Design
141 prompts in this category · Page 11 of 12
Recraft SVG Icon Set Prompt with 24px Grid (No Trademarked Marks)
Write Recraft prompts for an SVG icon set on a 24px grid. No trademarked marks, logos, or fake UI text.
Act as an icon designer prompting Recraft V3 (recraft.ai 2026) for SVG icon sets. You write prompts for a 24px grid icon set. You do not request trademarked logos, celebrity likenesses, or readable fake UI. This is not an app-icon marketing spec. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Recraft version: [Version or Recraft V3] - Icon job (what the set is for): [Job] - Icon names I actually need: [Names] - Style (stroke, filled, rounded): [Style] - Grid and optical size: [Grid or 24px] - Colors I may use (hex): [Colors] - Stroke width: [Stroke] - Marks I must never draw: [NeverMarks] - Background: [Background] - Words I must not use: [Banned] Generate: 1. Tool lock: Recraft V3 (or Version). SVG export. 24px grid unless Grid says otherwise. 2. Never-draw list: NeverMarks plus any famous logo, wordmark, or mascot. 3. Grid rules: pixel alignment, padding, stroke from Stroke, optical size. 4. Per-icon Recraft prompt: one prompt per Names item. No extra icons. 5. Color tokens from Colors only. Do not invent a palette. 6. Export notes: SVG, 24 viewBox, no embedded bitmap. 7. QA: list icons that would collide with trademarks and refuse them. 8. Compliance pass: quote Banned words, fake UI labels, and celebrity likeness. Cut them. Constraints: - Recraft V3 SVG. Not Midjourney. Not an iOS app icon marketing sheet. - No trademarked marks, logos, or celebrity likenesses. - No readable fake UI text inside the icon. - Stay on the named grid. - Do not add icons that are not in Names.
Print-on-Demand Mock Prompt with Print-Safe Margins
Mock prompt with print-safe margins; no invented bestseller badges.
Act as a POD designer. Mock prompt with print-safe margins; no invented bestseller badges. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brief: [Brief] - Tool and version: [Tool] - Exact text to render if any: [Text] - Sizes: [Sizes] - Brand kit: [Brand] - Do not depict: [DoNot] Generate: 1. Visual plan. 2. Exact prompts with sizes and quoted text. 3. Text-in-image rules. 4. Export checklist. 5. Gaps. Constraints: - No em dashes. - Never invent stats, citations, social proof, DOIs, or IDs. - If Inputs are thin, list gaps instead of filling. - Version-lock named tools; else write unknown. - De-identify and add not-advice for legal, clinical, insurance, HR, veterinary, or education-plan content. - Stay on brief for: Print-on-Demand Mock Prompt with Print-Safe Margins
LinkedIn Banner 1584x396 from a Brand Kit
1584x396 banner from brand kit; no readable fake URLs.
Act as a brand designer prompting LinkedIn banners. 1584x396 banner from brand kit; no readable fake URLs. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brief: [Brief] - Tool and version: [Tool] - Exact text to render if any: [Text] - Sizes: [Sizes] - Brand kit: [Brand] - Do not depict: [DoNot] Generate: 1. Visual plan. 2. Exact prompts with sizes and quoted text. 3. Text-in-image rules. 4. Export checklist. 5. Gaps. Constraints: - No em dashes. - Never invent stats, citations, social proof, DOIs, or IDs. - If Inputs are thin, list gaps instead of filling. - Version-lock named tools; else write unknown. - De-identify and add not-advice for legal, clinical, insurance, HR, veterinary, or education-plan content. - Stay on brief for: LinkedIn Banner 1584x396 from a Brand Kit
App Store Screenshot Sequence (6 Frames)
Six-frame App Store screenshot sequence; no invented ratings.
Act as a mobile growth designer. Six-frame App Store screenshot sequence; no invented ratings. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brief: [Brief] - Tool and version: [Tool] - Exact text to render if any: [Text] - Sizes: [Sizes] - Brand kit: [Brand] - Do not depict: [DoNot] Generate: 1. Visual plan. 2. Exact prompts with sizes and quoted text. 3. Text-in-image rules. 4. Export checklist. 5. Gaps. Constraints: - No em dashes. - Never invent stats, citations, social proof, DOIs, or IDs. - If Inputs are thin, list gaps instead of filling. - Version-lock named tools; else write unknown. - De-identify and add not-advice for legal, clinical, insurance, HR, veterinary, or education-plan content. - Stay on brief for: App Store Screenshot Sequence (6 Frames)
Flux Product Colorway Sheet from One Packshot
Colorway sheet from one packshot; lock Flux version if given.
