Imagen 3

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 Image generation Digital watermarking and verification User-configurable safety settings Prompt enhancement using prompt rewriter Person generation GA allowlist feature 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 Provisioned Throughput 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 Image generation Digital watermarking and verification User-configurable safety settings Negative prompting Person generation GA allowlist feature 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 Provisioned Throughput 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 Image generation Digital watermarking and verification User-configurable safety settings Negative prompting Person generation GA allowlist feature 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 Provisioned Throughput 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 Image generation Digital watermarking and verification Prompt enhancement using prompt rewriter Upscale images Person generation
Usage types	Supported Not supported Provisioned Throughput
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.