Gpt Image Edit
Edit product and marketing images with OpenAI GPT Image 2 on RunComfy while using bundled preservation, typography, and multi-reference prompting patterns.
Overview
GPT Image Edit is an agent skill for the Build phase that edits images with OpenAI GPT Image 2 on RunComfy using documented prompting patterns, multi-reference inputs, and CLI-backed `/edit` runs.
Install
npx skills add https://github.com/agentspace-so/runcomfy-skills --skill gpt-image-editWhat is this skill?
- Calls `runcomfy run openai/gpt-image-2/edit` through the local RunComfy CLI
- Documents GPT Image 2 edit strengths: preservation language, multilingual in-image text, layout and typography precision
- Supports multi-reference editing with up to 10 input images
- Bundles model-specific prompting patterns for sharper edits than naive prompts
- Documents request schema and when to route to Nano Banana Edit, Flux Kontext, or GPT Image 2 text-to-image instead
- Multi-reference editing supports up to 10 input images
- Targets OpenAI GPT Image 2 `/edit` (ChatGPT Images 2.0 image-to-image) via RunComfy
Adoption & trust: 18 installs on skills.sh; 2 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need controlled image-to-image edits (text, layout, preservation) but raw GPT Image 2 calls and vague prompts keep breaking composition or the wrong RunComfy model.
Who is it for?
Solo builders already using RunComfy who want an agent to edit marketing creatives, UI screenshots, or localized in-image copy with GPT Image 2 edit patterns.
Skip if: Builders without RunComfy CLI setup, pure local offline image pipelines, or workflows that only need unrelated video or 3D generation with no RunComfy image edit path.
When should I use this skill?
User says “gpt image edit”, “gpt-image-edit”, “chatgpt image edit”, “edit with gpt image 2”, or any explicit ask to edit images with this model on RunComfy.
What do I get? / Deliverables
Your agent runs structured GPT Image 2 edit jobs via RunComfy with preservation-first prompts, optional multi-image references, and clear fallbacks to alternate RunComfy edit or text-to-image models when appropriate.
- Edited image output from `runcomfy run openai/gpt-image-2/edit`
- Model-aware prompt and parameter choices documented for the run
- Optional routing note when another RunComfy edit or t2i model is a better fit
Recommended Skills
Journey fit
Canonical shelf is Build because the skill wires your coding agent to the RunComfy CLI and GPT Image 2 edit endpoint for asset iteration during product work. Integrations fits best: the deliverable is reliable image-to-image runs via `runcomfy run openai/gpt-image-2/edit`, not a full design system or frontend framework task.
How it compares
Use this as a RunComfy-focused GPT Image 2 edit skill with prompting doctrine, instead of ad-hoc OpenAI image API calls without preservation or model-routing guidance.
Common Questions / FAQ
Who is gpt-image-edit for?
It is for solo and indie builders who use Claude Code, Cursor, Codex, or similar agents and want GPT Image 2 image-to-image edits executed through RunComfy with stronger, model-aware prompts.
When should I use gpt-image-edit?
Use it when you explicitly want ChatGPT Images 2.0 / GPT Image 2 editing—fixing typography in a graphic, preserving a subject while changing background, merging up to ten reference images, or routing away from t2i when `/edit` is the right endpoint during Build integrations work
Is gpt-image-edit safe to install?
It is an MIT-licensed skill that instructs network and shell use via the RunComfy CLI; review the Security Audits panel on this Prism page and your RunComfy account policies before handing it production API keys or sensitive source images.
SKILL.md
READMESKILL.md - Gpt Image Edit
# GPT Image Edit — Pro Pack on RunComfy [runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-edit) · [Edit endpoint](https://www.runcomfy.com/models/openai/gpt-image-2/edit?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-edit) · [Text-to-image sibling](https://www.runcomfy.com/models/openai/gpt-image-2/text-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=gpt-image-edit) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/gpt-image-edit) OpenAI **GPT Image 2 — `/edit` endpoint** (ChatGPT Images 2.0 image-to-image) on the **RunComfy Model API**. Strongest in its class at preserving identity through targeted edits and rewriting embedded text in any script (Latin, kana, CJK, Cyrillic, Arabic). ```bash npx skills add agentspace-so/runcomfy-skills --skill gpt-image-edit -g ``` ## When to pick this model (vs siblings) | You want | Use | |---|---| | Edit multilingual / embedded text in image | **GPT Image Edit** | | Identity preservation through translated headline variants | **GPT Image Edit** | | Layout-precise edit (move headline, swap CTA, etc.) | **GPT Image Edit** | | Up to 10 reference images | **GPT Image Edit** | | Batch up to 20 images consistently | Nano Banana Edit | | Single-shot precise local edit, source-fidelity-first | Flux Kontext | | Generate from scratch with GPT Image 2 | sibling [`gpt-image-2`](../gpt-image-2) skill | | Batch SKU galleries with stable identity | Nano Banana Edit | ## 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 ### `openai/gpt-image-2/edit` | Field | Type | Required | Default | Notes | |---|---|---|---|---| | `prompt` | string | yes | — | Edit instruction. Lead with preservation, end with the change. | | `images` | string[] | yes | — | **Up to 10** publicly-fetchable HTTPS URLs. First is primary; rest are auxiliary. | | `size` | enum | no | `auto` | `auto` (preserve input), `1024_1024` (1:1), `1024_1536` (2:3 portrait), `1536_1024` (3:2 landscape). | `size=auto` preserves the input ratio — strongly recommended unless the edit explicitly changes framing. ## How to invoke **Single-ref preservation edit:** ```bash runcomfy run openai/gpt-image-2/edit \ --input '{ "prompt": "Keep the person'\''s face, pose, and brand mark unchanged. Replace the background with a soft warm-grey studio sweep and a gentle floor shadow.", "images": ["https://.../portrait.jpg"] }' \ --output-dir <absolute/path> ``` **Multilingual text rewrite (preserve everything except the headline):** ```bash runcomfy run openai/gpt-image-2/edit \ --input '{ "prompt": "Keep the photograph, layout, and brand mark exactly as in the input. Replace only the in-image headline. The new headline reads \"今日のおすすめ\" in bold Japanese kana, same position and font weight as before.", "images": ["https://.../poster-en.jpg"] }' \ --output-dir <absolute/path> ``` **Mu