README
¶
Google Imagen Provider
Google Imagen 4.0 provider for image generation using the Gemini API.
Requirements
✅ Works with AI Studio API keys - No Google Cloud billing required!
- Google AI Studio API key (same as Gemini)
- Access via
generativelanguage.googleapis.comendpoint - Model:
imagen-4.0-generate-001
Configuration
apiVersion: promptkit.altairalabs.ai/v1alpha1
kind: Provider
metadata:
name: imagen-provider
spec:
type: imagen
model: imagen-4.0-generate-001
Note: Project ID and location are no longer required when using the Gemini API endpoint.
Environment Variables
GOOGLE_API_KEYorGEMINI_API_KEY- Required for authentication
Cost
- $0.04 per image (fixed cost, not token-based)
- No token counting
API Details
- Endpoint:
https://generativelanguage.googleapis.com/v1beta/models/{model}:predict - Authentication:
x-goog-api-keyheader (same as Gemini) - Method: POST
- Request format:
{"instances": [{"prompt": "..."}], "parameters": {"sampleCount": 1, ...}} - Response format:
{"predictions": [{"bytesBase64Encoded": "...", "mimeType": "image/png"}]}
Limitations
- No streaming support
- Works with AI Studio API keys (no GCP billing required!)
- Only supports image generation (no analysis or multimodal understanding)
- Always generates PNG format - cannot generate JPEG, WebP, or other formats
- Cannot convert or manipulate existing images
- Generates one image per request (even if prompt asks for multiple)
Alternative for Testing
For testing image generation scenarios without GCP billing:
- Use the
mockprovider with pre-generated images - Or implement an OpenAI DALL-E provider (requires OpenAI API key)
Documentation
¶
Overview ¶
Package imagen provides Google Imagen image generation provider integration.
Index ¶
- type Config
- type Provider
- func (p *Provider) CalculateCost(inputTokens, outputTokens, cachedTokens int) types.CostInfo
- func (p *Provider) Close() error
- func (p *Provider) Generate(ctx context.Context, req base.ImageRequest) (base.ImageResponse, error)
- func (p *Provider) Model() string
- func (p *Provider) Predict(ctx context.Context, req providers.PredictionRequest) (providers.PredictionResponse, error)
- func (p *Provider) PredictStream(ctx context.Context, req providers.PredictionRequest) (<-chan providers.StreamChunk, error)
- func (p *Provider) Pricing() *base.PricingDescriptor
- func (p *Provider) SupportsStreaming() bool
- func (p *Provider) Type() base.ProviderType
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Config ¶
type Config struct {
ID string
Model string
BaseURL string
ApiKey string
ProjectID string
Location string
IncludeRawOutput bool
Defaults providers.ProviderDefaults
}
ImagenConfig holds configuration for creating an Imagen provider
type Provider ¶
type Provider struct {
providers.BaseProvider
BaseURL string
ApiKey string
ProjectID string
Location string
Defaults providers.ProviderDefaults
HTTPClient *http.Client
// contains filtered or unexported fields
}
Provider implements the Provider interface for Google's Imagen image generation
func NewProvider ¶
NewProvider creates a new Imagen provider
func (*Provider) CalculateCost ¶
CalculateCost calculates cost breakdown (simplified for Imagen)
func (*Provider) Generate ¶
func (p *Provider) Generate(ctx context.Context, req base.ImageRequest) (base.ImageResponse, error)
Generate satisfies base.ImageProvider. It delegates to Predict by translating the ImageRequest into the legacy PredictionRequest shape internally, then extracts the image bytes back into an ImageResponse.
This is a thin shim — call sites that already use Predict continue to work. Future PRs can migrate call sites to Generate directly.
func (*Provider) Predict ¶
func (p *Provider) Predict(ctx context.Context, req providers.PredictionRequest) (providers.PredictionResponse, error)
Predict generates images based on the last user message
func (*Provider) PredictStream ¶
func (p *Provider) PredictStream( ctx context.Context, req providers.PredictionRequest, ) (<-chan providers.StreamChunk, error)
PredictStream is not supported for image generation
func (*Provider) Pricing ¶
func (p *Provider) Pricing() *base.PricingDescriptor
Pricing returns Imagen's per-image pricing descriptor.
func (*Provider) SupportsStreaming ¶
SupportsStreaming returns false for Imagen
func (*Provider) Type ¶
func (p *Provider) Type() base.ProviderType
Type returns base.ProviderTypeImage. Imagen is an image generation provider, not an inference provider — overriding the default from the embedded providers.BaseProvider helper.
Source Files