# boona13/image-extender

Seamlessly extend any image in any direction with AI. Open-source web app powered by Gemini via OpenRouter, with Poisson-blended seams and best-of-3 variant picker.

Repository: https://github.com/boona13/image-extender
Canonical: https://ross.abutalabs.com/products/image-extender
Homepage: https://github.com/boona13/image-extender
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, gemini, image-generation, nano-banana, nextjs, openrouter, outpainting, poisson-blending, tailwindcss, typescript
Last push: 2026-05-31T19:39:52+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 85, release rhythm 35, longevity 7
- inputs: {"age_days": 99, "days_push": 94, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1096, forks 128 (observed 2026-08-28T04:03:34.172698+00:00)

## What it is
An open-source Next.js web app for AI image outpainting that extends images in any direction using Gemini models via OpenRouter, with Poisson blending to hide seams. It also includes studios for generating 2D game art assets such as parallax backgrounds, autotile sets, sprite animations, and decoration props.

## Use cases
- extend an image in any direction with ai
- outpaint a square photo into a widescreen cinematic frame
- generate parallax background layers for a 2d game
- create autotile sets for a platformer
- generate sprite animation sheets for game characters
- make transparent decoration props for tile maps
- remove visible seams when ai-extends an image

## When to choose
- you want a self-hostable, bring-your-own-key outpainting tool
- you need AI-generated 2D game art sets (tiles, sprites, parallax layers) in one studio
- you want seamless Poisson-blended image extension without visible seams

## When to avoid
- you need offline image editing without an AI API key or paid inference
- you need professional raster editing tools like layers and masks
- you target 3D asset generation rather than 2D art

## Facets
- artifact type: application
- maturity: active
- function: image-processing, machine-learning, llm-inference
- domain: image-processing, artificial-intelligence, web-development
- platform: browser
- tags: outpainting, gemini, openrouter, poisson-blending, game-art, parallax-backgrounds, autotiles, sprite-sheets, nextjs, bring-your-own-key, game-development, web-server, nodejs

## Member repositories
- boona13/image-extender (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:34.172698+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:47:09.476223+00:00, confidence not recorded.
  - readme: https://github.com/boona13/image-extender (fetched 2026-08-28T04:03:34.172698+00:00, sha 2cad3a2f8f1a)
  - homepage: https://github.com/boona13/image-extender (fetched 2026-08-29T12:49:57.526349+00:00, sha 1db290ff47a4)
- Data as of 2026-08-30T08:39:29.467469+00:00.