Generate and edit images with embedded text using OpenAI GPT Image 2 via RunComfy CLI.
npx skills add https://github.com/runcomfy-com/skills --skill gpt-image-2-runcomfy-com
Please help me install this Agent Skill. Skill: gpt-image-2 Source: https://github.com/runcomfy-com/skills/tree/main/gpt-image-2 Command: npx skills add https://github.com/runcomfy-com/skills --skill gpt-image-2-runcomfy-com
It helps users generate and edit high-quality images with reliable prompt-following, especially when the output must include accurate embedded text, logos, and brand-safe layout details.
Use the gpt-image-2 skill to generate an image by asking for your exact subject, setting, and any embedded text you want included.
High-intent search queries and answers about installing and using this skill.
To generate images with accurate embedded text and logos, you use text-to-image generation by providing a precise prompt that includes your exact subject, setting, and the specific text or typography you require. The system processes these instructions to produce brand-safe layouts with reliable prompt-following for signage and packaging mockups.
Yes, you can edit existing images while preserving the original subject by providing up to 10 public HTTPS reference image URLs. The system uses these references to maintain intended subject characteristics while allowing you to change backgrounds, layouts, and text placement.
The best way to create multilingual typography for UI concepts is through text-accurate image generation. You provide exact text strings and layout instructions in your prompt, and the model outputs high-quality visual mockups with strong instruction precision for the required typography.
This approach is optimized for text-accurate visual requirements and brand-safe layouts rather than heavy stylization or photorealistic portraits. For heavy stylization, you should route to Flux 2; for photorealistic portraits, use Nano Banana Pro; and for cinematic, aesthetic-first shots, use Seedream.
To use reference images for ad creatives and UI mockups, you invoke the CLI with the correct model endpoint and provide your prompt alongside up to 10 public HTTPS reference image URLs. You can also specify optional size constraints to meet your creative formatting requirements.
agentspace-soGenerate and edit brand-safe images with GPT Image 2 on the RunComfy Model API.
GroundMountCompanyGenerate production-ready product photography assets for ecommerce and marketing platforms.
doany-aiRoute image edits to the best RunComfy model and download results.
code-senseiGenerate structured Flux AI image prompts across FLUX.1, FLUX.2, and Kontext models.
