imagegen

name	imagegen
description	Use when generating or editing images. Primary tool: bundled `scripts/image_gen.py` (OpenAI GPT Image 2). For non-OpenAI providers (Gemini Pro, Gemini, Imagen), use the `generate-image` CLI. Covers generate, edit/inpaint/mask, background removal, product shots, concept art, covers, and batch variants.

Image Generation Skill

Generates or edits images for the current project (e.g., website assets, game assets, UI mockups, product mockups, wireframes, logo design, photorealistic images, infographics). Defaults to gpt-image-2 and the OpenAI Image API, and prefers the bundled CLI for deterministic, reproducible runs.

Model selection — read this before picking a model

The user names the model. Don't infer it from quality cues.

User shorthand → model mapping:

• "image 2.0", "image-2", "gpt image", "gpt-image", "openai image", or no model specified → gpt-image-2 (OpenAI). Use the bundled scripts/image_gen.py with --quality high for best results. This is the default — do not silently substitute another model.
• "nano banana", "nano banana pro", "gemini image", "gemini 3 pro image" → gemini-3-pro-image-preview via generate-image --provider gemini-pro.
• "imagen", "imagen 4", "google imagen" → imagen-4.0-* via generate-image --provider imagen.

"High quality" / "high fidelity" / "the good one" is not a model selector — it's a --quality high flag on whatever model the user chose. If the user has not named a model, default to gpt-image-2 with --quality high. Only switch providers when the user names one.

When in doubt about which model the user means, ask before generating.

When to use

• Generate a new image (concept art, product shot, cover, website hero)
• Edit an existing image (inpainting, masked edits, lighting or weather transformations, background replacement, object removal, compositing, transparent background)
• Batch runs (many prompts, or many variants across prompts)

Decision tree (generate vs edit vs batch)

• If the user provides an input image (or says “edit/retouch/inpaint/mask/translate/localize/change only X”) → edit
• Else if the user needs many different prompts/assets → generate-batch
• Else → generate

Workflow

1. Decide intent: generate vs edit vs batch (see decision tree above).
2. Collect inputs up front: prompt(s), exact text (verbatim), constraints/avoid list, and any input image(s)/mask(s). For multi-image edits, label each input by index and role; for edits, list invariants explicitly.
3. If batch: write a temporary JSONL under tmp/ (one job per line), run once, then delete the JSONL.
4. Augment prompt into a short labeled spec (structure + constraints) without inventing new creative requirements.
5. Run the bundled CLI (scripts/image_gen.py) with sensible defaults (see references/cli.md).
6. For complex edits/generations, inspect outputs (open/view images) and validate: subject, style, composition, text accuracy, and invariants/avoid items.
7. Iterate: make a single targeted change (prompt or mask), re-run, re-check.
8. Save/return final outputs and note the final prompt + flags used.

Temp and output conventions

• Use tmp/imagegen/ for intermediate files (for example JSONL batches); delete when done.
• Write final artifacts under output/imagegen/ when working in this repo.
• Use --out or --out-dir to control output paths; keep filenames stable and descriptive.

Dependencies (install if missing)

Prefer uv for dependency management.

Python packages:

uv pip install openai pillow

If uv is unavailable:

python3 -m pip install openai pillow

Environment

• OPENAI_API_KEY must be set for live API calls.

If the key is missing, give the user these steps:

1. Create an API key in the OpenAI platform UI: https://platform.openai.com/api-keys
2. Set OPENAI_API_KEY as an environment variable in their system.
3. Offer to guide them through setting the environment variable for their OS/shell if needed.

• Never ask the user to paste the full key in chat. Ask them to set it locally and confirm when ready.

If installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.

Non-OpenAI providers (generate-image CLI)

For Gemini Pro, Gemini, or Imagen, use the generate-image bash CLI (~/.dotfiles/bin/generate-image) instead of scripts/image_gen.py. It requires no Python — just curl and a GEMINI_API_KEY.

Quick example:

generate-image "A sunset over mountains" --provider gemini-pro --size 2048x2048

Full reference (providers, flags, input-image limits, sizes): references/generate-image-cli.md.

Defaults & rules

• Use gpt-image-2 via scripts/image_gen.py unless the user explicitly asks for a non-OpenAI provider or a cheaper/faster model.
• For non-OpenAI providers (Gemini Pro, Gemini, Imagen), use generate-image CLI.
• Assume the user wants a new image unless they explicitly ask for an edit.
• Require OPENAI_API_KEY for OpenAI calls; GEMINI_API_KEY for Gemini/Imagen calls.
• Use the OpenAI Python SDK (openai package) for OpenAI API calls; do not use raw HTTP.
• If the user requests edits, use client.images.edit(...) (OpenAI) or generate-image -i (Gemini).
• Prefer the bundled CLIs over writing new one-off scripts.
• Never modify scripts/image_gen.py. If something is missing, ask the user before doing anything else.
• If the result isn’t clearly relevant or doesn’t satisfy constraints, iterate with small targeted prompt changes; only ask a question if a missing detail blocks success.

Prompt augmentation

Reformat user prompts into a structured, production-oriented spec. Only make implicit details explicit; do not invent new requirements.

Do not use --no-augment unless the user explicitly asks for raw passthrough. Augmentation consistently improves output quality — even when your prompt is already detailed. Long, unstructured prompts actually hurt results because the model has to parse competing directives. Augmentation compresses and labels the intent so the model focuses on the right things. Skipping it to "save time" or because "the prompt is detailed enough" is a false economy that produces worse images.

