Help for typedporn
How to write prompts, what the site does with your text and why an image sometimes fails.
Create page
Above the prompt field are the aspect ratio, the cut-outs button and links here. Below the field are two buttons: “Improve prompt” and “Generate”. Everything else about generation is below.
World rules
Every world has its own rules: what may and may not be drawn in it. The world’s generator sets them, and they are named here as it names them:
No world allows children or teenagers in any explicit form. An image with forbidden content is rejected by the check, and its tokens are returned.
Prices
Tokens for an image are charged when the picture is ready. If it fails, they are returned in full.
“Improve prompt” is charged for every press. You can bring your own text back while you stay on the page — the tokens for improving are not returned.
Your own face in the image
The face button above the prompt field opens your cut-outs. Tick a face and the generator gives it to the heroine or hero of the image. The site recognises people by itself and groups their faces under one name; you can correct the name.
You can name a face right in the prompt: <face:1> — the first of the faces ticked in the faces window, <face:Name> — a person’s face from the faces window by name, even if nothing is ticked. If the prompt has such tags, only the faces they name go into the image; the generator does not see the tags themselves.
You can set the frame ratio with a tag, like in Midjourney: <ar:5:7> or <ratio:5:7> — numbers from 1 to 99, from 1:3 to 3:1. The tag overrides the ratio button; pressing the button rewrites the tag. A ratio out of range turns red and the job is not sent.
The “Body and frame” button has sliders for build, breasts, skin tone, angle, light and other generator controls. The weight goes into the prompt as a tag <ctl:breast_size:1.2>; 0 turns the control off. Move 3–4 sliders per image, no more: otherwise the picture “drifts”. “Age” can only be raised. Set words (poses, clothes, styles, camera, light) are in the “Tags ?” window: a word in the prompt switches its set on by itself.
The generator of this world takes faces only. Body cut-outs do not go into the image — the site removes them itself and says so in the report.
Using faces requires consent — it is asked at your first cut-out. Use only your own face or the face of a person who agreed to it.
An image with a cut-out stays in your private gallery and is not published in the public one.
Which language to write in
The world’s generator reads only English. Write in English — or in Russian: before creating the image the site translates the prompt for free and shows the translation in the field.
The translation keeps names and English words as they are and adds nothing of its own. If the translation came out incomplete, the site does not accept it and your text stays in the field.
Improve prompt and random details
The button says what the next press will do: “formatting” — the text becomes short English phrases separated by commas, nothing new is added; “+ details and setting”; “+ frame work”; “new scene” — a ready scene of this world with your people. Add something of your own and the cycle starts again.
When the field is empty, the button is called “Write a prompt” and puts a ready scene of this world into the field.
Under the field are random details: emotion, body, hair, clothes, pose, place, time of day, weather, light, angle, photo style and “New scene”. A roll writes the result into your prompt and replaces the previous result of the same item. If the AI lost too many of your words while doing it, the roll is not written in and no token is charged.
The price is in the “Prices” line above.
How to write a prompt
The generator of this world is a photorealistic model of the Pony family. It reads short English phrases separated by commas, and the first words weigh more than the last.
The example button erases nothing: the example is added after what is already in the field, and the frame ratio stays yours.
Short phrases separated by commas→
One phrase — one idea, 2–6 words. The order that works: who and how many → appearance → pose and action → clothes → place → light → camera.
adult woman in her thirties, long dark hair, sitting on a windowsill, reading a letter, silk robe, quiet loft at dawn, soft window light, medium shot, 50mm lens
It will read long sentences too, but it understands the links between their parts worse — the picture is assembled at random.
What comes first matters most
The beginning of the prompt weighs the most. Put people and what must be in the frame first, background and mood at the end.
One or two main phrases can be strengthened with a weight: (red silk dress:1.2). Do not go above 1.3 — the picture starts to break.
Shorter is more precise→
Every phrase splits attention. Ten clear phrases work better than forty. If the result is “almost it”, remove the extra rather than adding more.
Light and angle matter more than adjectives→
“Beautiful”, “masterpiece”, “8k”, “best quality” give nothing — the generator adds quality tags itself. What changes the frame is the light source and the camera: backlight, soft window light, candlelight, close-up, full body, low angle, 85mm lens.
Style — in words
The generator switches style sets on by itself — from the words of the prompt. Want a style — name it: neon night city, steampunk city, retro photo, cinematic film still, dark moody low key, bokeh. Hands and detail are always improved, no need to ask.
Two or more people→
Give the number of people and describe each separately: age, pose, where the hands and legs are, where the bodies touch. Without that the generator mixes up whose hand is whose and draws extra limbs.
Standing figures come out cleaner than lying ones, one person cleaner than two. If the hands came out crooked, simplify the pose rather than asking for “correct hands”.
