One idea → a short film
Make a movie

Prompt library

AI photo prompts and AI image prompts that actually work

A free library of copy-paste prompts for the photos people are making right now: Gemini trend edits, the ChatGPT caricature, Nano Banana figurines, Halloween and Christmas portraits, text-perfect thumbnails and Seedance 2.5 video. Every prompt is shown next to the real, unedited result it produced, so you can see what you will get before you paste it.

  • 73 tested prompts
  • 7 collections
  • Real outputs, unedited

All examples were generated on MakeInfluencer.ai with GPT Image 2.5 and Seedance 2.5, using our own AI character as the model. The prompts also work in Gemini, Nano Banana and ChatGPT. MakeInfluencer.ai is not affiliated with Google, OpenAI or ByteDance.

Woman in a sheer black chiffon saree standing against a warm wall with sharp window shadows
Caricature of a smiling woman content creator at a desk with a camera, laptop and coffee
Collectible figurine of a woman on a round clear base on a desk next to a monitor

Browse by collection

Prompt collections

Trend edits, caricatures, photo edits, seasonal portraits and video. Each collection has 10 to 12 prompts with real outputs.

Editor's picks

12 of the best AI photo prompts

Our favourite prompt from each collection, ready to copy. Open any title to see the rest of its collection.

Woman in a sheer black chiffon saree standing against a warm wall with sharp window shadowsNo. 01GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture.

Create a photorealistic vintage-style portrait of the woman wearing a sheer black chiffon saree with a thin gold border, draped over one shoulder, and a sleeveless black blouse. Her hair is loose with soft waves, a small white flower tucked behind one ear. She stands against a plain warm beige wall, body angled slightly away, looking back toward the camera with a calm, faint smile. Late-afternoon sun comes through a window on the left, casting sharp shadow stripes across the wall and her shoulder. Framed from the waist up, slightly off-centre, 50mm look. Warm golden grade with soft film grain, like a 1990s Bollywood film still. The chiffon shows real folds and transparency at the edges.

Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

Caricature of a smiling woman content creator at a desk with a camera, laptop and coffeeNo. 02GPT Image 2.5 · photo edit

Use the uploaded photo as the reference for the woman's face. Keep her instantly recognisable: same face shape, eyes, eyebrows, nose, smile, hairline, hair colour and skin tone. Draw her as a caricature: an oversized head on a small body, playfully exaggerated eyes and smile, affectionate rather than mocking.

Create a caricature of her and her job as a content creator who makes AI photo and video content. She sits at a small desk, waving at the viewer with a huge grin, a laptop showing colourful thumbnails with no readable text, a camera on a mini tripod, a ring of sticky notes, headphones around her neck and an oversized iced coffee. A cat sleeps on a pile of cables. Style: a polished digital caricature painting like the viral ChatGPT caricature trend, soft painterly shading, clean outlines, bright friendly colours, plain light background with a soft shadow under her feet.

No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

Collectible figurine of a woman on a round clear base on a desk next to a monitorNo. 03GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face shape, eyes, eyebrows, nose, lips, hairline, hair colour and skin tone recognisable in the new style. Do not redesign her.

Turn her into a small collectible vinyl toy figure and photograph it on a wooden computer desk. The toy figure is fully clothed in a cream knit sweater, blue jeans and white trainers, with her hairstyle and face sculpted and hand-painted in realistic detail, a slight vinyl sheen, standing on a round clear acrylic base. Behind it, a monitor shows a grey 3D modelling viewport of the same toy with no readable text, and beside it stands a plain kraft-paper toy box with a clear window and no printing. Soft daylight from a window on the left, a desk lamp glowing out of focus. Macro-lens look, shallow depth of field.

No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

Full-body street-style photo of a woman in a camel coat crossing a city streetNo. 04GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture.

Create a photorealistic editorial street-style photograph of the woman walking across a city crosswalk in late afternoon, mid-stride, glancing just past the camera. She wears an oversized camel wool coat over a white ribbed knit top, straight-leg dark jeans and white leather trainers, and carries a plain black leather shoulder bag with no visible logo. Full body visible, feet included, shot from slightly below eye level, 35mm look, pedestrians and buildings softly out of focus. Low warm sun from the side, long shadows on the asphalt. 35mm film look, subtle grain.

Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

No. 05Seedance 2.5 Turbo · 720p clip

She lifts the cup, takes a small sip, lowers it and laughs softly at something off camera to the left. Keep her face, hair, wardrobe, set and lighting exactly as in the start frame. Camera nearly static, a very slow push-in. Natural, believable motion: steam from the cup, people passing outside the window out of focus. Sound: quiet café ambience, cups clinking, no music. No on-screen text, no subtitles, no logos, no morphing or face warping.

Start frame prompt

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture. Create a photorealistic candid photograph of the woman sitting at a small marble café table by the window in late morning. She wears a cream cable-knit sweater with pushed-up sleeves and small gold hoop earrings, holds a cup of coffee in both hands and looks off to the left with a relaxed half-smile, as if a friend just said something. A croissant on a small plate in front of her; the street outside softly out of focus. Framed from mid-chest up, slightly off-centre, eye level, as if taken by a friend on a phone. Soft daylight from the window, gentle shadow on the far side of her face. Natural phone-photo colour. Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No text, no logos, no watermark.

See the still: Café window candid

Upload one clear photo of yourself, then paste the prompt.

Woman dressed as a witch holding a lantern in a misty autumn forest at duskNo. 06GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture.

