image-outpainting

Extends image canvases and changes aspect ratios via RunComfy edit endpoints.

Updated Jun 11, 2026
One-click install
npx skills add https://github.com/brillianodhiya/VisionScript --skill image-outpainting-brillianodhiya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-outpainting
Source: https://github.com/brillianodhiya/VisionScript/tree/main/.agents/skills/image-outpainting
Command: npx skills add https://github.com/brillianodhiya/VisionScript --skill image-outpainting-brillianodhiya

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Extending a photo beyond its original frame — uncropping, converting square images to 16:9 or 9:16, or filling in what the camera missed — normally requires manual editing or complex ComfyUI node graphs. This Skill routes the task to the right RunComfy image-edit endpoint through the runcomfy CLI while preserving the original content. ## Core Features & Use Cases - Model routing: Picks between Nano Banana 2 Edit (default, spatial-language driven), GPT Image 2 Edit (multi-reference style matching), FLUX Kontext Pro (maximum preservation), and brand edit endpoints (Seedream, Dreamina, Qwen, FLUX 2) based on the outpaint scenario. - Prompting patterns: Provides tested prompt structures for aspect-ratio changes, uncropping portraits, and banner generation, including preservation clauses and explicit aspect_ratio locking. - Use Case: Convert a 1:1 product photo into a 16:9 hero banner by running runcomfy run google/nano-banana-2/edit with a prompt that extends the sides with matching environment while keeping the product untouched. ## Quick Start Ask the agent to extend your image to a 16:9 aspect ratio using the image-outpainting skill with your image URL, and it will run the appropriate runcomfy edit command and save the result to an output folder.

Frequently Asked Questions about image-outpainting

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I outpaint an image to change its aspect ratio?▼

Run `runcomfy run google/nano-banana-2/edit` with a prompt describing the canvas extension, your image URL in `image_urls`, and the target `aspect_ratio` set explicitly. The model extends the canvas with matching environment while preserving the original content.

Which model should I use for image outpainting?▼

Nano Banana 2 Edit is the default for prompt-shaped outpaints like aspect-ratio changes. Use GPT Image 2 Edit when matching a reference style, FLUX Kontext Pro for maximum preservation, and brand endpoints like Seedream or FLUX 2 to stay within a source generation's style.

Can outpainting uncrop a portrait to show more of the body?▼

Yes, outpainting can extend a portrait downward to reveal the upper body and arms. Prompt Nano Banana 2 Edit to continue the clothing style, lighting, and background while keeping the face and visible area exactly as in the input.

Why does my outpainted image have visible seams or mismatched lighting?▼

Seams appear when the extension boundary doesn't continue cleanly. Switch to GPT Image 2 Edit with a style reference, use FLUX Kontext Pro with preservation language, or open a dedicated ComfyUI outpainting workflow on RunComfy for finer seam control.

What is the difference between image outpainting and inpainting?▼

Outpainting extends the canvas beyond the original image borders, while inpainting fills masked regions inside the existing canvas. This Skill handles outpainting only; mask-driven internal edits belong to the image-inpainting skill.

Does the runcomfy CLI support video outpainting?▼

This Skill covers still images only. Extending the canvas of a video spatially is handled by the separate video-outpainting skill, which uses video-specific endpoints in the RunComfy catalog.