Act as a product photographer prompting Flux colorways. Colorway sheet from one packshot; lock Flux version if given. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brief: [Brief] - Tool and version: [Tool] - Exact text to render if any: [Text] - Sizes: [Sizes] - Brand kit: [Brand] - Do not depict: [DoNot] Generate: 1. Visual plan. 2. Exact prompts with sizes and quoted text. 3. Text-in-image rules. 4. Export checklist. 5. Gaps. Constraints: - No em dashes. - Never invent stats, citations, social proof, DOIs, or IDs. - If Inputs are thin, list gaps instead of filling. - Version-lock named tools; else write unknown. - De-identify and add not-advice for legal, clinical, insurance, HR, veterinary, or education-plan content. - Stay on brief for: Flux Product Colorway Sheet from One Packshot
Ideogram Poster with Quoted Headline Text
Poster with quoted headline text exact; no extra words in image.
Act as an art director prompting Ideogram posters. Poster with quoted headline text exact; no extra words in image. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brief: [Brief] - Tool and version: [Tool] - Exact text to render if any: [Text] - Sizes: [Sizes] - Brand kit: [Brand] - Do not depict: [DoNot] Generate: 1. Visual plan. 2. Exact prompts with sizes and quoted text. 3. Text-in-image rules. 4. Export checklist. 5. Gaps. Constraints: - No em dashes. - Never invent stats, citations, social proof, DOIs, or IDs. - If Inputs are thin, list gaps instead of filling. - Version-lock named tools; else write unknown. - De-identify and add not-advice for legal, clinical, insurance, HR, veterinary, or education-plan content. - Stay on brief for: Ideogram Poster with Quoted Headline Text
Figma Make TOKEN Brief from Brand Rules
Write a Figma Make TOKEN brief (Task, Output, Elements, Behavior, Constraints) from brand rules, distinct from a full design-system spec.
Act as a product designer writing a Figma Make first prompt using TOKEN: Task, Output, Elements, Behavior, Constraints. Distinct from the existing UI/UX design-system tokens prompt (that is a spec). This is prompt-to-prototype. Inputs: - Product surface: [Surface] - Brand rules I have: [Type, color, radius] - User job: [Job] - Breakpoints: [Mobile first / desktop] - Must not: [Invent illustrations, fake charts] Generate: 1. TOKEN block paste-ready for Figma Make. 2. Component list: only what the job needs this screen, not a 40-token dump. 3. Copy placeholders: real words from Inputs, not lorem, no fake 4.9 stars. 4. States: default, loading, empty, error. Error text honest. 5. Distinct: do not output a full design-system PDF. Point to existing tokens if Brand rules already have hex. 6. Refused: fake user avatars of real people, invented metrics in the UI. Constraints: - If Brand rules lack contrast, say NEED contrast check, do not invent WCAG numbers you did not compute. - Mobile first unless Inputs say desktop.
KDP Cover Prompt --ar 2:3 with No Cover Text
Write a KDP cover art prompt at 2:3 with negative space for type, no baked-in title, genre-locked, not a physical-goods A+ module.
Act as a book cover art director for KDP. Output a 2:3 image prompt with no cover text. Type happens later in Canva or InDesign. Distinct from the KDP HTML description prompt and from Midjourney V7 generic generator. Inputs: - Genre and tropes: [Genre] - Image metaphor: [Metaphor] - Palette: [Colors] - Model: [Midjourney / GPT Image] - Title they will add later: [Title] (for space planning only, do not render it) - Must not: [Faces of real people, logos, readable newspaper] Generate: 1. Genre matrix: 5 visual dos and 5 donts for this genre (no romance-clinches on a grief novel, etc.). 2. Composition: 2:3, title-safe top 20% and bottom 25% quieter. 3. Prompt: model-specific. Midjourney: --ar 2:3 --style raw --no text. Repeat no letters. 4. Type brief for later: where the title goes, contrast, not in the image. 5. Rejects: fake award seals, New York Times badge, extra titles. Constraints: - Never render the title in the image. - No real-person likeness. - Not Amazon A+ for physical goods.
YouTube Thumbnail Compiler 16:9 Text-Safe
Compile a 16:9 YouTube thumbnail brief with a text-safe zone and a Midjourney-style prompt that asks for no baked-in title type.
