Route image outpainting tasks across multiple endpoints via the RunComfy CLI.
npx skills add https://github.com/doany-ai/skills --skill image-outpainting-doany-ai
Please help me install this Agent Skill. Skill: image-outpainting Source: https://github.com/doany-ai/skills/tree/main/image-outpainting Command: npx skills add https://github.com/doany-ai/skills --skill image-outpainting-doany-ai
Image outpainting on RunComfy via the RunComfy CLI — extend a still beyond its original canvas, fill in what the camera didn't capture, change aspect ratio (square to 16:9, portrait to landscape) while preserving the original content. Routes across Nano Banana 2 Edit (default, spatial-language driven), GPT Image 2 Edit (multi-ref with reference-style matching), FLUX Kontext Pro (single-shot maximum-preservation), and the brand edit endpoints (Seedream / Dreamina / Qwen / FLUX 2). Picks the right route based on whether the outpaint is prose-driven, reference-driven, or brand-locked. Triggers on "outpaint", "outpainting", "extend image canvas", "expand the image", "fill in around the photo", "uncrop", "change aspect ratio", "extend frame", "wide-screen from square", or any explicit ask to add canvas around an existing still.
Use the image-outpainting skill to extend a still beyond its original canvas.
High-intent search queries and answers about installing and using this skill.
To extend an image canvas and change the aspect ratio, the skill routes outpainting tasks across multiple endpoints like Nano Banana 2 Edit or FLUX Kontext Pro, expanding the frame while preserving the original content.
For reference-style matching during outpainting, the skill routes the task to GPT Image 2 Edit, which uses multi-reference inputs to ensure the expanded canvas boundaries match the desired visual style.
Yes, you can use the RunComfy CLI to expand a portrait image into a landscape format by providing input prompts and image URLs, allowing boundary continuity and aspect ratio changes while preserving the original still.
For maximum preservation of original content when extending an image frame, the skill selects FLUX Kontext Pro, which handles single-shot outpainting tasks while strictly maintaining the integrity of the initial still.
Brand-specific edit endpoints, such as Seedream or Dreamina, are used for brand-locked continuations when the outpainting task requires strict adherence to specific brand styles rather than prose-driven or reference-driven expansions.
Before running an outpainting task, you need to install the RunComfy CLI, authenticate your account, and prepare JSON inputs containing your prompts and optional image URLs to route the expansion correctly.
agentspace-soGenerate AI video clips from text, images, or Veo extensions via RunComfy CLI.
numekudiGenerate images from text prompts with configurable model, size, and aspect ratio.
Bria-AIConvert natural language image requests into deterministic VGL JSON prompts for Bria's FIBO models.
Syh1906Automates image generation, editing, and batch creation via OpenAI-compatible API with Python.
