gpt-image-editEdit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation language, multilingual in-image text editing, multi-reference up to 10 images, layout / typography precision), the schema, and when to route to Nano Banana Edit / Flux Kontext / GPT Image 2 t2i instead. Calls `runcomfy run openai/gpt-image-2/edit` through the local RunComfy CLI. Triggers on "gpt image edit", "gpt-image-edit", "chatgpt image edit", "edit with gpt image 2", or any explicit ask to edit with this model.
Install via ClawdBot CLI:
clawdbot install kalvinrv/gpt-image-editGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://model-api.runcomfy.net/v1/models/openai/gpt-image-2/edit`Calls external URL not in known-safe list
https://www.runcomfy.comAudited May 1, 2026 · audit v1.0
Generated May 12, 2026
An e-commerce company uses GPT Image Edit to quickly replace headlines in product images for different markets, preserving the original layout, brand elements, and subject fidelity. The model excels at rewriting embedded text in languages such as Japanese, Arabic, or Cyrillic while maintaining visual consistency.
A marketing agency edits a series of brand images by swapping backgrounds or repositioning logos while keeping the brand's identity (e.g., face, pose, typography) intact. The multi-reference capability allows up to 10 auxiliary images for comps.
A social media platform allows users to edit their uploaded photos by changing text or objects with simple instructions, leveraging the model's preservation language to keep user identity unchanged.
A publishing house edits magazine layouts by adjusting headline positions or replacing images while keeping the structure and typography precise. The model handles spatial edits like moving a headline from top-right to bottom-center.
An online retailer creates multiple variations of product photos, such as different background colors or angles, using multi-reference composition (subject from image 1, lighting from image 2) for catalog consistency.
Offer tiered subscriptions (monthly/annual) for access to the RunComfy GPT Image Edit endpoint, with usage limits per tier. Higher tiers unlock batch processing and priority support.
Charge a fixed fee per edit task, with volume discounts for enterprises. Ideal for businesses with sporadic editing needs, like small ad agencies or freelancers.
License the skill to SaaS platforms (e.g., Canva, Adobe) for integration into their editing tools. Revenue comes from licensing fees or revenue sharing per edit performed through the platform.
💬 Integration Tip
Ensure RUNCOMFY_TOKEN is set in CI environments and prefer 'size: auto' to preserve input aspect ratio unless cropping is explicitly required.
Scored May 12, 2026
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Perform image manipulation tasks like background removal, resizing, format conversion, rounding corners, watermarking, and color adjustments using ImageMagic...
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, docu...
A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego...
从图片中提取表格数据并输出为表格和CSV格式;当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用;触发条件:试验图片表格提取,图片表格提取,试验图片数据提取,提取图片数据,提取试验数据