Banana AI

メディア

Gemini 3 Proで画像を生成・編集

• テキストから画像生成と画像編集
• 最大14枚の入力画像を組み合わせ
• 4Kまでの解像度コントロール

できること

Generate images — Create images from text prompts using Gemini 3 Pro Image

Edit images — Modify existing images with natural language instructions

Multi-image composition — Combine up to 14 input images into a single generation

Resolution control — Choose 1K (default), 2K, or 4K output resolution

Auto-attach — Generated images automatically appear in chat context

Timestamped filenames — Automatic naming prevents overwrites

試してみる質問

"Generate an image of a sunset over mountains"

"Edit this photo to make the sky more dramatic"

"Combine these 3 images into a panoramic scene"

"Create a 4K wallpaper of a cyberpunk city"

"Change the background in this product photo to white"

プロのコツ

Requires GEMINI_API_KEY environment variable

Higher resolutions (4K) take longer but provide excellent detail

Multi-image composition enables creative mashups and comparisons

Edit mode preserves the original composition while modifying specific elements

Auto-attach means generated images are immediately available for follow-up edits

Use specific style keywords in prompts for better results: "photorealistic", "watercolor", "flat illustration"