Create a photorealistic Halloween portrait of the woman as a witch in a misty autumn forest at dusk. She wears a wide-brimmed black felt witch hat, a long black wool cloak over a dark green dress and holds an old brass lantern with a candle inside. Fallen orange leaves on the ground, bare trees fading into fog behind her. She looks at the camera with a calm, knowing half-smile. Framed from the waist up, eye level, 50mm look. Warm candlelight from the lantern on her face, cool blue fog light behind. Fine film grain.

Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

Retro 90s film-style portrait of a woman in a brown turtleneck with warm tonesNo. 07GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture.

Create a photorealistic 1990s film portrait of the woman in a chocolate-brown ribbed turtleneck, hair loosely half-up with a few face-framing strands. She sits on the arm of a worn leather sofa, one elbow on her knee, chin resting lightly on her hand, looking straight into the lens with a quiet, confident expression. Behind her, a wood-panelled wall with a warm lamp glowing out of focus. Chest-up, eye level, 50mm look. Warm tungsten light from a table lamp on the right, soft shadow on the left side of her face. Kodak Portra 400 look: warm brown tones, visible film grain, slightly faded blacks.

Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

Woman holding a mug of mulled wine at a Christmas market at duskNo. 08GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture.

Create a photorealistic photograph of the woman at a European-style Christmas market at dusk, holding a steaming ceramic mug of mulled wine in gloved hands and smiling at the camera. She wears a camel wool coat, a cream knit scarf and a red beanie. Wooden stalls with warm string lights and pine garlands behind her, softly out of focus, no readable signs. Light snow falling. Framed from the waist up, eye level, 50mm look. Warm stall lights on her face against the deep blue evening sky.

Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

YouTube thumbnail of a surprised woman next to a laptop with the text I TRIED ITNo. 09GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture.

Create a 16:9 YouTube thumbnail, photorealistic. The woman, large and close on the left third, with a genuinely surprised expression, mouth open, one hand on her cheek. On the right third, an open laptop showing a simple rising green line chart. Headline text "I TRIED IT" rendered exactly once in heavy white sans-serif with a thick black outline, top right, large and legible at small size. High contrast, simple deep-blue gradient background, soft key light from the front-left. No other text.

Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

Tiny miniature woman sitting on the rim of a large latte cupNo. 10GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture.

Create a photorealistic miniature scene: a tiny version of the woman, about five centimetres tall, sits on the rim of a large white ceramic latte cup on a café table, legs dangling over the foam, holding a coffee bean in both arms like a beach ball and laughing. She wears a yellow raincoat and white trainers. Latte art heart in the foam, a teaspoon and a sugar cube beside the cup for scale. Macro-lens look with a tilt-shift feel, soft morning window light, shallow depth of field.

Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

Woman on a wet city street at night lit by pink and blue neon signsNo. 11GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture.

Create a photorealistic cinematic night photograph of the woman standing on a narrow wet city street, wearing a black leather jacket over a white T-shirt. She looks just past the camera, hands in her jacket pockets, a few strands of hair across her face in the breeze. Blurred shop signs glow pink and teal behind her with no readable lettering, reflections on the wet asphalt. Framed from the waist up, eye level, 35mm look, shallow depth of field. Neon light from both sides: magenta on one cheek, cyan on the other. Slight haze, fine grain, deep blacks.

Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

Woman in a Victorian gothic outfit with a candelabra in a dark roomNo. 12GPT Image 2.5 · photo edit

Use the uploaded photo only for the woman's identity. Keep her face exactly as in the photo: face shape, eyes, eyelids, eyebrows, nose, lips, jawline, hairline, hair colour and skin tone. Do not beautify, slim, smooth or retouch her face; keep its natural asymmetry and texture.

Create a photorealistic gothic Halloween portrait of the woman as an elegant vampire in a candlelit Victorian drawing room. She wears a high-collared black lace blouse, a deep burgundy velvet cape and a small silver pendant, dark berry lipstick and subtle smoky eye makeup. She sits in a carved wooden armchair beside a silver candelabra, looking at the camera with a cool, amused expression. Framed from the chest up, eye level, 50mm look. Warm candlelight from the right, deep shadows on the left, dark green damask wallpaper behind. Film grain.

Real skin texture: visible pores, fine vellus hair, slightly uneven natural tone. Unretouched, no skin smoothing, no beauty filter, no glamorization. No text, no logos, no watermark.

Upload one clear photo of yourself, then paste the prompt.

How to write your own

How to write an AI image prompt

Every prompt in this library follows the same order. Use it for your own ideas and your first result will be much closer to what you pictured.

  1. 1

    Say what the image is for

    Candid phone photo, product listing, YouTube thumbnail, watercolour card. The use sets the look before anything else.

  2. 2

    Lock the face if you upload a photo

    List what must stay the same: face shape, eyes, nose, lips, hairline and skin tone. Ask for no retouching.

  3. 3

    Describe the scene concretely

    Outfit and fabric, action and gaze, the place and two or three props, then shot size, angle and lens.

  4. 4

    Name the light

    Source, direction and colour. Directional light shows real skin and texture; flat light looks plastic.

  5. 5

    Finish with text and exclusions

    Quote any words exactly once, then rule out other text, logos, watermarks and extra people.

FAQ

Frequently Asked Questions

Make these photos with your own face

Save your AI character once, then run any prompt from this library with GPT Image 2.5, Nano Banana Pro or Seedance 2.5.

Start creating in minutes · Pay as you go