Free tool, no sign-up

AI Image Prompts, Written for the Model You Use

Describe your picture once. Get an AI photo prompt in the exact syntax of Nano Banana, GPT Image, Midjourney, Flux, Ideogram or Stable Diffusion, plus 3 AI variations when you want more ideas.

Build a prompt See examples

Free, no sign-up

15 models, image and video

Updated October 2026

AI model What do you want?

Describe it Keep exactly the same

Setting Style

Lighting Shot / framing

Camera move Lens look Format

Exact text in the image (optional)

Sound (optional) Spoken line (optional)

Avoid (optional) Stylize --s (0-1000, optional)

Your prompt for Nano Banana

Describe what you want on the left. Your prompt appears here as you type.

Open Nano Banana

Free: 5 AI runs a day, 3 variations each. Pro: 100 runs, 10 variations, saved prompt library.

Tips

Refine in the same chat: one small change per turn ("make the light warmer, keep everything else").
Upload your photos first and refer to them as image 1, image 2 in the order you attached them.

Image to prompt

Upload a picture and the AI writes a prompt that recreates it for the model picked in the studio above, in that model's format. Your image is processed in memory and never stored.

Your image (JPEG, PNG or WebP)We shrink it to 1024 px in your browser before sending. It is not saved on our side. Note for the AI (optional)

Pro feature. Image to prompt is part of All-Access Pro: 20 images a day, plus 100 AI runs, 10 variations and a saved prompt library. Already Pro? Sign in.

Prompt from your image for the selected model

Pick a model in the studio above, upload an image and press "Write prompt from image".

AI Image Prompts: examples you can copy

Each example was written by the studio above. Click "Edit in the studio" to load it into the form and change the details.

Marketplace packshotNano Banana

Using image 1, create a clean e-commerce packshot of my product on a pure white background, centered, filling about 85 percent of the frame. Keep the product shape, colors, label text and logo exactly the same. Match the lighting, perspective and grain of the original so the change looks natural. Square 1:1. Avoid: props, text, reflections. Do not change anything else.

Lifestyle product photoMidjourney V7

lifestyle photo of a matte black 500 ml steel water bottle with a bamboo lid, a white marble kitchen counter in a bright modern home, soft morning window light, 50mm, shallow depth of field, editorial home magazine photo --ar 4:5 --style raw --s 75 --no text, clutter --v 7

90s film portraitGPT Image (ChatGPT)

Using image 1, restyle the photo as a 1990s film portrait with warm faded Kodak colors and soft grain. Keep the person's face, features, hairstyle and age exactly the same. Match the lighting, perspective and grain of the original so the change looks natural. Vertical 4:5. Do not change anything else.

Anime characterFlux

An original anime heroine with short silver hair and a red scarf standing on a rooftop in a neon city at night. Soft rim light. Anime illustration, clean line art, cel shading.

Event poster with textIdeogram

A bold event poster for a summer rooftop jazz night. Flat graphic style, warm orange and navy palette, strong contrast. The text reads "JAZZ ON THE ROOF". Spell all text exactly as written; no other text.

Negative prompt: extra text, watermark

SDXL fantasy landscapeStable Diffusion

a floating island with a waterfall and an ancient stone temple, golden hour, epic fantasy matte painting, high detail

Negative prompt: people, text, blurry, lowres, deformed hands, extra fingers, watermark

Why the same idea needs a different prompt in each AI

Image models read prompts differently. A prompt that works in ChatGPT can confuse Midjourney, and a Midjourney prompt full of --parameters is noise to Nano Banana. The studio rewrites your idea in each model's own grammar.

Instruction models

Nano Banana and GPT Image follow full sentences. They edit your own photo when you say what to change AND what to keep, and they refine turn by turn in one chat.

Keyword models

Midjourney reads short descriptive phrases, most important first, steered by parameters like --ar, --s and --style raw. Never write "no text" inside the prompt: use --no text.

Prose models

Flux and Stable Diffusion 3.5 want natural sentences that start with the subject. Flux has no negative prompt at all, so the studio drops your avoid list and tells you why.

