How to Prompt a Flux Infographic with Quoted Labels
Infographic prompts add a 40 percent callout and a fifth label. Quote the four labels. Flat 2x2. No hex if Colors was UNKNOWN.
The matching generator is the Flux Infographic Prompt with Quoted Labels (Flat Layout, No Fake Stats) (Flux Infographic Prompt Quoted Labels Flat Layout No Fake Stats) prompt. Browse related cards in the PromptDig library (Browse more prompts). When a filled run survives, share the version you actually use (Share a prompt).
Every on-image word is a quoted label
Write a Flux infographic prompt that quotes labels from Inputs and keeps a flat layout. No fake statistics. Not a GPT Image card. Start by filling Inputs, not by asking the model to remember last week's run. If a field is blank, write NONE or NOT IN INPUTS and leave it blank through Generate. The card is built so the model cannot honestly invent a number, owner, URL, or command that you did not paste.
Paste these fields before you hit run:
Labels I allow (quote these exactly): [Labels]
Layout I lock (flat, columns, rows): [Layout]
Colors I allow (or UNKNOWN): [Colors]
Aspect I lock: [Aspect or 16:9]
Words I must not use: [Banned]
What I must never invent (stats, extra words): [Never]
Flux version I lock (or UNKNOWN): [Version]
Output format: [Format]
Language for the prompt: [Lang]
Negative I lock: [Negative]
That inventory is the honesty ledger. Anything that does not appear there is forbidden in the draft. If you catch yourself adding a nice-to-have after the run, you are no longer using the card. You are ghostwriting. Put the extra fact in Inputs and run again.
Keep the layout flat as locked
Generate is numbered on purpose. Do not skip a step because the first paragraph looked done. The early steps exist to stop later prose from smuggling claims.
Walk the Generate list in order:
- Honesty ledger: Labels (each quoted), Layout, Colors, Aspect, Version, Lang. Forbidden: extra words on the image, invented %, GPT Image as the model.
- Flux prompt: model Flux, Version quoted or UNKNOWN. Flat layout from Layout. Scene with no extra body text. Embed each Label in quotes.
- Label map: a table of where each quoted label sits (left column, header, footer) using Layout only.
- Negative: quote Negative plus no fake stats, no extra captions, no logos unless a label is a logo word (it should not be).
- Refuse: GPT Image prompt block, Ideogram --magic, invented KPI numbers.
- Colors: quote Colors or UNKNOWN. Do not invent hex if UNKNOWN.
- Never: do not add a source line with a fake URL.
- Compliance pass: quote Banned and Never hits. Cut them. Format as Format.
If a step asks for a version lock, quote the version from Inputs in the output. If a step asks for a refuse list, keep the refuse list in the published artifact, not in a sidebar you delete. Reviewers should see what the model was not allowed to do.
Do not invent hex or percents
Most failures are the same shape: a missing field gets a confident fill. A conversion rate appears. A Gradle task appears. A flash point appears. A caption appears on a job that asked for slide text only. Your review is to search the draft for numbers, names, and commands, then grep Inputs. No match means cut.
Honor the constraints as hard stops, not vibes:
- Flux infographic from Labels. Not GPT Image and not Ideogram.
- Every on-image word is a quoted Label.
- No fake stats.
- No emojis unless a Label includes them.
When the card says not legal advice, not certification, not an exam dump, or not a caption engine, that sentence belongs at the top of the output. Deleting it to look more finished is how you inherit risk.
Refuse GPT Image and Ideogram blocks
Finish with the compliance pass the prompt already asks for. Quote the banned-word hits. Cut them. Print character counts when the job has a cap. Print word counts when the job has a budget. List gaps as gaps. Five missing facts are more useful than one smooth paragraph.
Tags on the card (flux infographic quoted labels, flat layout no fake stats, not a gpt image infographic) are a reminder of the job shape, not an invitation to wander into a neighboring cluster. If you need a different surface, open a different PromptDig card rather than stretching this one.
Fill the card, then run
Replace every bracket. Run on ChatGPT, Claude, or Gemini. Read the ledger first, then the artifact. If the model invents a commit, KPI, DOI, PEL, bid, or logo, discard the run. Tighten Inputs. Run again. Share the filled card that survived, not the first draft that sounded done.