Garba night in a mirror-work chaniya choli
Works with your photo
Free to copy, no account needed
AI prompts that show you the result first
The picture beside a prompt is what that prompt produced. Each one states the model it was tested on, the ratio it expects, and whether it can keep your own face from a photo.
- 73
- AI tools compared
- 68
- Categories across four kinds
- Free
- Every prompt, in full
- Markdown
- Structured for models to read
Start with what you are making
Image
Prompts for still images, each one shown with the output it produced and the model it was tested on.
26 categoriesVideo
Prompts for video models, with the clip each one produced and the settings it needs.
12 categoriesProductivity
Prompts for work: search, advertising, writing, analysis and code, each written to return something usable rather than a draft.
16 categoriesDaily
Prompts for the things that come up every week: replies, messages, notes and planning.
14 categoriesLatest prompts
All prompts
Serum bottle on wet basalt under a hard key light
Wuxia swordswoman landing on a rain-soaked roof
Works with your photo
4:5
Cricket fan portrait in team colours
Works with your photo
4:5
Rainy street portrait under a shop awning
Works with your photo
1:1
Product hero on brushed concrete
Banarasi lehenga full-length in a courtyard
Works with your photo
3:4
Golden hour rooftop couple
Works with your photo
How it works
- 1
Find one that already worked
Every prompt shows the output it produced, so you are choosing a result rather than guessing from a description.
- 2
Check the three fields
The model it was tested on, the ratio it expects, and whether it works with a photo of your own. Those three explain almost every case where a prompt does not reproduce.
- 3
Copy and adapt
The copy action hands over Markdown with each part under its own heading, so you can change the wardrobe without touching the lighting.
Every category
All sectionsPortraitCoupleFestival and devotionalTraditional wearVintage and retroEditorial and fashionSports and fandomHeadshots and professionalProduct and brandIllustration and 3DWallpapersLogo and designWeddingBaby and familyMaternityTravel and placesFood and drinkReal estate and interiorFitness and sportPets and animalsAnime and cartoonFantasy and science fictionBlack and whiteOld photo restorationThumbnailsMockupsCinematicProductSocial mediaAnimationB-rollTransitionsTalking headExplainer
Ads and promoMusic and visualiserNature and landscapeImage to videoSEOAds and copyContent writingSocial mediaData and analysisCodingPresentationsResearchEmail marketingSales and outreachProduct and UXHR and hiringLegal and adminCustomer supportEcommerceTranslationEmailWhatsApp and chatClient communicationMeetings and notesPlanningLearningPersonal financeTravelResume and careerHealth and habitsHome and cookingShopping and decisionsPersonal writingParenting and study
Browse by model
All modelsGPT Image
Strong at following a long instruction literally and at legible text in an image.
OpenAINano Banana
Built for editing an existing image and for holding a face across edits.
GoogleGemini
General image generation inside a general assistant, useful for quick iterations.
GoogleMidjourney
The most art-directed look of the group, at the cost of literal instruction following.
MidjourneyWhat is different here
The output is on the page
The picture beside a prompt is what that prompt produced. You are choosing a result, not guessing from a description of one.
The model is named
The same text on two models is two different pictures. A prompt that does not say which one it was run on cannot be reproduced.
Ratio is a field
Aspect ratio changes what the model puts in frame, not just where it crops. It belongs where you can read it, not buried in prose.
A photo requirement is stated
Some prompts only work with a photograph of your own. That is marked on the card, before you copy anything.
Worth preparing for
CollectionsFebruary or March
Maha Shivaratri
Worth having ready about 6 weeks ahead, so the page is indexed before anyone starts looking.
MarchHoli
Worth having ready about 6 weeks ahead, so the page is indexed before anyone starts looking.
variesEid
Worth having ready about 6 weeks ahead, so the page is indexed before anyone starts looking.
September or OctoberNavratri
Worth having ready about 6 weeks ahead, so the page is indexed before anyone starts looking.
73 AI tools, compared the same way
Every entry says what the tool does, what it costs, what it is genuinely good at, and where it falls short. Written to one shape, so two tools can be compared without reading two different kinds of page.
Open the directory
Gathered by what you are doing
All collectionsFestival portraits
Traditional wear, devotional settings and warm light, for the run-up to a festival rather than the morning of it.
Prompts that use your photo
Everything that takes a reference photograph and holds the face through it, with what a usable source photo looks like.
Selling something online
Product shots, brand imagery and the listing copy around them, for a shop page or a marketplace listing.
How prompts are put together
All postsMaking festival portraits that do not look generic in AI
Festival and traditional-wear prompts fail in predictable ways. Name a real weave, control the jewellery, light warm skin well, and keep backgrounds quiet.
Free vs paid, where AI image tool free tiers actually stop
An honest look at the limits of free AI image tiers: resolution caps, queue priority, commercial-use terms, watermarks, private generation and ownership.
Which aspect ratio to use, and why it changes the image
Aspect ratio is not a crop applied at the end. It changes composition and what the model puts in frame. A guide to 1:1, 4:5, 3:4, 9:16, 16:9, 3:2 and 2:3.
What this library is
Every prompt here was run before it was published. The picture beside one is the output that prompt produced, not stock imagery chosen to look good next to the text, and a prompt that could not be made to work is not published at all.
Most prompt collections hand you a block of text and nothing else. You paste it, get something unlike the picture on the page, and have no way to tell whether the prompt is wrong, the model is different, the ratio is different, or it needed a photograph you never gave it.
Each of those is answerable before you copy anything, so each is answered on the card: the model, the ratio, and whether a reference photo is required. The image beside a prompt is the output that prompt produced, not stock imagery chosen to look good next to it.
How to use a prompt
Copy it, paste it into the model named on the page, and set the aspect ratio it asks for. Where a prompt needs a reference photo, upload that first, before pasting. Then change one clause at a time: rewriting the whole thing at once leaves you unable to tell which change did the work.
Prompt bodies are written in Markdown, with each part under its own heading, because a language model follows a structured document more reliably than a paragraph of run-on description.
What is covered
Image prompts for portraits, festivals, traditional wear, products and editorial work. Video prompts for cinematic shots, social clips and product motion. Productivity prompts for search, advertising copy, analysis and code. And daily prompts for the writing most people actually do: email, messages, meetings and planning.
Common questions
What is an AI prompt?
An instruction you give a model to get a specific result. For images it describes the subject, the wardrobe, the setting, the light and the camera; for text it describes the task, the voice and the format. A good prompt is specific enough that two people running it get the same kind of output.
Do these prompts work on any model?
Usually, but not untouched. Every prompt here names the model it was tested on, because the same text on two models does not give the same picture. Moving one across normally means adjusting a clause or two rather than rewriting it.
Why do some prompts ask for my own photo?
Because they are built to keep a real face. Those prompts anchor identity to a photograph you upload, so the output is recognisably you rather than a generic person. Every prompt that needs one says so on its card, before you copy anything.
Can I use these commercially?
Yes. Copy any published prompt, change it, run it in any tool, and use what it produces in paid work. No attribution is needed. The one thing not permitted is copying the library wholesale and republishing it.
Does it cost anything?
No. Every published prompt is free and complete, including the settings it needs and the output it produced. The site is supported by advertising rather than by putting the text behind a wall.