Text-first models

Ideogram renders words best. Put the exact text in double quotes, turn Magic Prompt off, and the studio moves exclusions into the negative prompt field.

How to write an AI image prompt that works the first time

Start with the image type and a concrete subject "Studio product photo of a matte black 500 ml steel bottle with a bamboo lid" beats "a nice bottle". Two or three identifying details (material, color, size, age, clothing) stop the AI from guessing.
Set the light Light is the fastest quality lever: "soft window light from the left", "golden hour backlight", "hard flash, deep shadows".
Fix the frame Shot size, angle and space for text: "top-down flat lay, empty space on the left for a headline".
Say the format 1:1 for marketplaces, 4:5 for Instagram, 9:16 for Stories and Reels, 16:9 for YouTube and web heroes.
Edit, do not restart With Nano Banana and GPT Image send one small change per turn and repeat what must stay the same.

AI image models: prompt cheat sheet

Checked October 2026. Model syntax changes often; we review this table every month.

Model	Modes	Negative prompt	Key tip
Nano Banana Google Gemini image	New image, Edit a photo	One Avoid sentence	Refine in the same chat: one small change per turn ("make the light warmer, keep everything else").
GPT Image (ChatGPT) OpenAI	New image, Edit a photo	One Avoid sentence	Ask for exact wording ("use this text exactly") when the image contains text.
Midjourney V7 Midjourney	New image, From a reference image	--no list	Keep --seed fixed while you change one word to see what that word does.
Flux Black Forest Labs	New image, Edit (Flux Kontext)	None, phrase positively	Flux ignores negative prompts: say what you want instead ("an empty street", not "no cars").
Ideogram Ideogram	New image, Edit a photo	Separate field	Turn Magic Prompt OFF when exact wording or layout matters.
Stable Diffusion Stability AI (SD 3.5, SDXL)	New image, Image to image	Separate field	Fix the seed while you test one change at a time.

Want ready prompts instead of building them?

The AI Image Prompt Pack has 64 tested prompts with formulas, a camera and style cheat sheet, troubleshooting and an assistant prompt for Claude or ChatGPT.

AI Image Prompt Pack

64 prompts as a plain-text file, yours to keep. One-time payment.

Get the pack, $9

Or everything with Pro

100 AI runs a day with 10 variations, prompts from your images, a saved library of 500 prompts with tags and search, every prompt pack, and 10 files a month.

See Pro

More prompt tools

Nano Banana prompts Midjourney prompt generator ChatGPT image prompts AI video prompts ChatGPT photo editing prompts Gemini prompts DALL-E prompts Prompt optimizer for text AI

FAQ

What is an AI image prompt?

It is the text you give an image generator to describe the picture you want: the subject, setting, light, framing, style and format. Good AI image prompts are specific and use the syntax of the model you run them in.

Is this AI image prompt generator free?

Yes. Building a prompt for any model is free and unlimited, it runs in your browser. The "Improve with AI" button gives 5 free runs a day with 3 variations each; Pro raises that to 100 runs and 10 variations.

Does it generate the image too?

No. The studio writes the prompt; you paste it into Nano Banana (Gemini), ChatGPT, Midjourney, Flux, Ideogram or Stable Diffusion and generate there.

Which AI image generator should I use?

For editing your own photo or exact product labels use Nano Banana or GPT Image. For mood and style from scratch use Midjourney. For text inside the image use Ideogram. For open models and local workflows use Flux or Stable Diffusion.

Can I get AI photo prompt ideas?

Pick a style chip (product photo, 90s portrait, anime, cinematic, flat lay) or click one of the examples on this page. Then press Improve with AI to get three different takes on your idea.

Can I save my prompts?

With KissMySkills Pro you can save up to 500 prompts with tags and search them on any Studio or Prompt Library page.

Can it write a prompt from my image?

Yes, with Pro. In Image to prompt upload a picture, pick the model in the studio, and the AI writes a prompt that recreates it in that model's format, up to 20 images a day. The image is shrunk in your browser, processed in memory and never stored by us; press Edit in the studio to tweak the result.