Loading pattern preview
Loading preview…
PatternsSDK API
AI SDK Nano Banana Image Merge
AI SDK Nano Banana Image Merge
Generate, edit, and merge images using Nano Banana 2.5 Flash. Create new images from text, edit existing ones with natural language, or merge two images together. Includes version history and image comparison.
Loading pattern preview
Loading preview…
Problems solved
Technical challenges this implementation handles out of the box.
- Merge multiple source images into a new Gemini Flash composition
- Guide composition with structured prompts and references
- Preview merged outputs for creative iteration
Use cases
Products and workflows this pattern is designed to support.
- Collage and composite generators
- Moodboard merge tools
- Campaign visual mashups
- Multi-reference product imagery
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in — then wire env vars and routes the same way.
- 1
Install from the preview toolbar
Copy the install command above and run it in your project — Pro patterns include a short-lived token.
- 2
Add environment variables to .env.local
GOOGLE_AI_API_KEY, AI_GATEWAY_API_KEY, UPSTASH_REDIS_REST_URL, UPSTASH_REDIS_REST_TOKEN
- 3
Customize the agent and tool files
Adapt prompts, tools, and stop conditions for your product — Copy for AI in the toolbar helps seed that work.
- 4
Run your dev server and open the pattern route
Install dependencies if needed, then start the app and verify responses.
Environment variables
Capabilities
AI SDK APIs
generateTextgatewayProviders
Gemini
External services
Upstash
Files added
10 filesapp/page.tsxapp/layout.tsxapp/create-image-action.tsxapp/edit-image-action.tsxapp/merge-image-action.tsxlib/rate-limit.tslib/image-utils.tshooks/use-image-version.tshooks/image-version-context.tsxREADME.md
Dependencies
9 totalnpm packages
6UpstashAISDKlucide-reactNext.jsReactsonner
Registry components
buttondialoginput-group
Critical files
app/create-image-action.tsxServer action for image creation using gateway + Gemini flash image model.
app/edit-image-action.tsxServer action for image editing: multimodal message with image data URL + edit instructions sent to Gemini.
app/merge-image-action.tsxUnique to this block: server action that merges two images by processing both into data URLs and constructing a multimodal message with two image inputs + merge instructions.
lib/image-utils.tsExtended image processing utilities including MergeImageData type. Essential for create/edit/merge operations.
hooks/use-image-version.tsExtended state machine hook: adds merge-specific state and actions (setImage1/2, setMergedImage, merge steps). Complex multi-reducer architecture managing three operational modes.
Requirements
- Complexity
- Intermediate
- Setup time
- ~20 minutes
- Node
- 24+
- Memory
- 512MB
