# GPT Image 2 / 2.5 — Prompt Rules Load this file when the user wants a **GPT Image 2 or GPT Image 2.5** image (OpenAI). The live family is `gpt-image-2`, `gpt-image-2.5-sunburst` and `gpt-image-2.5-flare` — all three are the ONLY Kolbo image models that can output a native transparent background. (`gpt-image/1.5-text-to-image` is the older row and cannot.) For other image models see `models/nano-banana.md`, `models/creative-director.md`, or `models/prompt-copilot.md`. **Kolbo MCP routing:** call `generate_image` (text-to-image) or `generate_image_edit` (edits with `source_images`). Pass the exact identifier the user named (`gpt-image-2`, `gpt-image-2.5-sunburst`, `gpt-image-2.5-flare`); otherwise consult `list_models({ type: "text_to_img" })`. On `generate_image_edit` the same families appear as their `/edit` rows under `list_models({ type: "image_editing" })`. ## CRITICAL Kolbo Platform Rules - **Resolution and aspect ratio are MCP-tool params** (`aspect_ratio`, `resolution`) — NEVER include `size=`, `1024x1536`, aspect-ratio tags, or any resolution syntax inside the `prompt` field. - Pass aspect / resolution as separate tool parameters. Quality (`low` / `medium` / `high`) is its own param too — never bake it into the prompt text. - **No background uses both a tool parameter and a prompt cue.** If the user asks for no background / a transparent cutout, call `list_models` for the chosen image type and require `supports_transparent_background: true`. Then pass `background: "transparent"` and `output_format: "png"` (or `"webp"`). Kolbo appends the exact phrase `no background` once to the effective prompt automatically. The phrase alone is not sufficient; if the model does not advertise the capability, choose a supported model with the user. - Do not write Python, `client.images.generate`, OpenAI SDK code, or `size=` keyword arguments. The user is generating through Kolbo's MCP tools. ## Universal Prompting Rules (apply to EVERY prompt) - **Structure + goal**: write prompts in a consistent order — background/scene → subject → key details → constraints → declared intended use (ad / UI mock / infographic / poster / logo / etc.). The "intended use" line sets the mode and polish level. - **Format**: prefer skimmable templates over clever syntax. Use short labeled segments or line breaks for complex requests. Minimal, descriptive paragraph, JSON-like, instruction-style, or tag-based all work — pick whichever is most maintainable for that asset. - **Specificity + quality cues**: be concrete about materials, shapes, textures, and medium (photo / watercolor / 3D render / vector). Add targeted quality levers only when needed (`film grain`, `textured brushstrokes`, `macro detail`). - **Phone-shot / UGC / "authentic" realism**: photorealism triggers are not enough — that look needs deep depth of field, computational-HDR flatness, named available light and deliberate imperfection. Read `workflows/ugc-smartphone.md`. - **Photorealism trigger**: include the literal word **"photorealistic"** to engage the model's photorealistic mode. Supporting phrases: "real photograph", "taken on a real camera", "professional photography", "iPhone photo", "35mm film". Camera specs (lens mm, aperture) work for high-level look but are loosely interpreted — use for vibe, not physics. - **Composition**: specify framing/viewpoint (close-up, wide, top-down), perspective (eye-level, low-angle), lighting/mood (soft diffuse, golden hour, high-contrast). If layout matters, call out placement ("logo top-right", "subject centered, negative space on left"). - **People, pose, action**: describe scale, body framing, gaze, object interactions ("full body visible, feet included", "looking down at the open book, not at the camera", "hands naturally gripping the handlebar"). - **Complex scene, an edit that must not drift, or a reusable template**: use the block schema, the reference contract (`identity_lock` + an explicit `preserve` list) and named slots from `workflows/prompt-structure.md`. - **Constraints — what changes vs what stays**: state exclusions and invariants explicitly. For edits use **"change only X" + "keep everything else the same"**, and re-state the preserve list on every iteration to prevent drift. Common invariants: identity, geometry, layout, brand elements, camera angle, saturation, contrast, labels, surrounding objects. Always include "no watermark, no extra text, no logos/trademarks" unless the brief specifies otherwise. - **Text in images**: put literal text in **quotes** or **ALL CAPS**, specify typography (font style, size, color, placement). For tricky words / brand names, spell letter-by-letter. Recommend quality **high** when text is small, dense, or multi-font. - **Multi-image inputs**: reference each input by number with a short description ("Image 1: product photo… Image 2: style reference…") and describe the interaction ("apply Image 2's style to Image 1", "place the dog from Image 2 next to the woman in Image 1"). Use `@image1` / `@image2` tags — see `workflows/visual-dna.md`. - **Iterate, don't overload**: prefer a clean base prompt + single-change follow-ups ("make lighting warmer", "remove the extra tree", "restore the original background") over one giant prompt. ## Latency vs Fidelity (recommend `quality` param) - **low**: only when the user prioritizes minimum cost or latency; medium remains the ordinary GPT Image 2.5 default. - **medium**: default best price/quality for ordinary generations, edits and exploration. - **high**: final assets, small/dense text, multi-font layouts, close-up portraits, identity-sensitive edits, infographics, diagrams, posters, UI with labels, scientific visuals, slides with charts/footnotes. - **xhigh/max** (GPT Image 2.5 only, when listed): exceptional dense text or difficult multilingual/Hebrew typography after medium/high are insufficient. Do not auto-run retries or raise spending without authorization. ## Use Cases (text → image) ### Infographics, diagrams, scientific visuals, slides/charts - Treat as artifact spec, not illustration request. Name exact deliverable. Define hierarchy. Provide real text/data verbatim in quotes. - Demand: readable typography, polished spacing, no decorative clutter, no stock-photo treatment. - Recommend: `quality: "high"`, landscape `aspect_ratio` for deck/slide outputs. ### Photorealism - Prompt as if a real photo is being captured in the moment. Use photography language (lens, lighting, framing). Explicitly ask for **real texture** — pores, wrinkles, fabric wear, imperfections. - Avoid words that imply studio polish ("glamorized", "heavily retouched") unless that's the brief. ### Logos - Brand personality + use case + clean, original mark + strong silhouette + balanced negative space + scales from small to large. Flat design, minimal strokes, no gradients unless essential. Plain background, generous padding, centered. "Original, non-infringing". - Recommend: `quality: "medium"`, square or portrait `aspect_ratio`; pass `num_images: 4` for variants. ### Ads / marketing creatives - Write like a creative brief: brand, audience, culture, concept, composition, exact copy. Let the model make taste decisions inside boundaries. - Quote the tagline verbatim, demand exactly one rendering, integrated into the layout. ### Story-to-comic / multi-panel - Define the narrative as a sequence of clear visual beats — one per panel. Number each panel and describe action concretely. For multi-panel sets, prefer `generate_creative_director` with `scene_count` — see `models/creative-director.md`. ### UI mockups - Describe the product **as if it already exists**. Focus on layout, hierarchy, spacing, real interface elements. Avoid concept-art language. Place inside a device frame when relevant ("iPhone frame"). ### Translation in images (edit) - "Translate the text to . Do not change any other aspect of the image. Preserve typography style, placement, spacing, and hierarchy. Translate verbatim. No reflow unless necessary. Do not edit logos, icons, or imagery." ## Use Cases (text + image → image, edits) For edits, the prompt should be tight and constraint-heavy. Call `generate_image_edit` with `source_images: [...]`. ### Style transfer - "Use the same style from the input image. Generate . Keep consistent. Background: . Framing: . No extra elements." ### Virtual try-on - Lock the person (face, body shape, pose, hair, expression). Change garments only. Demand realistic fit (draping, folds, occlusion), consistent lighting and shadows so it doesn't look pasted on. No accessories/text/logos unless asked. ### Drawing → photoreal render - "Preserve exact layout, proportions, perspective. Add realism via plausible materials, lighting, environment. Do not add new elements or text." ### Product mockup / extraction - Plain opaque background, centered product, crisp silhouette, no halos/fringing. Preserve geometry and label legibility exactly. Only light polishing + subtle contact shadow. No restyling. ### Marketing creative with in-image text - Quote copy exactly. Demand "verbatim, no extra characters, exactly once". Specify font style, contrast, kerning, placement. ### Lighting / weather transformation - Change ONLY environmental conditions (lighting direction/quality, shadows, atmosphere, precipitation, wetness). Preserve identity, geometry, camera angle, object placement. ### Object removal - "Remove the . Do not change anything else." Keep edits surgical. Re-state every invariant. ### Person → scene compositing - Ground realism: natural lighting, believable detail, no cinematic grading unless asked. Lock subject identity, expression, body. Higher input fidelity helps likeness across larger scene edits. ### Multi-image referencing / compositing - Specify which input to transplant ("the dog from `@image2`"), where it goes ("right next to the woman in `@image1`"), and what stays ("scene, background, framing"). Match lighting, perspective, scale, and shadows. ### Interior design swap (precision edit) - "Replace ONLY