chore: import upstream snapshot with attribution

examples/google-imagen/README.md

@@ -0,0 +1,133 @@
+# google-imagen (Google Imagen)
+
+This example demonstrates Google image generation models, including both Imagen and Gemini native image generation.
+
+You can run this example with:
+
+```bash
+npx promptfoo@latest init --example google-imagen
+cd google-imagen
+```
+
+## Prerequisites
+
+You can use Imagen models through either Google AI Studio or Vertex AI:
+
+### Option 1: Google AI Studio (Quick Start, Limited Features)
+
+- Get an API key from [Google AI Studio](https://aistudio.google.com/apikey)
+- **Supports**: Imagen 4 models only
+- **Limitations**: No `seed` or `addWatermark` parameters
+
+### Option 2: Vertex AI (Full Features)
+
+- Google Cloud project with billing enabled
+- Vertex AI API enabled
+- Authentication via `gcloud auth application-default login`
+- **Supports**: All Imagen models and all parameters
+
+## Setup
+
+### For Google AI Studio:
+
+```bash
+# Set your API key (Unix/Linux/macOS)
+export GOOGLE_API_KEY=your-api-key
+
+# For Windows Command Prompt:
+# set GOOGLE_API_KEY=your-api-key
+
+# For Windows PowerShell:
+# $env:GOOGLE_API_KEY="your-api-key"
+```
+
+### For Vertex AI:
+
+```bash
+# Enable Vertex AI API
+gcloud services enable aiplatform.googleapis.com
+
+# Authenticate
+gcloud auth application-default login
+
+# Set project ID (Unix/Linux/macOS)
+export GOOGLE_PROJECT_ID=your-project-id
+
+# For Windows Command Prompt:
+# set GOOGLE_PROJECT_ID=your-project-id
+
+# For Windows PowerShell:
+# $env:GOOGLE_PROJECT_ID="your-project-id"
+```
+
+## Environment Variables
+
+- `GOOGLE_API_KEY` - Google AI Studio API key (Option 1)
+- `GOOGLE_PROJECT_ID` - Your Google Cloud project ID (Option 2)
+
+## Available Models
+
+### Imagen Models (use `google:image:` prefix)
+
+- `imagen-4.0-ultra-generate-001` - Ultra quality ($0.06/image)
+- `imagen-4.0-generate-001` - Standard quality ($0.04/image)
+- `imagen-4.0-fast-generate-001` - Fast generation ($0.02/image)
+- `imagen-3.0-generate-002` - Imagen 3.0 ($0.04/image)
+
+Google has deprecated the Imagen 4 models with an August 17, 2026 shutdown and recommends `gemini-3.1-flash-image` as the replacement. The older `imagen-4.0-*-preview-06-06` ids are already shut down.
+
+### Gemini Native Image Generation
+
+- `google:gemini-3.1-flash-lite-image` - Gemini 3.1 Flash-Lite (Nano Banana 2 Lite) for the fastest, lowest-cost image generation (~$0.034/image at 1K; 1K only)
+- `google:gemini-3.1-flash-image` - Gemini 3.1 Flash (Nano Banana 2) with native image generation (~$0.067/image at 1K)
+- `google:gemini-3-pro-image` - Gemini 3 Pro (Nano Banana Pro) with native image generation (~$0.134/image at 1K/2K)
+- `google:gemini-2.5-flash-image` - Gemini 2.5 Flash (Nano Banana) with image generation (~$0.039/image)
+
+Use the GA ids above; Google shut down the `gemini-3.1-flash-image-preview` and `gemini-3-pro-image-preview` aliases on June 25, 2026. Nano Banana 2 Lite never had a `-preview` alias.
+
+## Running the Example
+
+```bash
+npx promptfoo@latest eval
+```
+
+## Notes
+
+- Imagen models are available through both **Google AI Studio** and **Vertex AI**
+- **Google AI Studio**:
+  - Uses API key authentication (quick start)
+  - Only supports Imagen 4 models (4.0 preview models)
+  - Limited parameter support:
+    - No `seed` or `addWatermark` parameters
+    - Only `block_low_and_above` safety filter level
+- **Vertex AI**:
+  - Requires authentication via `gcloud auth application-default login`
+  - Supports all Imagen models (both 3.0 and 4.0)
+  - Full parameter support:
+    - All safety filter levels (`block_most`, `block_some`, `block_few`, `block_fewest`)
+    - `seed` for deterministic generation
+    - `addWatermark` control
+  - You must provide a Google Cloud project ID either via:
+    - `GOOGLE_PROJECT_ID` environment variable
+    - `projectId` in the provider config
+- Seed and watermark parameters are mutually exclusive (Vertex AI only)
+
+## Advanced Configuration
+
+See `promptfooconfig-advanced.yaml` for examples of platform-specific configurations that take advantage of each platform's unique capabilities.
+
+## Gemini Native Image Generation
+
+Gemini models can generate images natively using the `generateContent` API with `responseModalities` set to include images. This is different from Imagen which uses a dedicated image generation endpoint.
+
+See `promptfooconfig-gemini.yaml` for Gemini native image generation examples.
+See `promptfooconfig-gemini-grounding.yaml` for Google Search-grounded Gemini image generation.
+
+Key differences from Imagen:
+
+- Uses the same `google:` provider namespace as Gemini chat (models with `-image` in the name automatically enable image generation)
+- Supports additional aspect ratios: `1:4`, `1:8`, `2:3`, `3:2`, `4:1`, `4:5`, `5:4`, `8:1`, `21:9`
+- Supports image resolution: `512px` (Gemini 3.1), `1K`, `2K`, `4K`
+- Can return both text and images in the same response
+- Uses the same authentication as Gemini chat models
+- Supports Google Search grounding via `tools: [{ googleSearch: {} }]`

