Text to Image
Describe what you want and get a generated image — from product visuals to brand posters and creative concepts.
Plug the AI Image Generator Skill into your OpenClaw agent and unlock image creation, editing, product model images, and background removal — all through natural language.
Install Topview Skill for me: https://github.com/topviewai/skill.gitQuick Start
ImageDemo
AI Image Generator Skill is a capability you can add to your AI assistant through Topview Skill. Once installed, your agent can create images from text, edit existing visuals, remove backgrounds, and generate product model images — all through natural conversation.
Describe what you want and get a generated image — from product visuals to brand posters and creative concepts.
Change backgrounds, swap scenes, adjust details, or restyle an image by describing what you want changed.
Place your product into model-style marketing scenes automatically — great for e-commerce and ads.
Get clean transparent cutouts from any image in one step, ready for downstream workflows.
Switch across models like Nano Banana 2, GPT Image 1.5, Imagen 4, and more for the style you need.
All generated images are organized on Topview Board — preview, compare, edit, and share in one place.
Claude Skill protocol
This skill package follows the Claude Skill protocol structure, so agents can install, read, and execute it in a predictable way. It is a workflow package rather than an executable installer, which means there is no malware or virus risk in normal use.
View VirusTotal virus scan reportInstall Topview Skill for me: https://github.com/topviewai/skill.git
Install Topview Skill into your agent first so it can call the relevant capabilities.
Send prompts, images, product photos, portraits, or audio-related requests directly to your agent.
Your agent will automatically call the right Topview capability to generate video, image, avatar, or audio results for you.