Gpt Image 2
Generate or edit brand visuals via RunComfy’s GPT Image 2 API from the agent using the documented CLI routes and model-specific prompt rules.
Overview
gpt-image-2 is an agent skill most often used in Build (also Launch creative assets) that runs OpenAI GPT Image 2 on RunComfy via documented CLI text-to-image and edit commands.
Install
npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill gpt-image-2What is this skill?
- Routes `runcomfy run openai/gpt-image-2/text-to-image` and `/edit` through local RunComfy CLI—async REST, no OpenAI key
- Documents GPT Image 2 strengths: embedded text, logos, multilingual typography, directive precision
- Three fixed output sizes and edit-with-preservation language for iterative creatives
- Sibling routing guidance: when to use Flux 2, Nano Banana Pro, or Seedream instead
- Triggers on gpt-image-2, ChatGPT Images 2, and explicit generate/edit requests for this model
- 3 fixed output sizes documented for GPT Image 2
- Two CLI paths: text-to-image and edit
Adoption & trust: 18.5k installs on skills.sh; 15 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want GPT Image 2 quality in your agent workflow but lack clear RunComfy routes, size constraints, and edit-preservation prompts.
Who is it for?
Builders already using RunComfy who need logo-ready or text-heavy creatives from agent-driven pipelines.
Skip if: Teams that require on-prem diffusion only or will not use network-backed RunComfy Model API calls.
When should I use this skill?
User says gpt image 2, gpt-image-2, ChatGPT Images 2, image 2, or asks to generate or edit with this model on RunComfy.
What do I get? / Deliverables
The agent issues correct RunComfy CLI jobs with model-appropriate prompts and knows when to hand off to a sibling image skill.
- RunComfy CLI invocations for text-to-image or edit
- Model-appropriate prompts including preservation language for edits
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Image generation through RunComfy is integrated during Build when agents and apps need programmatic creative assets. This is an external Model API integration (RunComfy CLI), not generic frontend UI work.
Where it fits
Wire an agent command that submits async GPT Image 2 jobs after a feature ships.
Batch hero and ad creatives with embedded product name text for a Product Hunt launch.
Refresh multilingual social tiles using edit mode while preserving logo placement.
How it compares
RunComfy-hosted model integration skill—not a local Stable Diffusion installer or generic DALL·E REST wrapper.
Common Questions / FAQ
Who is gpt-image-2 for?
Solo builders and agent authors who generate or edit images through RunComfy and want GPT Image 2-specific sizing, prompts, and CLI paths.
When should I use gpt-image-2?
Use it in Build when wiring creative automation into an agent, and at Launch when producing ad, ASO, or social assets that need crisp in-image text; switch siblings when the skill’s routing section says another RunComfy model fits better.
Is gpt-image-2 safe to install?
It documents network calls to RunComfy; review the Security Audits panel on this Prism page and your org’s policy on external image APIs before installing.
SKILL.md
READMESKILL.md - Gpt Image 2
# GPT Image 2 — Pro Pack on RunComfy [runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-2) · [Text-to-image](https://www.runcomfy.com/models/openai/gpt-image-2/text-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-2) · [Edit](https://www.runcomfy.com/models/openai/gpt-image-2/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-2) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/gpt-image-2) OpenAI **GPT Image 2** (ChatGPT Images 2.0) hosted on the **RunComfy Model API** — no OpenAI key, async REST. ```bash npx skills add agentspace-so/runcomfy-skills --skill gpt-image-2 -g ``` ## When to pick this model (vs siblings) GPT Image 2's distinct strength is **directive precision**: it follows multi-element prompts, layout cues, and embedded-text instructions more reliably than its peers. Pick it when **what's on the canvas matters more than how stylized it looks**. | You want | Use | |---|---| | Embedded text, logos, signage, multilingual typography | **GPT Image 2** | | Brand-safe, e-commerce / ad / UI mockup imagery | **GPT Image 2** | | Iterative refinement that holds composition stable | **GPT Image 2** | | Heavy stylization, painterly look | Flux 2 | | Hyperrealistic portrait | Nano Banana Pro | | Cinematic / aesthetic-first hero shots | Seedream 5 | If the user explicitly asked for GPT Image 2 / ChatGPT Image 2 / Image 2, route here regardless — don't second-guess the model choice. ## Prerequisites 1. **RunComfy CLI** — `npm i -g @runcomfy/cli` 2. **RunComfy account** — `runcomfy login` opens a browser device-code flow. 3. **CI / containers** — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`. ## Endpoints + input schema Two endpoints, same model. ### `openai/gpt-image-2/text-to-image` | Field | Type | Required | Default | Notes | |---|---|---|---|---| | `prompt` | string | yes | — | The positive prompt | | `size` | enum | no | `1024_1024` | `1024_1024` (1:1), `1024_1536` (2:3 portrait), `1536_1024` (3:2 landscape) — **only these three** | ### `openai/gpt-image-2/edit` | Field | Type | Required | Default | Notes | |---|---|---|---|---| | `prompt` | string | yes | — | Natural-language **edit instruction** | | `images` | string[] | yes | — | **Up to 10** reference image URLs (publicly fetchable HTTPS) | | `size` | enum | no | `auto` | `auto` (preserve input ratio), or one of the three fixed sizes above | `size=auto` on edit preserves the input aspect ratio — strongly recommended unless the edit explicitly changes framing. ## How to invoke **Text-to-image:** ```bash runcomfy run openai/gpt-image-2/text-to-image \ --input '{"prompt": "<user prompt>", "size": "1024_1536"}' \ --output-dir <absolute/path> ``` **Edit (single ref):** ```bash runcomfy run openai/gpt-image-2/edit \ --input '{ "prompt": "<edit instruction>", "images": ["https://..."] }' \ --output-dir <absolute/path> ``` **Edit (multi-ref, up to 10):** ```bash runcomfy run openai/gpt-image-2/edit \ --input '{ "prompt": "compose subject from image 1 into the room from image 2; match the lighting of image 2", "images": ["https://...subject.jpg", "https://...room.jpg"] }' \ --output-dir <absolute/path> ``` The CLI su