gpt-image-2-runcomfyGPT Image 2 on RunComfy. GPT Image 2 (OpenAI ChatGPT Images 2.0) is the strongest text-rendering image model available — embedded text, logos, signage, multilingual typography, and high-fidelity layout. This skill calls GPT Image 2 through the RunComfy CLI: `runcomfy run openai/gpt-image-2/text-to-image` (or `/edit`). GPT Image 2 has 3 fixed sizes and supports up to 10 reference images on the GPT Image 2 edit endpoint. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2", "ChatGPT Image 2", "OpenAI Image 2", "GPT Image", or any explicit ask to generate or edit with GPT Image 2.
Install via ClawdBot CLI:
clawdbot install kalvinrv/gpt-image-2-runcomfyGrade 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/<endpointCalls external URL not in known-safe list
https://www.runcomfy.comAudited May 1, 2026 · audit v1.0
Generated May 12, 2026
Generate product mockups, store signage, or labeling with precise text rendering using GPT Image 2's typography capabilities. Ideal for e-commerce listings that require legible brand names or multilingual instructions.
Produce ad visuals with accurate brand logos, headlines, and layout consistency across multiple variants. GPT Image 2's directive precision ensures brand guidelines are followed without manual retouching.
Adapt a single reference image into multiple language versions by editing embedded text (e.g., headlines in English, Japanese, Arabic) while preserving the original composition and design.
Refine UI mockups by changing specific elements (e.g., button text, color) while keeping the overall layout stable across iterations. Useful for rapid prototyping without rebuilding designs.
Combine up to 10 reference images into a single coherent composition, using natural-language instructions to preserve key features (e.g., face, logo) while blending backgrounds or subjects.
Charge per generation using RunComfy's model API, offering GPT Image 2 capabilities without requiring an OpenAI account. Customers pay for compute/time used, enabling scalable image generation for high-volume tasks.
Offer tiered subscriptions (monthly or yearly) for design agencies or in-house teams needing unlimited GPT Image 2 access for branding, ads, and mockups. Bundles include priority queue and higher concurrency.
Integrate GPT Image 2 into existing creative tools (e.g., Canva, Figma plugins) as a premium add-on. Revenue share per user action or flat licensing fee per integration.
💬 Integration Tip
Start with runcomfy login to authenticate, then run simple text-to-image commands with a prompt and size parameter. Use --output-dir to save outputs locally.
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