Skip to main content
Gemini 2.0 Flash is Google’s multimodal model with image editing capabilities, available through Starrise AI via the native Gemini API. It can edit existing images based on text instructions.

​
Key Capabilities

  • Image editing — Modify existing images using natural language instructions
  • Multimodal input — Accepts both text instructions and source images
  • Text generation — Also supports standard text generation tasks
  • Efficient and flexible — Suitable for a variety of multimodal tasks

​
Quick Example

curl "https://ai.alad.com/v1beta/models/gemini-2.0-flash:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          { "text": "Replace the background with a beach scene" },
          { "inline_data": { "mime_type": "image/png", "data": "BASE64_DATA" } }
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": ["IMAGE"]
    }
  }'

​
Parameters

ParameterTypeRequiredDescription
keystringYesAPI key (query parameter)
contentsarrayYesArray of { role, parts } with text and inline_data
generationConfig.responseModalitiesarrayYesMust include IMAGE

API Reference

View the interactive API Playground for Gemini 2.0 Flash.