examples/google-imagen/promptfooconfig-advanced.yaml

@@ -0,0 +1,44 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Advanced Imagen configuration showing platform-specific settings
+
+prompts:
+  - 'Create a {{quality}} image of {{subject}} with {{style}} aesthetic'
+
+providers:
+  # Google AI Studio configuration (API key authentication)
+  - id: google:image:imagen-4.0-generate-001
+    label: Imagen 4.0 (Google AI Studio)
+    config:
+      aspectRatio: '16:9'
+      safetyFilterLevel: 'block_low_and_above' # Only value supported by Google AI Studio
+      # Note: seed and addWatermark are not supported in Google AI Studio
+
+  # Vertex AI configuration (OAuth authentication)
+  - id: google:image:imagen-4.0-generate-001
+    label: Imagen 4.0 (Vertex AI)
+    config:
+      projectId: 'your-project-id' # Forces Vertex AI usage
+      aspectRatio: '16:9'
+      safetyFilterLevel: 'block_some' # Vertex AI supports all safety levels
+      seed: 42 # Deterministic generation
+      addWatermark: false # Disable watermark (incompatible with seed)
+
+  # Imagen 3.0 - Only available through Vertex AI
+  - id: google:image:imagen-3.0-generate-002
+    label: Imagen 3.0 (Vertex AI only)
+    config:
+      projectId: 'your-project-id'
+      aspectRatio: '1:1'
+      safetyFilterLevel: 'block_fewest'
+      personGeneration: 'allow_adult'
+
+tests:
+  - vars:
+      quality: 'photorealistic'
+      subject: 'a serene mountain landscape'
+      style: 'golden hour photography'
+    assert:
+      - type: javascript
+        value: |
+          // Check if the output contains a valid image data URL
+          return output.includes('![Generated Image](data:image/')

examples/google-imagen/promptfooconfig-gemini-grounding.yaml

@@ -0,0 +1,24 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Gemini image generation with search grounding
+
+prompts:
+  - 'Create a travel poster for {{city}} using real landmarks and current points of interest'
+
+providers:
+  - id: google:gemini-3.1-flash-image-preview
+    config:
+      imageAspectRatio: '16:9'
+      imageSize: '1K'
+      tools:
+        - googleSearch: {}
+
+defaultTest:
+  assert:
+    - type: javascript
+      value: output.length > 0 && (output.startsWith('data:image/') || output.startsWith('promptfoo://blob/'))
+
+tests:
+  - vars:
+      city: 'Tokyo'
+  - vars:
+      city: 'Paris'

