{"slug":"image-prompts-one-style","name":"Image Prompts in One Style: Clean Pictures for a Site","version":"1.0.3","updated_at":"2026-10-09T08:44:54.628Z","use_when":"Writes prompts for image models (FLUX, Stable Diffusion, ChatGPT images, Gemini and the like) that give a website, a blog or a product one recognisable style and come back without garbled letters. The scene comes first and the site's style recipe follows it word for word; absence is described positively instead of \"no text, no watermark\", which in a single prompt box summons those very things; anything that would need readable writing (a price list, a chart, a date) becomes a metaphor without characters; the scene ends with a closed list of what is in it; people and hands, the usual weak spots, are shown through objects; the aspect ratio is stated in numbers; and several pictures become several prompts, never one. Use when you write or fix prompts for hero images, blog headers, cards or illustrations, when generated pictures come back with pseudo-letters, cluttered scenes or a different style each time, or when a brief arrives in another language.","not_for":"Generating the pictures themselves, editing or retouching existing images, logos or typography that must carry real text, photo-realistic portraits of real people, or choosing a brand's colours from scratch. It writes and fixes the prompts you send to an image tool and keeps every picture in the style you already have.","languages":["any"],"tags":["image-prompts","ai-images","flux","illustrations","brand-style","hero-image"],"category":"marketing","category_url":"https://aiskills402.com/categories/marketing","keywords":["garbled letters","hero images","image models"],"faq":[{"q":"Where do the smeared letters in generated pictures come from?","a":"Usually because the prompt asks for them, often without meaning to. A sign, a menu board, a document or a dial invites writing, and in a tool with one prompt box a line like 'no text, no logo' is read as a request for text and logos too. The skill turns such objects into shapes and light, gives the unavoidable ones a blank face and describes clean surfaces positively, so there is nothing for the model to spell."},{"q":"How does it keep every picture in the same style?","a":"Your style recipe, one paragraph about medium, light, background, palette and the single accent colour, goes into every prompt word for word and after the scene, never paraphrased. Each prompt ends its scene with a closed list of what is in it, states the frame in numbers, and several pictures become several prompts, each one complete, so nothing turns into a collage or drifts between images."},{"q":"Does it help Claude Sonnet?","a":"Markedly, on every trap. We gave Sonnet and Haiku twelve image briefs, ten of them built around a trap such as a menu board, an invoice total, a smiling support agent or a user asking for no logo, and code checked each prompt. Left alone, Sonnet wrote rich prompts but answered a request for a clean picture with lists of bans in ten of them, named the writing it meant to avoid and drew faces; with the file loaded, all twelve came out clean. Counting the defects alone, it went from one to twelve; Haiku from one to nine."},{"q":"Did the cleaner prompts give cleaner pictures?","a":"In FLUX, clearly; in ChatGPT, not visibly. On 9 October 2026 we sent three trap briefs (a menu board, an invoice total, a road sign) to both tools, once with the prompt written without the file and once with it. In FLUX schnell the plain prompts gave a board covered in pseudo-letters although they asked for none, an invoice amount with the wrong figures and a sign missing its house number; the guided prompts gave three clean pictures. ChatGPT drew all twelve of its pictures cleanly either way, writing a requested amount or street name correctly. One run per picture: a probe, not a benchmark."}],"examples":[{"lang":"en","model":"claude-sonnet-5-5","input_excerpt":"Hero image for our restaurant's website: the chalkboard menu next to the entrance, listing today's dishes and their prices.","output_excerpt":"A soft clay standing board with a rounded frame leans beside an arched restaurant doorway, seen straight on at eye level and centred, with generous empty space around it. On the board face, rows of short rounded clay bars of different lengths sit slightly raised, each row ending in a small round dot, and a single bar in vivid teal is the focal point. Wide landscape, 3:2, 1536x1024.…"},{"lang":"bg","model":"claude-sonnet-5-5","input_excerpt":"Снимка за статия „Как се пише фактура“: фактура на бюро, на която се вижда крайната сума, а до нея химикалка.","output_excerpt":"A single sheet of paper lying flat on a sand-coloured desk, seen from slightly above and centred, with a pen resting diagonally beside it. The sheet carries rows of short navy bars of different lengths stacked down its face, and at the bottom a wide rounded coral block glows as the one accent, drawing the eye to the end of the rows. The pen has a navy body and a coral tip.