OpenAI GPT Image generation and editing (gpt-image-2, 1.5, 1, mini). Text-to-image, mask-based inpainting, multi-reference composition, multi-turn conversational editing via Responses API, streaming with partial images. This skill should be used when generating or editing images via OpenAI's image models, when near-perfect text rendering in images is needed, when mask-based region-aware editing is required, when multi-turn conversational image editing is desired, or when streaming progressive image delivery is needed. Complements nano-banana-pro (Gemini) as a parallel image generation backend.
Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
OpenAI GPT Image generation and editing (gpt-image-2, 1.5, 1, mini). Text-to-image, mask-based inpainting, multi-reference composition, multi-turn conversational editing via Responses API, streaming with partial images. This skill should be used when generating or editing images via OpenAI's image models, when near-perfect text rendering in images is needed, when mask-based region-aware editing is required, when multi-turn conversational image editing is desired, or when streaming progressive image delivery is needed. Complements nano-banana-pro (Gemini) as a parallel image generation backend.
GPT Atelier
OpenAI GPT Image generation and editing. Wraps both the Image API (one-shot) and Responses API (multi-turn conversational) with 6 scripts covering generate, edit, compose, converse, stream, and test workflows.
Prerequisite:OPENAI_API_KEY environment variable.
Models
Flag
Model
Strengths
(default)
gpt-image-2
Reasoning-based, ~99% text rendering, up to 8 consistent images, 4K, streaming
--fast
gpt-image-1.5
Region-aware editing, 4x faster, cheaper
--mini
gpt-image-1-mini
Cheapest ($0.006/image low quality)
Quick Start
# Test connectivity
python3 scripts/test_connection.py --check-models
# Generate an image
python3 scripts/generate_image.py "A Minoan bull-leaper under golden light"# Compare models side-by-side (HTML page)
python3 scripts/compare_models.py --all --open
python3 scripts/edit_image.py photo.png --mask sky_mask.png
python3 scripts/compose_images.py item1.png item2.png item3.png
python3 scripts/converse_image.py
python3 scripts/stream_image.py --partials 3
"A bronze seal stamp in Minoan style"
# Edit with mask
"Replace the sky with a dramatic sunset"
# Compose from references
"Create a gift basket containing these items"
# Multi-turn editing session
# Streaming with partial images
"An ancient fresco being restored"
Image API scripts share: --output DIR, --filename NAME, --quality low|medium|high, --format png|jpeg|webp, --fast, --mini. converse_image.py uses --orchestrator instead of --fast/--mini.
Auto-converts B&W masks to RGBA (requires Pillow: pip install Pillow).
# Region-aware edit with mask
python3 scripts/edit_image.py "Add a flamingo to the pool" lounge.png --mask pool_mask.png
# Full-image restyle
python3 scripts/edit_image.py "Convert to watercolor painting style" photo.jpg
# Edit with reference images
python3 scripts/edit_image.py "Replace the car with this bicycle" street.png --images bicycle.png
Without a prompt, enters interactive REPL. Maintains conversation state via previous_response_id.
# Interactive session
python3 scripts/converse_image.py --auto-save
> A cyberpunk street scene at night
> Now add neon signs with Japanese text
> Make it rain and add reflections
> /save final_scene
# Single-shot
python3 scripts/converse_image.py "Design a coffee brand logo" --output ./logos
Generates the same prompt across multiple models and outputs a dark-themed HTML comparison page. See references/compare-models-reference.md for full options.
6. Streaming with Partial Images
python3 scripts/stream_image.py "prompt" --partials N [options]
Outputs partial images as they generate, then the final image.
# Stream with 3 progressively sharper partials
python3 scripts/stream_image.py "A detailed architectural drawing" --partials 3 --save-partials
Additional option: --save-partials to save intermediate images.
Prompting Quick-Hits
Lead with scene/style, not subject. First words carry highest visual weight. Specify intended use (ad, UI mockup, editorial) so the model picks the right polish level.
Always double-quote literal text."HELLO WORLD" engages the high-accuracy text rendering engine.
Pixel dimensions in prompt. For custom aspect ratios, append "Output in exactly WxH (R:R ratio) resolution" — the API size param alone is unreliable. Done automatically by inject_size_hint() for gpt-image-2.
Use --thinking for complex scenes. The orchestrator model matters — Thinking models produce significantly better multi-element compositions.
Generate fresh, don't edit. Reference-image editing on gpt-image-2 produces yellow tint and poor prompt adherence. For design-final work, generate from scratch.
See references/prompting-guide.md for full details.
When to Use GPT Atelier vs Nano Banana Pro
Task
GPT Atelier
Nano Banana Pro
Text rendering (complex, non-Latin)
Best
Good
Mask-based inpainting
Native, low drift
Higher drift (~40%)
Reference-image editing
Yellow tint risk — use --fast
Better fidelity
Multi-turn editing with state
Responses API
Multi-turn chat
Photorealism
Excellent
Excellent
Cinematic digital painting
Good
Best
UI mockups / screenshots
Best
Good
Multi-image consistency
Up to 8/prompt
Up to 14 references
Streaming partial delivery
Native
Not available
Dark/artistic themes
Stricter policy
More permissive
Budget/volume
$0.006/img (mini low)
Gemini pricing
Arbitrary aspect ratios
Any (16px multiples)
10 presets
Cost Control
Start with --quality low ($0.006/image) for ideation. Graduate to medium ($0.05) for review, high ($0.21) for final assets. Use --fast for cheaper generation, --mini for maximum cost savings. Use --format jpeg for faster response times.
Script Reference
Script
Purpose
API
generate_image.py
Text-to-image
Image API
edit_image.py
Edit with mask/references
Image API
compose_images.py
Multi-reference composition
Image API
converse_image.py
Multi-turn editing
Responses API
compare_models.py
Side-by-side model comparison (HTML)
Image API
stream_image.py
Streaming with partials
Image API
test_connection.py
Connectivity check
Models API
Reference Documentation
File
Contents
references/api-reference.md
Full parameter reference, pricing, size constraints
references/compare-models-reference.md
Model comparison script: options, examples, HTML output
references/prompting-guide.md
Prompt engineering patterns, text rendering, style keywords
