bottom center.  

Finally, add the starring section at the bottom, always formatted as:  
“Starring: ”  

Typography should be bold, dramatic, and genre-appropriate.  
The final result must look like a genuine movie poster ready for theaters, with all elements harmonized to the photo’s mood.

Output

Input: Upload a reference image of the X account.

Prompt:

Make my X account into a floppy disk in the 90s 

Input	Output

Input: A reference image must be uploaded.

Prompt:

Make this object transparent.

Input	Output

Input: A reference image must be uploaded.

Prompt:

ultra-detailed anime illustration, fisheye lens peephole perspective, circular distorted view as if looking through a door peephole, warped wide-angle effect with curved edges, darkened vignette around the circular
frame, two people leaning their faces close to the peephole trying to peek through, both with mischievous playful smiles, exaggerated perspective distortion making their features appear larger and curved, faces
approaching the peephole lens, hallway or room interior bent by the lens effect, slightly blurry edges mimicking actual peephole optics, playful atmosphere, 8k resolution

Output

Prompt:

A hyper-realistic, professional interior design photograph of a modern living room inspired by a [Superhero]. The room has clean lines, a neutral color palette of greys, blacks, and whites, with accents of [Theme Color]. A large, stylized 3D wall sculpture of the [Superhero] dominates the main wall. Subtle thematic details are placed throughout the room, such as framed art prints of blueprints, a floor lamp designed to resemble a specific motif (e.g., a shield or logo), and a side table with a few well-placed props (e.g., a stylized helmet). The furniture is contemporary and minimalist, with a large, comfortable sofa and a low coffee table. Dramatic, focused lighting highlights the main wall sculpture, while warm ambient light from windows and lamps creates an inviting atmosphere. The overall style is sophisticated and elegant, a subtle homage rather than an overt fan-tribute.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Generate an image showing this animal as a simplified and deformed as an anime-like plush toy (made of short-pile, soft-touch polyester knit fabric), with multiple units inside a UFO catcher machine. On either side are additional UFO Catcher machines containing multiple plush toys of different animals, distinct from the main image. The setting is a Japanese game center, with an overall very bright impression. Only the top section of the UFO catcher is painted in vibrant colors. The lower section is painted white. The background is a wall, and the area behind the UFO catcher is quite blurred.　The floor is carpeted. The shooting angle is from the front. Most importantly, absolutely no text or logos should appear in the output.

Output

Prompt:

Create a typographic illustration shaped like a {OBJECT}, where the text itself forms the shape — bold and playful lettering style that fills the entire silhouette — letters adapt fluidly to the curves and contours of the object — vibrant and contrasting color palette that fits the theme — background is solid and enhances the focus on the main shape — vector-style, clean, high resolution, poster format, 1:1 aspect ratio.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Use the character in the original image to create a character status screen for an RPG game.
Keep the character design and style from the original image, but change the costume to one from a fantasy RPG. Also, change the pose to suit the situation.
Display the character from the original image and the status screen side by side.
The status screen will list various parameters, skills, icons, etc.
The background should be a fantasy background that matches the style of the original image.
The status screen should be rich and stylish, like a game from 2025.

Input	Output

Input: A reference image containing text must be uploaded.

Prompt:

Convert this explanatory diagram into pictograms.

Input	Output

Input: A reference image must be uploaded.

Prompt:

Photorealistic pen tablet screen. Realistic first-person hand holding the pen tablet and pen.
The original image is reproduced on the pen tablet in an unfinished state. The line art has been extracted from the original image. Portions of the line art have been colored with the same coloring as the original image. Unfinished coloring. Must not be monochrome. About 70% of the coloring is done.
Close-up. The pen tip is touching the tablet screen.

Input	Output

Input: Upload a facial expression reference and a character reference image.

Prompt:

Character sheet, facial expressions, joy, anger, sadness, happiness

Output

Input: A reference portrait must be uploaded.

Prompt:

Photorealistic minimalist therapy room; light walls, grey sofa, wooden coffee table with a tissue box, notebook and a glass of water, simple frame and floor lamp, soft natural daylight. The same person at two ages sits side-by-side: adult on the left speaking with open hands; child on the right listening with head slightly down. Both wear matching [OUTFIT] (same color & style). Clean studio vibe, centered composition, shallow depth of field, 50mm look, 4K, vertical 3:4. No extra people, no text, no watermark.

Output

Input: A character reference image must be uploaded.

Prompt:

3D avatar of the young man in the image attached, smiling happily, clean white background, conceptual digital art in Pixar-style, high quality, soft lighting, smooth textures, vibrant colors, realistic proportions with a cartoon touch & studio render look.

The various cases in this repository rely on sharing from the AI community. Please allow us to express our sincere gratitude to all case contributors.

Thank you to the following users for sharing their amazing works. You can also visit their profiles to learn more:

• @ZHO_ZHO_ZHO
• @tokumin
• @bilawalsidhu
• @Zieeett
• @AmirMushich
• @MrDavids1
• @op7418
• @黄建同学
• @balconychy
• @berryxia_ai
• @umesh_ai
• @Gdgtify
• @302.AI
• @Gorden Sun
• @GeminiApp
• @skirano
• @Error_HTTP_404
• @arrakis_ai
• @AiMachete
• @icreatelife
• @demishassabis
• @TechHallo
• @tapehead_Lab
• @AIimagined
• @0xFramer
• @fofrAI
• @songguoxiansen
• @hckinz
• @tetumemo
• @nobisiro_2023
• @namaedousiyoka
• @riddi0908
• @azed_ai
• @bwabbage
• @nglprz
• @UNIBRACITY
• @lehua555
• @bind_lux
• @techhalla
• @vista8
• @googlejapan
• @NanoBanana_labs
• @old_pgmrs_will
• @AI_Kei75
• @tokyo_Valentine
• @ImperfectEngel
• @Arminn_Ai
• @aiehon_aya
• @emakiscroll
• @IqraSaifiii
• @aziz4ai
• @samann_ai
• @hAru_mAki_ch

We cannot guarantee that all cases come from the original authors. If this causes you any inconvenience, please feel free to contact us for modifications.

The cases we collect cannot cover all possible application scenarios. If you have other interesting discoveries 🔍, we welcome you to contact us to showcase more creativity 📧!