…"}],"page_url":"https://aiskills402.com/skills/image-prompts-one-style","markdown_url":"https://aiskills402.com/skills/image-prompts-one-style.md","image_url":"https://cdn.aiskills402.com/og/skills/image-prompts-one-style/eecebe78.png","related_url":"https://api.aiskills402.com/v1/skills/image-prompts-one-style/related","purchases_count":null,"tested":{"date":"2026-10-09","strong":{"model":"claude-sonnet-5-5 (Claude Code alias \"sonnet\")","verdict":"Right on all 12 briefs, read by hand: every prompt opened with the scene and closed with the house style copied exactly, gave the frame in numbers and a closed list of objects, and described clean surfaces in positive words. It turned a chalkboard of dishes, an invoice total, a chart-filled laptop, a road sign with an address and a clock at five to twelve into plain shapes, showed a hiking group from behind with hands out of frame, put the unwanted things only in the separate negative box when the tool had one, wrote three complete prompts for three services, and wrote in English for the two Bulgarian briefs."},"weak":{"model":"claude-haiku-5-5 (Claude Code alias \"haiku\")","verdict":"Right on 9 of 12, but it missed three: it still named the dashboard on the laptop screen, kept one negation (no markings on the kettle) in the coffee prompt where the user had asked for no text and no logo, and put a line of its own notes before one prompt although only the prompt was asked for. The order, the house style, the frame, the closed list and the people rule held in every answer."},"note":"Twelve image briefs written by us for two house styles: ten with a trap (writing on a menu board, an invoice total, a chart-filled screen, a road sign with an address, a clock showing a time, a group of hikers, a smiling support agent, a user who asks for 'no text, no logo', three images at once, a tool with a separate negative box) and two plain controls; two briefs are in Bulgarian. The request is the same on both sides and states the tool, the house style word for word, 'premium, without the usual defects of AI images' and 'return only the prompt'. Code checks the prompt, not a picture: English, the style copied exactly, the scene before the style, a closed list, the frame in numbers, no negations in the prompt box, no words that ask for writing or name what a shape stands for, people only from behind or far away and without faces, one complete prompt per picture. Facts from the FLUX prompting guide (re-read 2026-10-09): there is no negative-prompt field, the wanted scene is described instead, a text-to-image request without references comes back square, the subject comes first. Owner-measured and NOT re-checked: a list of forbidden things in a FLUX prompt filled the picture with letters, a dial carried digits until the scene was a closed list, and ChatGPT made one collage from three scenes in one message and a square when no frame was given. Checks widened after the run, for both sides, each after a defensible answer was refused: people seen from behind or in the distance with hands out of frame, a tile grid in a bathroom, twelve dots as hour markers, and a curve shaped like a smile. The skill was also changed once after the first run (describe a shape by its look, not by the value it stands for) and its side was re-run in full. One run per model and brief. Picture probe after the test, on 9 October 2026: three trap briefs (menu board, invoice total, road sign) went to ChatGPT with the plain and the guided prompt, in two rounds (the second asked it to ignore its memory and saved preferences, because the account keeps the owner's own rules for pictures). None of the twelve pictures had garbled letters; ChatGPT wrote the requested amount and street name cleanly; stray objects appeared once in the first round only. A third round went to FLUX schnell (Cloudflare Workers AI): the plain prompts gave a board with pseudo-letters despite asking for none, a wrong amount and a sign without its number; the guided prompts gave three clean pictures. One run per picture.","baseline":{"date":"2026-10-09","rows":[{"label":"Prompts right on every check (12 prompts)","better":"higher","strong":{"with":{"n":12,"of":12},"without":{"n":0,"of":12}},"weak":{"with":{"n":9,"of":12},"without":{"n":0,"of":12}}},{"label":"Prompts free of the defects alone (12 prompts)","better":"higher","strong":{"with":{"n":12,"of":12},"without":{"n":1,"of":12}},"weak":{"with":{"n":9,"of":12},"without":{"n":1,"of":12}}}],"note":"Same request on both sides. The second row leaves out the three structure checks the request never states (scene before style, closed list, frame in numbers) and counts only defects: negations, words that summon writing, faces, collages, language and the exact style; the price follows that stricter row. Read by hand, Sonnet without the skill wrote careful, vivid prompts and kept the house style exactly, but in 10 of 12 it answered the request for a clean picture with a list of bans (no text, no letters, no logos, no watermark), which a one-box tool reads as a request for those things; it also named the menu, the dashboard, the street name and the time on the clock, drew the smiling agent and the laughing hikers with their faces, and put the style before the scene every time. Haiku without the skill made the same moves."