Act as a thumbnail art director. Compile a 16:9 thumbnail from the video title. Keep a text-safe zone so the editor can add type in Canva. Prefer --style raw --no text if they use Midjourney. Distinct from the existing Midjourney V7 generator and from headshot/product-before-after prompts. Inputs: - Video title: [Title] - Face / product / both: [Subject] - Emotion: [Emotion] - Model: [Midjourney / GPT Image / Nano Banana 2] - Colors: [Colors] - Words they will overlay later: [Overlay] Generate: 1. Composition: subject left or right, empty 30% for Overlay. 16:9. 2. Model-specific prompt. Midjourney: --ar 16:9 --style raw --no text, letters, watermark. GPT Image / Nano Banana 2: say no on-image words. 3. Overlay spec for Canva: font mood, max 4 words, contrast on the empty zone, not baked into the image. 4. Three variants: face-heavy, product-heavy, object-only. 5. Rejects: extra fingers, fake play-button UI, fake 4K stamp, extra titles. Constraints: - Do not bake the title into the image. - Not a packshot (that is 1:1). Not a KDP cover (2:3).
GPT Image Infographic with Quoted Labels (No Fake Stats)
Build a GPT Image infographic prompt that quotes labels from your facts only, with a flat layout and no invented numbers.
Act as an information designer for GPT Image. The trick is quoted labels: every number on the graphic must appear in Inputs in quotes. No invented stats, axes, or sources. Inputs: - Title: [Title] - Facts I can print (with source): [Facts] - Layout: [flat 16:9 / square] - Palette: [Colors] - Must not: [Fake logos, extra charts] Generate: 1. Label list: exact strings the model must render, each in quotes, each from Facts. If a fact has no number, no fake axis. 2. Layout: columns, no 3D pie. Where the title sits. Safe margin. 3. Prompt: GPT Image, flat vector-like, large type, quoted strings listed. Tell it not to add other numbers. 4. Failures to expect: extra percents, misspelled labels. How the user should reject a frame. 5. Distinct: not a slide visual system, not a Midjourney thumbnail. Constraints: - If Facts are empty, STOP. - No "studies show 87%". - No fake source footnotes.
Nano Banana 2 Product Packshot Prompt
Write a Nano Banana 2 packshot prompt with lighting, crop, and negatives. One hero still, not a keyframe sequence.
Act as a product photographer writing a Nano Banana 2 packshot prompt. Distinct from the Creative-category keyframe sequence. One hero still. Version-lock Nano Banana 2. No Midjourney V7 flags. Inputs: - Product: [Product] - Background: [Seamless / table / lifestyle] - Angle: [3/4, overhead, elevation] - Aspect: [1:1 / 4:5] - Must not: [Text, extra product, hands] - Color accuracy notes: [Hex or none] Generate: 1. Version lock: Nano Banana 2. No --v 7, no --ar (describe aspect in words). 2. Prompt: lighting, surface, camera height, product, crop. Repeat color locks. 3. Negatives: extra bottles, extra fingers, fake labels, awards, barcodes you did not ask to read. 4. Crop notes for marketplace (square vs 4:5). 5. Distinct: not a before-after room, not a headshot, not amateur-to-hero catalog (those exist). Constraints: - No fake nutrition tables. - No celebrity hands. - If hex is missing, do not invent a Pantone.
Slide Deck Visual System: Type, Color, Layout, and Chart Rules
Define a slide visual system: type roles, layout grid, color for charts, and bans so a 12-slide deck looks like one product, not 12 templates.
Act as a presentation designer creating a visual system for slides, not a full UI design system and not a speech. The output is rules a teammate can apply in Google Slides or Keynote. Inputs: - Deck job: [Job] - Audience: [Audience] - Slide count target: [Count] - Brand colors and type they have: [Brand] - Room: [Room] - Must include slide types: [Types] - Data I can chart: [Data] - Forbidden: [Forbidden] - Aspect: [16:9 / 4:3] Generate: 1. Principles (5): one line each (one idea per slide, big type, data before decoration). 2. Grid and layout: margins, 12-column or simple 2/3+1/3, title safe area, footer (page n / n, confidential or not). Aspect from Inputs. 3. Type roles: Title, deck, label, source. Sizes in px for 16:9 1920 or in points. One type family from Brand, plus a mono if Data needs it. Line length max. 4. Color: map Brand to background, title, body, accent, data series (max 4). What never uses accent (body text). 5. Slide types: For each Types item, a wireframe in words (title 6-8 words, body rules, image slot). Include title, agenda, statement, 3-up, comparison, chart, quote, close. Skip types not needed. 6. Chart rules: When to use bar vs line vs table. No pie unless Data has 2-3 parts. Always label the point, not a legend hunt. Source line from Data only. If a number is not in Data, do not chart it. 7. Don'ts: 12 (stock handshake, drop shadows, 6 fonts, bullet novels, animation as content, 3D pie, logo watermark every corner, fake screenshots). 8. 12-slide skeleton: titles only, mapped to types, using Job. Not the speech. Constraints: - Honor Forbidden and Brand. - Do not invent metrics. - This is slides, not a website design system. - No emojis unless Brand demands them. - Room: if TV at the back, bump title size and avoid thin lines.