Comparisons are drawn literally
“Like a panther”, “predator and prey”, “a cornered animal” — the generator draws an animal in the frame. Write what is visible: the pose and the expression — tense crouch, predatory gaze.
What not to draw — don’t write
There is no “exclude” field: the world sets its own exclusion list. In a prompt, “without clothes on him” reads as “clothes”: the generator does not know the word “without”. Write what must be in the frame.
A face from a cut-out and the prompt
If your face is in the image, do not describe facial features — eye colour, nose shape, the age of the face. They argue with the cut-out, and the face comes out like nobody. Describe the pose, clothes, light and place.
Why it came out “wrong”
In order of frequency: long sentences instead of phrases; too many phrases; a comparison drawn as an object; a contradiction inside the prompt (“night” and “sunlight”); neither light nor angle named; two people without poses.
Adults and the check
An adult site. A model checks every prompt and every finished image: in an explicit scene all people must be clearly adults.
Give the age in words
The most common reason for a refusal is an unclear age. Write it for every person: adult woman in her thirties, man in his forties. For fantasy heroines and creatures (“dragoness”, “elf woman”) the age is needed even more — there is nothing to guess it from.
Words that lead to a refusal
Child words are refused before drawing, and the tokens come back: child, kid, teen, schoolgirl, loli, underage and an age under 18 in numbers (“16 years old”). “Girl”, “young” and “petite” are ordinary words for adults — still give the age in words.
Captivity, beatings, “prey”, coercion next to an explicit scene are also read by the model as helplessness. Explicit scenes — only with the consent of adults.
What “Request rejected” means
The check did not let the prompt through — generation did not start, tokens are returned. “Image rejected” means the picture is ready but did not pass the check; tokens are returned too.
The model’s reason in words is in the diagnostics report (Ctrl+Alt+D). Send it to support if a refusal looks like a mistake.
Child protection is not relaxed for anyone: an age refusal cannot be appealed, only the prompt can be fixed.
Site and tokens
How much a generation costs
The cost is given in the “Prices” line. Tokens are not taken when you press, but when the job goes into assembly — that is, when it actually starts being computed. They are charged when the picture is ready.
Not enough tokens — what happens
There is no refusal. The job joins the queue and waits, just as it waits for a returning service. Top up your balance and it goes into assembly by itself, without a single press.
Can I press “Create” many times in a row
Yes, as many as you like. There is no limit on how often you press: each press is paid and becomes a separate job in the queue. One is computed at a time, the others wait their turn — but are not lost.
The image failed — what about the tokens
They are returned in full. No exceptions: no picture — no payment. The card keeps the reason for the failure.
What “Retry” does on a failed image
Puts it back at the end of the queue. It is not an attempt to get the same picture: the retry has its own seed, so the result will differ — and that is right, because there was no picture to repeat in the first place.
For the same reason, pressing again with the same prompt will not give the same picture: the seed is new every time.
The image was rejected by the check
The prompt or the finished image did not pass the check. Tokens are returned. Change the prompt — what most often gets in the way in this world is described under “How to write a prompt”.
Why the image is waiting in the queue
The generator draws one image at a time. Yours waits its turn; its place is shown on the card. No need to keep the tab open — the job continues.
The bar at the bottom of the window
The site talks to you through one line at the bottom — your balance, your place in the queue, the reason for a refusal. It appears when there is something to say and slides away by itself. A normal message is pale, yellow means “not everything works”, red means “not working”.
Ctrl+Alt+D builds a diagnostics report: a screenshot, the event log and the passports of your generations. Send it to support if something goes wrong.
The site build you are looking at: —. Mention it when reporting a problem — the number shows exactly what you have open.
Paying with ether
The payment window shows only the wallet address and the exact ETH amount. The amount is unique — that is how the payment is recognised, so send exactly that.
Publishing
What “publish” means
The image goes to the public gallery and to your author page. Everyone will see it, including people who are not signed in.
The public gallery shows the newest images first, without curation: the later an image is published, the higher it stands.
Author page
A separate page with all your published images. You can share its link with anyone — no sign-in is needed to view it. The cover, the avatar and the name are changed in your profile: click the avatar or the name right there. The “Open my author page” link is in your profile, to the right of the name.
Country
The country flag appears next to your name on every image. It is your choice: if you do not want the badge, do not set a country.
Can I unpublish
Yes, with the same action on the card. The image comes back to you and disappears from the public gallery.
Support
Something does not work, tokens went missing or you need advice — write to us. Real people answer, and the conversation is kept in your request.
Chat with support. Describe what you did and what you saw — and attach a screenshot if you have one. That way we answer faster.
You need to sign in to contact us. Direct link to the chat: /help#supportDocuments
The site’s rules in plain words and legally precise. Each section starts with a short summary.