image-outpainting
๐ฏSkillfrom prime-skills/runcomfy-agent-skills
Installation
npx vibeindex add prime-skills/runcomfy-agent-skills --skill image-outpaintingnpx skills add prime-skills/runcomfy-agent-skills --skill image-outpainting~/.claude/skills/image-outpainting/SKILL.md
|A Claude Code skill for extending images beyond their original canvas via the RunComfy CLI. Supports uncropping, aspect ratio changes (square to 16:9, portrait to landscape), and environment continuation by routing across Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro, and brand-specific edit endpoints.
Overview
Image Outpainting is a Claude Code skill that extends a still image beyond its original canvas using the RunComfy CLI. It handles common use cases like uncropping photos, changing aspect ratios (square to 16:9, portrait to landscape), and filling in what the camera did not capture while preserving the original content. The skill routes across multiple model endpoints based on intent: Nano Banana 2 Edit for prompt-shaped spatial extensions, GPT Image 2 Edit for composite outpainting with reference-style matching, FLUX Kontext Pro for single-shot maximum-preservation edits, and brand-specific endpoints like Seedream, Dreamina, and FLUX 2 for style-consistent continuation.
Key Features
- Prompt-driven canvas extension with Nano Banana 2 Edit as the default, honoring spatial language like "extend left and right by 30%" or "add sky above"
- Aspect ratio conversion with explicit
aspect_ratioparameter support (1:1 to 16:9, 1:1 to 9:16 for Reels, portrait to 21:9 for banners) - Reference-style matching via GPT Image 2 Edit when outpainting needs to match a style from up to 10 reference images
- Maximum preservation mode with FLUX Kontext Pro for single-shot outpaints that keep the original content pixel-perfect
- Multi-step chaining by using each outpaint result as input for the next pass, extending 30-50% per step to avoid boundary artifacts
- ComfyUI workflow fallback pointing to dedicated outpainting node graphs for pixel-precise seam handling when CLI endpoints are not enough
Who is this for?
- Photographers and designers who need to change image aspect ratios for different social media platforms without losing the original composition
- E-commerce teams preparing product shots that need extended backgrounds for catalog banners and hero images
- Digital artists and retouchers restoring cropped photos or expanding compositions with environment-matched continuation
Same repository
prime-skills/runcomfy-agent-skills(25 items)
SKILL.md
More from this repository10
A smart intent-routing skill for video editing on RunComfy that automatically selects the best model (Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, or Lucy Edit Restyle) based on what the user wants to do, from general restyling and background swaps to precise motion transfer and outfit changes.
A smart intent-routing skill that animates still images on RunComfy by selecting the optimal model: HappyHorse 1.0 I2V for general portrait and product animation with native audio, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition with image, video, and audio references.
A skill for generating images with Google Nano Banana 2, the flash-tier text-to-image model in the Gemini family on RunComfy, optimized for rapid iteration, batch ideation, in-image typography rendering, and optional web-grounded context with support for resolutions from 0.5K to 4K.
A smart intent-routing skill for image editing on RunComfy that selects the optimal model from Nano Banana Edit (batch up to 20 images), GPT Image 2 Edit (multilingual text rewrite, multi-ref composition), Flux Kontext Pro (single-shot precise local edit), or Z-Image Turbo Inpaint (mask-driven region edit) based on user intent.
A Claude Code skill that enables precise single-image editing using Black Forest Labs's Flux 1 Kontext Pro model through the RunComfy CLI, with built-in prompting patterns for high-fidelity local edits.
A skill for generating text-to-video with Wan 2.7, Wan-AI's flagship motion model on RunComfy, featuring multi-reference conditioning, audio-driven lip-sync via custom audio tracks, smooth transition physics, prompt expansion control, and up to 1080p output at 15 seconds duration.
A Claude Code skill for generating text-to-video clips with HappyHorse 1.0 via the RunComfy CLI. HappyHorse 1.0 is currently ranked #1 on the Artificial Analysis Video Arena, producing native 1080p video with in-pass synchronized audio and multi-shot character consistency.
A Claude Code skill for generating video with Kling 3.0 via the RunComfy CLI. Covers all six Kling 3.0 endpoints across three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video), with native synchronized audio and multi-shot character consistency.
A Claude Code skill that generates custom OpenAI Codex Pets from a single reference image via the RunComfy CLI. It produces a Codex-compatible spritesheet (1536x1872, 8 columns x 9 rows) and pet.json manifest using GPT Image 2 and ImageMagick, without requiring Codex Pro or an OPENAI_API_KEY.
A Claude Code skill that acts as a smart router for AI video generation across the full RunComfy model catalog. Supports text-to-video, image-to-video, and video-extend modes with models including HappyHorse 1.0, Kling 3.0, Wan 2.7, Seedance, Veo 3.1, and more.