},"report_url":null},"price_usd":"0.05","price_micro":50000,"size_bytes":8568,"sha256":"85292656693b4dcab29e1645dd8fa02a3b047659d2816ebb1913846b060b65e4","outline":["The house style is written once","Order: scene first, recipe after","Say what is there, not what is missing","Writing becomes a metaphor","Close the scene","People through objects","Format in numbers","One picture, one prompt","Language","What to deliver","Reviewing the result","Short example"],"license":{"summary":"Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing","holder":"Georgi Kalchev, aiskills402.com","url":"https://aiskills402.com/docs#license"},"buy_url":"https://api.aiskills402.com/v1/skills/image-prompts-one-style/file","redownload_url_template":"https://api.aiskills402.com/v1/purchases/{token}","mcp_tool":null,"payment":{"protocol":"x402","scheme":"exact","asset":"USDC","selling":true,"network":"base","network_caip2":"eip155:8453","pay_to":"0x8e37022edcf0f21cf3c9f93fee9d4d32519f36f4","facilitator":"cdp"},"seo_title":"Image Prompts That Keep One Clean Style","seo_description":"Image prompts that keep one style across a site and come back without garbled text or clutter, for FLUX and ChatGPT. Pay $0.05 once, in USDC.","versions":[{"version":"1.0.3","date":"2026-10-09","changelog":"# Changelog\n\n## 1.0.0 — 2026-10-09\n\nFirst release: writes prompts for image models that keep a site's pictures in one style and free of garbled writing. The scene comes first and the house style recipe follows word for word; absence is described positively instead of with \"no\" in a single prompt box, while a separate negative field takes the unwanted things; anything that needs readable writing becomes a metaphor and objects that carry writing are left out or given a blank face; each scene ends with a closed list; people and hands are shown through objects; the frame is stated in numbers; several pictures become several complete prompts; prompts are in English whatever the language of the brief. Twelve cases; test/control.mjs proves right prompts pass and wrong ones fail. Before the run, the meeting case was replaced by a hiking group because the skill's own example (cups and a laptop at a table) was its answer, and two words that matched case checks exactly were taken out of the skill. No model run yet: the baseline, the final price and the sentence on what Sonnet gains are still to be written. Price 10000 is provisional.\n\n## 1.0.1 — 2026-10-09 (finalised after the model test)\n\n- After the first run the skill gained one rule: describe a shape by its look, never by the value, time or figure it stands for (both models had written \"a bar for the final total\" and named \"the dashboard\"); the skill side was re-run in full.\n- Measured on 12 briefs, same request on both sides: every check — Sonnet 0 -> 12, Haiku 0 -> 9; the defects alone (without the three structure checks the request never states) — Sonnet 1 -> 12, Haiku 1 -> 9.\n- Checks widened for both sides after defensible answers were refused: people from behind or in the distance with hands out of frame; a tile grid in a bathroom is not a collage; twelve dots as hour markers are not a written time; a curve shaped like a smile is not a face.\n- Price: $0.07 (Sonnet gain 11 on the stricter count, on owner-measured facts).\n\n## 1.0.2 — 2026-10-09\n\n- Price set by the owner to $0.03 and no Recommended badge, after a picture probe: three trap briefs sent to ChatGPT with the plain and the guided prompt gave six pictures without garbled letters (ChatGPT wrote the requested amount and street name cleanly); the difference was stray objects in the plain versions. The probe ran in an account whose memory holds the owner's own rules for pictures, so it is not neutral; FLUX was not tried. Card and test note say so. The skill text is unchanged.\n- Second picture probe the same day, asking ChatGPT to ignore its memory and saved preferences: again no garbled letters on either side, and the stray objects of the first round did not come back. The card says plainly that in today's ChatGPT the pictures came out about the same.\n\n## 1.0.3 — 2026-10-09\n\n- Picture probe in FLUX schnell (Cloudflare Workers AI), same three trap briefs: the plain prompts gave a menu board covered in pseudo-letters although they asked for no letters, an invoice amount with wrong figures and a road sign without its house number; the guided prompts gave three clean pictures. ChatGPT had drawn both sides cleanly. Price set by the owner to $0.05 and the Recommended badge added on that evidence. One run per picture.