Image outpainting lets you expand a picture beyond its original edges. You can fill in missing areas that the camera did not capture. It also helps you change aspect ratios, like turning a square into a widescreen landscape.
The skill uses several AI models to do the job. It picks the right model based on your instructions. Some models are good for matching a reference style, while others keep the original look exactly.
You control everything with a command line tool. Just tell it to extend the canvas and the tool handles the rest. The result is a larger image with the original content preserved.
Global
mkdir -p ~/.claude/skills/image-outpaintingProject
mkdir -p .claude/skills/image-outpaintingSource Repository
Remotion Best Practicesremotion-dev/skills
Best practices for building videos with React and Remotion
Ai Video Generationqu-skills/skills
Make AI videos from text, images, or references using 40+ models
Remotion Renderqu-skills/skills
Render animated videos directly from your React component code using Remotion
Ai Image Generationqu-skills/skills
Create AI images quickly with over 50 models via your terminal
Image To Videoagentspace-so/runcomfy-agent-skills
Pick the right AI model to animate your image into video
Flux Kontextagentspace-so/runcomfy-agent-skills
Flux Kontext Pro edits one image part while keeping the rest identical
Nano Banana 2agentspace-so/runcomfy-agent-skills
Create rapid image drafts with strong typography using Google Nano Banana 2 on RunComfy
Gpt Image Editagentspace-so/runcomfy-agent-skills
Edit images with OpenAI GPT Image 2 on RunComfy using smart prompting patterns