How to generate images from text prompts using the Image Generation tool in the Chatbot
The Image Generation tool lets you create AI-generated images from text prompts directly within the chat interface — powered by Nano Banana 2.
When Image Generation is enabled, describe an image in your prompt and the model generates it inline within the chat. You can generate images from scratch, edit uploaded images, blend multiple images, or create variations — all from within the conversation.
Common use cases:
Ad creatives and campaign visuals
Brand mood boards and visual references
UI concept visualization and wireframe illustrations
Storyboarding and narrative visuals
Social media content drafts
Toggle Image Generation on in the Toolkit panel. Include your image description in the prompt — be specific about style, composition, tone, and subject for better results.
Example prompt:
A minimalist flat-design illustration of a robot reading a book,
soft pastel colors, white background, suitable for a tech blog header.Generate from scratch
Describe the image in your prompt
Edit an uploaded image
Attach your image in the message and describe the edit
Edit a previously generated image
Reference the image by its position in the conversation (e.g., "edit the third image")
Blend multiple images
Upload 2 or more images and describe the desired composition
Keep character consistent
Use character consistency prompts across multiple scenes
Generate variations
Ask for multiple outputs from the same prompt
Change output size
Specify resolution in your prompt (0.5K to 4K) and aspect ratio
The more specific your prompt, the more accurate the output. Include details like style (photorealistic, illustration, flat design), mood, color palette, and intended use.
Last updated