\n"},{"version":"1.0.2","date":"2026-10-09","changelog":"# Changelog\n\n## 1.0.0 — 2026-10-09\n\nFirst release: writes prompts for image models that keep a site's pictures in one style and free of garbled writing. The scene comes first and the house style recipe follows word for word; absence is described positively instead of with \"no\" in a single prompt box, while a separate negative field takes the unwanted things; anything that needs readable writing becomes a metaphor and objects that carry writing are left out or given a blank face; each scene ends with a closed list; people and hands are shown through objects; the frame is stated in numbers; several pictures become several complete prompts; prompts are in English whatever the language of the brief. Twelve cases; test/control.mjs proves right prompts pass and wrong ones fail. Before the run, the meeting case was replaced by a hiking group because the skill's own example (cups and a laptop at a table) was its answer, and two words that matched case checks exactly were taken out of the skill. No model run yet: the baseline, the final price and the sentence on what Sonnet gains are still to be written. Price 10000 is provisional.\n\n## 1.0.1 — 2026-10-09 (finalised after the model test)\n\n- After the first run the skill gained one rule: describe a shape by its look, never by the value, time or figure it stands for (both models had written \"a bar for the final total\" and named \"the dashboard\"); the skill side was re-run in full.\n- Measured on 12 briefs, same request on both sides: every check — Sonnet 0 -> 12, Haiku 0 -> 9; the defects alone (without the three structure checks the request never states) — Sonnet 1 -> 12, Haiku 1 -> 9.\n- Checks widened for both sides after defensible answers were refused: people from behind or in the distance with hands out of frame; a tile grid in a bathroom is not a collage; twelve dots as hour markers are not a written time; a curve shaped like a smile is not a face.\n- Price: $0.07 (Sonnet gain 11 on the stricter count, on owner-measured facts).\n\n## 1.0.2 — 2026-10-09\n\n- Price set by the owner to $0.03 and no Recommended badge, after a picture probe: three trap briefs sent to ChatGPT with the plain and the guided prompt gave six pictures without garbled letters (ChatGPT wrote the requested amount and street name cleanly); the difference was stray objects in the plain versions. The probe ran in an account whose memory holds the owner's own rules for pictures, so it is not neutral; FLUX was not tried. Card and test note say so. The skill text is unchanged.\n"},{"version":"1.0.0","date":"2026-10-09","changelog":"# Changelog\n\n## 1.0.0 — 2026-10-09\n\nFirst release: writes prompts for image models that keep a site's pictures in one style and free of garbled writing. The scene comes first and the house style recipe follows word for word; absence is described positively instead of with \"no\" in a single prompt box, while a separate negative field takes the unwanted things; anything that needs readable writing becomes a metaphor and objects that carry writing are left out or given a blank face; each scene ends with a closed list; people and hands are shown through objects; the frame is stated in numbers; several pictures become several complete prompts; prompts are in English whatever the language of the brief. Twelve cases; test/control.mjs proves right prompts pass and wrong ones fail. Before the run, the meeting case was replaced by a hiking group because the skill's own example (cups and a laptop at a table) was its answer, and two words that matched case checks exactly were taken out of the skill. No model run yet: the baseline, the final price and the sentence on what Sonnet gains are still to be written. Price 10000 is provisional.\n\n## 1.0.1 — 2026-10-09 (finalised after the model test)\n\n- After the first run the skill gained one rule: describe a shape by its look, never by the value, time or figure it stands for (both models had written \"a bar for the final total\" and named \"the dashboard\"); the skill side was re-run in full.\n- Measured on 12 briefs, same request on both sides: every check — Sonnet 0 -> 12, Haiku 0 -> 9; the defects alone (without the three structure checks the request never states) — Sonnet 1 -> 12, Haiku 1 -> 9.\n- Checks widened for both sides after defensible answers were refused: people from behind or in the distance with hands out of frame; a tile grid in a bathroom is not a collage; twelve dots as hour markers are not a written time; a curve shaped like a smile is not a face.\n- Price: $0.07 (Sonnet gain 11 on the stricter count, on owner-measured facts).\n"}]}