by OpenAIImage
GPT Image
8 models · from 16 credits
Models in the GPT Image family
| Model | Mode | Price | Aspect ratios | |
|---|---|---|---|---|
| GPT Image 1.5 Edit | Image edit | from 16 credits | 1:1 · 2:3 · 3:2 | Open → |
| GPT Image 1.5 Text-to-Image | Text to image | from 16 credits | 1:1 · 2:3 · 3:2 | Open → |
| GPT Image 2.5 Flare Edit | Image edit | from 135 credits | — | Open → |
| GPT Image 2.5 Flare Text-to-Image | Text to image | from 37 credits | — | Open → |
| GPT Image 2.5 Sunburst Edit | Image edit | from 135 credits | — | Open → |
| GPT Image 2.5 Sunburst Text-to-Image | Text to image | from 37 credits | — | Open → |
| Openai GPT Image 2 Edit | Image edit | from 20 credits | — | Open → |
| Openai GPT Image 2 Text-to-Image | Text to image | from 18 credits | — | Open → |
Prompting guide for GPT Image 2
TARGET MODEL: GPT Image 2 (OpenAI). Prose + reference images are the ENTIRE control surface — no seed, no negative_prompt field, no style dial.
Rules that must hold
- Prose, not tags. Natural flowing English; commas only for concrete fragments, never abstract quality stacks.
- Ban dead tokens: never "8k, ultra-detailed, masterpiece, best quality, highly detailed, 1girl" — inert at best, degrading at worst (they feed the tiling artifact).
- Order: scene/background → subject → key details → constraints. Constraints ALWAYS last. Lead with the subject only when the figure is the hero — constraints still close.
- Name the deliverable in one word: "editorial photo", "product shot", "UI mock", "infographic", "poster" — it sets the model's mode and polish level.
- Concrete and physical, not adjectival: "warm tungsten key from the left, shallow depth of field" beats "cinematic lighting". A lens is a feel cue only ("50mm feel") — the model runs no optical simulation.
- Affirmative beats negative. Describe what IS, materially and confidently. Exclusions are SHORT concrete noun tokens in the constraints slot ("no watermark, no extra text") — never long "do not include…" sentences (they inject the banned concept).
- Aspect ratio is a parameter, never a sentence — do not write "16:9" or framing ratios into the prose.
- Never ask for a transparent background in prose — it paints a literal checkerboard as solid pixels.
- Start lean — don't overload one brief; a shorter concrete prompt beats a maximal one.
What works best
- Candid/authentic register — describe the DEGRADATION, not the production: "photorealistic" + one of "candid photograph / amateur photograph / iPhone photo", then the stack: "amateur composition, no studio lighting, subtle film grain, slight sensor noise in darker areas, slight overexposed highlights, mild compression artifacts, imperfect framing, natural color balance". Close on subtraction: "No glamorization, no heavy retouching. No cinematic grading, no flash, no studio light." Beat the camera-flash default with practical sources + two mixed color temperatures. Kill the influencer face: "no beauty filter, no HD polish".
- Commercial/product register is the OPPOSITE — keep studio language: "premium product photography, studio lighting, seamless white sweep, soft shadow beneath, sharp label printing". Pick the register from the stated use.
- Tiling guard on foliage / fur / grass / dense organic texture: shorten the prompt, drop grain vocabulary, and add "no speckled dot artifacts, no tiling texture, no repetitive grime pattern, no stippled texture".
- Style needs visual targets, not adjectives: "cream background, heavy black condensed sans, one hero object, generous negative space" beats "minimalist premium editorial". Name the medium flat ("35mm film photograph", "flat vector design", "hand-painted watercolor"); hyper-specific device/era mediums land ("early 2000s CCTV security camera", "low-poly PlayStation screengrab").
- Fight the warm/yellow house cast with explicit "natural color balance".
- In-image text: quote the literal copy in "double quotes" or ALL CAPS; describe type as a separate spatial constraint (weight, color, placement); spell tricky or brand words letter-by-letter; keep each text zone to 5 words or fewer and bind distinct strings to distinct objects ("Include ONLY this label text (verbatim): …"); multiple text blocks in one frame MERGE — keep blocks few; fence phantom text every time: "No other visible words. No random letters. No duplicate text. No watermark." and assert the single instance ("Render the tagline exactly once.").
- Character consistency is prompt-only — restate the preserve-list every turn ("change only X, keep everything else the same") and enumerate the identity traits; pair PRESERVE attributes with EXCLUDE additions ("no text, no watermark, no logos"). One change per edit.
From LUVI's own manual for this family, the same rules the workspace rewriter and the MCP prompt engine apply.