Use-case taxonomy (exact slugs)

Classify each request into one of these buckets and keep the slug consistent across prompts and references.

Generate:

• photorealistic-natural — candid/editorial lifestyle scenes with real texture and natural lighting.
• product-mockup — product/packaging shots, catalog imagery, merch concepts.
• ui-mockup — app/web interface mockups that look shippable.
• infographic-diagram — diagrams/infographics with structured layout and text.
• logo-brand — logo/mark exploration, vector-friendly.
• illustration-story — comics, children’s book art, narrative scenes.
• stylized-concept — style-driven concept art, 3D/stylized renders.
• historical-scene — period-accurate/world-knowledge scenes.

Edit:

• text-localization — translate/replace in-image text, preserve layout.
• identity-preserve — try-on, person-in-scene; lock face/body/pose.
• precise-object-edit — remove/replace a specific element (incl. interior swaps).
• lighting-weather — time-of-day/season/atmosphere changes only.
• background-extraction — transparent background / clean cutout.
• style-transfer — apply reference style while changing subject/scene.
• compositing — multi-image insert/merge with matched lighting/perspective.
• sketch-to-render — drawing/line art to photoreal render.

Quick clarification (augmentation vs invention):

• If the user says “a hero image for a landing page”, you may add layout/composition constraints that are implied by that use (e.g., “generous negative space on the right for headline text”).
• Do not introduce new creative elements the user didn’t ask for (e.g., adding a mascot, changing the subject, inventing brand names/logos).

Template (include only relevant lines):

Use case: <taxonomy slug>
Asset type: <where the asset will be used>
Primary request: <user's main prompt>
Scene/background: <environment>
Subject: <main subject>
Style/medium: <photo/illustration/3D/etc>
Composition/framing: <wide/close/top-down; placement>
Lighting/mood: <lighting + mood>
Color palette: <palette notes>
Materials/textures: <surface details>
Quality: <low/medium/high/auto>
Input fidelity (edits): <low/high>
Text (verbatim): "<exact text>"
Constraints: <must keep/must avoid>
Avoid: <negative constraints>

Augmentation rules:

• Keep it short; add only details the user already implied or provided elsewhere.
• Always classify the request into a taxonomy slug above and tailor constraints/composition/quality to that bucket. Use the slug to find the matching example in references/sample-prompts.md.
• If the user gives a broad request (e.g., "Generate images for this website"), use judgment to propose tasteful, context-appropriate assets and map each to a taxonomy slug.
• For edits, explicitly list invariants ("change only X; keep Y unchanged").
• If any critical detail is missing and blocks success, ask a question; otherwise proceed.

Examples

Generation example (hero image)

Use case: stylized-concept
Asset type: landing page hero
Primary request: a minimal hero image of a ceramic coffee mug
Style/medium: clean product photography
Composition/framing: centered product, generous negative space on the right
Lighting/mood: soft studio lighting
Constraints: no logos, no text, no watermark

Edit example (invariants)

Use case: precise-object-edit
Asset type: product photo background replacement
Primary request: replace the background with a warm sunset gradient
Constraints: change only the background; keep the product and its edges unchanged; no text; no watermark

Prompting best practices (short list)

• Structure prompt as scene -> subject -> details -> constraints.
• Include intended use (ad, UI mock, infographic) to set the mode and polish level.
• Use camera/composition language for photorealism.
• Quote exact text and specify typography + placement.
• For tricky words, spell them letter-by-letter and require verbatim rendering.
• For multi-image inputs, reference images by index and describe how to combine them.
• For edits, repeat invariants every iteration to reduce drift.
• Iterate with single-change follow-ups.
• For latency-sensitive runs, start with quality=low; use quality=high for text-heavy or detail-critical outputs.
• For strict edits on models prior to gpt-image-2, consider input_fidelity=high. For gpt-image-2, omit it because the API always uses high-fidelity image inputs.
• If results feel “tacky”, add a brief “Avoid:” line (stock-photo vibe; cheesy lens flare; oversaturated neon; harsh bloom; oversharpening; clutter) and specify restraint (“editorial”, “premium”, “subtle”).

More principles: references/prompting.md. Copy/paste specs: references/sample-prompts.md.

Guidance by asset type

Asset-type templates (website assets, game assets, wireframes, logo) are consolidated in references/sample-prompts.md.

CLI + environment notes

• CLI commands + examples: references/cli.md
• API parameter quick reference: references/image-api.md
• If network approvals / sandbox settings are getting in the way: references/codex-network.md

Reference map

• references/cli.md: how to run image generation/edits/batches via scripts/image_gen.py (commands, flags, recipes).
• references/generate-image-cli.md: generate-image bash CLI for non-OpenAI providers (Gemini Pro, Gemini, Imagen) — commands, provider table, input limits.
• references/image-api.md: what knobs exist at the API level (parameters, sizes, quality, background, edit-only fields).
• references/prompting.md: prompting principles (structure, constraints/invariants, iteration patterns).
• references/sample-prompts.md: copy/paste prompt recipes (generate + edit workflows; examples only).
• references/batch-workflow.md: batch generation workflow patterns.
• references/codex-network.md: environment/sandbox/network-approval troubleshooting.