GPT Image·par OpenAIÉdition d'image
GPT Image 2.5 Flare Edit
Natural-language image editing with OpenAI GPT Image 2.5. Up to 16 source images; 14 sizes up to 4K, five quality tiers including xhigh and max, transparent backgrounds. Priced live from quality, size, prompt length and the resolution of the source images.
Paramètres
| Paramètre | Type | Par défaut | Plage ou options |
|---|---|---|---|
Output format output_formatOutput image format. PNG keeps transparency; JPEG files are smaller. | select | png | png, jpeg |
Background backgroundtransparent produces a real alpha channel (needs PNG output). Set it here — asking for a transparent background in the prompt paints a checkerboard. | select | auto | auto, opaque, transparent |
Moderation moderationContent-moderation strictness on the provider side. low applies less restrictive filtering. | select | low | low, auto |
Quality qualityRendering quality tier. xhigh and max are new in GPT Image 2.5. At 1024×1024: low ≈0.6×, high ≈3.2×, xhigh ≈5.4×, max ≈11.9× the medium price. | select | medium | low, medium, high, xhigh, max |
Size sizeOutput size in pixels — the only control over dimensions and aspect ratio. Sizes above 2560×1440 are experimental upstream. Larger sizes cost more. | select | 1024x1024 | 1024×1024 · 1:1 (1024x1024), 1024×768 · 4:3 (1024x768), 768×1024 · 3:4 (768x1024), 1536×1024 · 3:2 (1536x1024), 1024×1536 · 2:3 (1024x1536), 2048×2048 · 1:1 (2048x2048), 2048×1152 · 16:9 (2048x1152), 1152×2048 · 9:16 (1152x2048), 2560×1088 · 21:9 (2560x1088), 1088×2560 · 9:21 (1088x2560), 2880×2160 · 4:3 (2880x2160), 2160×2880 · 3:4 (2160x2880), 3840×2160 · 16:9 (4K) (3840x2160), 2160×3840 · 9:16 (4K) (2160x3840) |
Entrées
Fichiers que ce modèle accepte en plus du prompt.
| Entrée | Accepte | Fichiers max. | |
|---|---|---|---|
images images | image | 16 | Obligatoire |
Règles de LUVI Prompt Engine pour GPT Image
TARGET MODEL: GPT Image 2.5 (OpenAI — Flare and Sunburst read the same dialect). The prompt reaches the model exactly as written. Prose, reference images and the app's settings (size, quality, background) are the whole control surface — there is no seed, no negative_prompt field, no weighting and no special token syntax.
Règles à respecter
- Keep the user's subject, intent and every quoted string exactly. Reshape; do not invent. Never add props, scene elements, people, wardrobe, architecture, materials, weather, time of day, light, lenses, styles or orientation words ("vertical", "wide") the user did not give — this model already fills empty scenes with extras on its own. A short brief stays short: "a red vespa in a narrow Istanbul street" must NOT gain cobblestones, shuttered windows or afternoon light.
- Every format works on this model (prose, tags, JSON-like, labeled sections). If you restructure a JSON-like or tag prompt, carry over every value — no field may be dropped or reinterpreted.
- Name the deliverable and its use in the opening words: "a vertical retail poster for a coffee roastery", "a product photograph for a web shop", "an infographic for high-school students".
- In-image text: every visible string in double quotes, exactly as it must read, with its position and typography in plain words; say "exactly once" when repetition would hurt. Keep non-English characters exact (Turkish İ ı ş ğ ç ö ü, ₺). A name given only as context ("a roastery called X") is not printed — when the deliverable obviously carries it (packaging, label, logo, sign, storefront, poster for that brand), quote the name and say where it is printed: a jar label reading "Arı Bal".
- End with the exclusions the result needs, as short plain negatives — they are safe and obeyed on this model: "No other text." · "No watermark, no logos." When the scene invites lettering the user did not ask for (a named town, harbor, street, shopfront, vehicle), add "No text, signs or lettering anywhere."
- Transparent background: the app's background=transparent setting makes the alpha; the words alone paint a fake checkerboard. When the user wants a cutout, describe ONE isolated subject with nothing behind it (no backdrop, floor, scene or colour) and add "Fully transparent background, no checkerboard, no shadow plate."
- Aspect ratio and resolution are settings. Do not write ratio numbers ("16:9") or resolutions ("4K", "8k") into the prompt; describe the composition in words instead ("a wide landscape", "a tall vertical poster with empty space at the top for the headline").
Ce qui fonctionne le mieux
- For a long brief use the order scene → subject → details → constraints; labeled sections ("Scene:", "Subject:", "Style:", "Text:", "Constraints:") are fine.
- Describe what is visible: materials, light, colour, medium, framing, texture. Ask for "photorealistic" or "real photograph" only when realism is the goal; camera terms ("35mm film photograph, eye level, 50mm lens") are look cues, not physics.
- Replace mood words and quality boosters ("cinematic", "stunning", "8k, masterpiece, best quality") with scale, atmosphere, colour and concrete detail.
- Candid or authentic photos: "It should look like a real photograph someone could have taken, not an overly enhanced or cinematic image. No glamorization, no heavy retouching."
- People: body framing, relative scale, gaze and what the hands do ("full body visible, feet included", "looking down at the open book").
- Charts, slides, diagrams: put the real numbers and labels into the prompt.
Issu des règles de LUVI Prompt Engine pour cette famille : les mêmes que celles qu'appliquent le réécriveur de l'espace de travail et le connecteur MCP de LUVI.