Imagen 3 is our current line of image generation models. This page documents the capabilities and features of the Imagen 3 models.
3.0 Generate 002
Model ID
imagen-3.0-generate-002
Supported inputs & outputs
- Inputs:
Text - Outputs:
Images
Capabilities
- Supported
- Not supported
- Image customization using few-shot learning
- Subject customization for product, person, and animal companion
- Style customization
- Controlled customization
- Instruct customization or style transfer
- Mask-based image editing
- Insert objects in images
- Remove objects from images
- Outpainting
- Product image editing
- Upscale images
- Negative prompting
Usage types
- Supported
- Not supported
Technical specifications
Images
- Maximum image size: 10MB
- Maximum number of output images per prompt: 4
- Supported aspect ratios: 1:1, 3:4, 4:3, 9:16, and 16:9
- Supported resolutions: 1024x1024, 896x1280, 1280x896, 768x1408, 1408x768
- Supported MIME types:
image/png,image/jpeg
Prompt languages
- English
- Chinese (simplified) Preview feature
- Chinese (traditional) Preview feature
- Hindi Preview feature
- Japanese Preview feature
- Korean Preview feature
- Portuguese Preview feature
- Spanish Preview feature
Quotas
- Regional online prediction requests per base model per minute per base model: 20
3.0 Generate 001
Model ID
imagen-3.0-generate-001
Supported inputs & outputs
- Inputs:
Text - Outputs:
Images
Capabilities
- Supported
- Not supported
- Prompt enhancement using prompt rewriter
- Image customization using few-shot learning
- Subject customization for product, person, and animal companion
- Style customization
- Controlled customization
- Instruct customization or style transfer
- Mask-based image editing
- Insert objects in images
- Remove objects from images
- Outpainting
- Product image editing
- Upscale images
Usage types
- Supported
- Not supported
Technical specifications
Images
- Maximum image size: 10MB
- Maximum number of output images per prompt: 4
- Supported aspect ratios: 1:1, 3:4, 4:3, 9:16, and 16:9
- Supported resolutions: 1024x1024, 896x1280, 1280x896, 768x1408, 1408x768
- Supported MIME types:
image/png,image/jpeg
Prompt languages
- English
- Chinese (simplified) Preview feature
- Chinese (traditional) Preview feature
- Hindi Preview feature
- Japanese Preview feature
- Korean Preview feature
- Portuguese Preview feature
- Spanish Preview feature
Quotas
- Regional online prediction requests per base model per minute per base model: 20
3.0 Fast Generate 001
Model ID
imagen-3.0-fast-generate-001
Supported inputs & outputs
- Inputs:
Text - Outputs:
Images
Capabilities
- Supported
- Not supported
- Prompt enhancement using prompt rewriter
- Image customization using few-shot learning
- Subject customization for product, person, and animal companion
- Style customization
- Controlled customization
- Instruct customization or style transfer
- Mask-based image editing
- Insert objects in images
- Remove objects from images
- Outpainting
- Product image editing
- Upscale images
Usage types
- Supported
- Not supported
Technical specifications
Images
- Maximum image size: 10MB
- Maximum number of output images per prompt: 4
- Supported aspect ratios: 1:1, 3:4, 4:3, 9:16, and 16:9
- Supported resolutions: 1024x1024, 896x1280, 1280x896, 768x1408, 1408x768
- Supported MIME types:
image/png,image/jpeg
Prompt languages
- English
- Chinese (simplified) Preview feature
- Chinese (traditional) Preview feature
- Hindi Preview feature
- Japanese Preview feature
- Korean Preview feature
- Portuguese Preview feature
- Spanish Preview feature
Quotas
- Regional online prediction requests per base model per minute per base model: 200
3.0 Capability 001
Model ID
imagen-3.0-capability-001
Supported inputs & outputs
- Inputs:
Images , text - Outputs:
Images
Capabilities
- Supported
- User-configurable safety settings
- Image customization using few-shot learning
- Subject customization for product, person, and animal companion
- Style customization
- Controlled customization
- Instruct customization or style transfer
- Mask-based image editing
- Insert objects in images
- Remove objects from images
- Outpainting
- Product image editing
- Negative prompting
- Not supported
Usage types
- Supported
- Not supported
Technical specifications
Images
- Maximum image size: 10MB
- Maximum number of output images per prompt: 4
- Supported aspect ratios: 1:1, 3:4, 4:3, 9:16, and 16:9
- Supported resolutions: 1024x1024, 896x1280, 1280x896, 768x1408, 1408x768
- Supported MIME types:
image/png,image/jpeg
Prompt languages
- English
- Chinese (simplified) Preview feature
- Chinese (traditional) Preview feature
- Hindi Preview feature
- Japanese Preview feature
- Korean Preview feature
- Portuguese Preview feature
- Spanish Preview feature
Quotas
- Regional online prediction requests per base model per minute per base model: 100
For Imagen pricing information, see the Imagen section of the Cost of building and deploying AI models in Vertex AI page.
