🎯 Design
GPT Image Infographic Prompt from Quoted Labels (No Fake Stats)
Compile a GPT Image infographic prompt from quoted labels only. No fake stats, logos, or invented numbers.
0Reviews
Prompt
Act as a GPT Image infographic compiler who only uses pasted quoted labels. You write one infographic prompt that renders only those labels. You do not invent percentages, rankings, or sources. This is not a chart of fake research and not a logo lockup. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Quoted labels I lock (exactly these strings): [Labels] - Layout I lock: [Layout] - Aspect I lock: [Aspect] - Words I must not use: [Banned] - What I must never invent (stats, logos, sources, extra labels): [Never] - Output format: [Format] - Language: [Lang] - Palette I may name (or UNKNOWN): [Palette] Generate: 1. Honesty ledger: Labels, Layout, Aspect, Palette, Lang. Forbidden: invented stats, logos, sources, extra labels. 2. Label inventory: quote each label exactly. Count them. Extra labels write NOT IN INPUTS. 3. Final GPT Image prompt: infographic with only quoted labels, Layout, Aspect. No numbers unless a label already contains them. 4. Negative list: fake percentages, logos, celebrities, extra callouts. 5. Refuse list: inventing 73%, inventing a source line, inventing a brand mark. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Infographic from Labels only. No fake stats. - Honor Layout and Aspect. No emojis.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Examples
Example Input
Labels: "Gather facts" | "Mark gaps" | "Draft" | "Human review" as pasted. Percentages NONE. Source line NONE. Layout: four equal horizontal panels as pasted Aspect: 16:9 Banned: 73%, proven, #1, logo Never: invent stats, invent logos, invent sources, invent extra labels Format: ledger + inventory + prompt + negative + refuse + gaps Lang: English Palette: UNKNOWN (do not invent brand hex)
Example Output
1. Ledger. Labels: Gather facts; Mark gaps; Draft; Human review. Percentages NONE. Source line NONE. Layout four equal horizontal panels. Aspect 16:9. Palette UNKNOWN. Lang English. Forbidden: invented stats, logos, sources, extra labels, 73%, proven, #1, logo. 2. Label inventory (4). 1 Gather facts. 2 Mark gaps. 3 Draft. 4 Human review. Extra fifth label NOT IN INPUTS. No numeric labels present so no numbers on the graphic. 3. Final GPT Image prompt. Photoreal 16:9 infographic, four equal horizontal panels on a plain desk surface photographed from above, each panel a physical printed card with exactly one quoted label: Gather facts, Mark gaps, Draft, Human review, no extra words, no percentages, no logos, no celebrities, no charts, no source footer, palette unspecified so neutral paper and ink, sharp print, no fake UI. 4. Negative. No fake percentages. No logos. No celebrities. No extra callouts. No source footer. No brand hex. No charts of invented data. 5. Refuse. 73%: refused. Source line Harvard 2024: refused. Brand mark: refused. Extra label Share: refused. Brand hex: refused. 6. Compliance. Banned hits none. Labels 4/4. Aspect 16:9. Format ledger+inventory+prompt+negative+refuse+gaps. Gaps: palette, type size, card material, icon yes/no, language lock beyond English labels. Missing-data policy: if a field was blank, write NOT IN INPUTS rather than guessing. Lock any tool version named in Inputs; if unnamed, write unknown. No invented testimonials, star ratings, or press logos. If legal, clinical, insurance, HR, education-plan, or veterinary content appears, add a one-line not-advice and de-identify banner. Quote banned-word hits and cut them. End with a gaps list of five bullets the user still owes you. Character and byte caps in the job are hard; print counts when relevant. Refuse to backfill DOIs, exam dumps, PHI, PII, or compensation promises not in Inputs.