examples/google-imagen/promptfooconfig-gemini.yaml

@@ -0,0 +1,67 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Gemini native image generation
+
+prompts:
+  - 'Create a {{quality}} image of {{subject}} with {{style}} aesthetic'
+
+providers:
+  # Gemini 2.5 Flash - Fast image generation (generally available)
+  # Note: imageSize is not supported for Gemini 2.5 models
+  - id: google:gemini-2.5-flash-image
+    config:
+      imageAspectRatio: '16:9'
+
+  # Gemini 3.1 Flash Image (Nano Banana 2)
+  # imageSize supports: 512px, 1K, 2K, 4K (this model only; see per-model notes below)
+  - id: google:gemini-3.1-flash-image
+    config:
+      imageAspectRatio: '16:9'
+      imageSize: '2K'
+
+  # Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite)
+  # Fastest, lowest-cost tier; 1K resolution only; no Google Search grounding
+  - id: google:gemini-3.1-flash-lite-image
+    config:
+      imageAspectRatio: '16:9'
+      imageSize: '1K'
+
+  # Gemini 3 Pro Image (Nano Banana Pro) — advanced generation, global endpoint only
+  # imageSize supports: 1K, 2K, 4K
+  - id: google:gemini-3-pro-image
+    config:
+      imageAspectRatio: '16:9'
+      imageSize: '2K'
+
+defaultTest:
+  assert:
+    # Verify that an image was generated (images land in the structured
+    # providerResponse.images field; output alone is text when the model
+    # also returns text parts)
+    - type: javascript
+      value: '(context.providerResponse?.images?.length ?? 0) > 0'
+
+tests:
+  - vars:
+      quality: 'photorealistic'
+      subject: 'a futuristic spacecraft'
+      style: 'cinematic sci-fi'
+
+  - vars:
+      quality: 'highly detailed'
+      subject: 'starry night over a cyberpunk city'
+      style: 'Van Gogh painting'
+
+  - vars:
+      quality: 'minimalist'
+      subject: 'a zen garden at sunrise'
+      style: 'Japanese ink wash'
+
+  - vars:
+      quality: 'vibrant'
+      subject: 'tropical birds in a rainforest'
+      style: 'watercolor illustration'
+
+  - vars:
+      quality: 'dramatic'
+      subject: 'a medieval castle during a thunderstorm'
+      style: 'fantasy art'

examples/google-imagen/promptfooconfig.yaml

@@ -0,0 +1,65 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Google Imagen image generation comparison
+
+prompts:
+  - 'Create a {{quality}} image of {{subject}} with {{style}} aesthetic'
+
+providers:
+  # Ultra quality - highest detail and quality
+  - id: google:image:imagen-4.0-ultra-generate-001
+    config:
+      # projectId: 'your-project-id'  # Optional: Can be set here or via GOOGLE_PROJECT_ID env var
+      aspectRatio: '16:9'
+      # seed: 42  # Note: seed is only supported in Vertex AI, not Google AI Studio
+      # safetyFilterLevel: 'block_some'  # Note: Google AI Studio only supports 'block_low_and_above'
+      # addWatermark: false  # Note: addWatermark is only supported in Vertex AI
+
+  # Standard quality - balanced quality and speed
+  - id: google:image:imagen-4.0-generate-001
+    config:
+      aspectRatio: '16:9'
+      # seed: 42  # Note: seed is only supported in Vertex AI
+      # safetyFilterLevel: 'block_some'  # Note: Google AI Studio only supports 'block_low_and_above'
+      # addWatermark: false  # Note: addWatermark is only supported in Vertex AI
+
+  # Fast generation - optimized for speed
+  - id: google:image:imagen-4.0-fast-generate-001
+    config:
+      aspectRatio: '16:9'
+      # seed: 42  # Note: seed is only supported in Vertex AI
+      # safetyFilterLevel: 'block_some'  # Note: Google AI Studio only supports 'block_low_and_above'
+      # addWatermark: false  # Note: addWatermark is only supported in Vertex AI
+
+  # Previous generation for comparison
+  - id: google:image:imagen-3.0-generate-002
+    config:
+      aspectRatio: '16:9'
+      # seed: 42  # Note: seed is only supported in Vertex AI
+      # safetyFilterLevel: 'block_some'  # Note: Google AI Studio only supports 'block_low_and_above'
+      # addWatermark: false  # Note: addWatermark is only supported in Vertex AI
+
+tests:
+  - vars:
+      quality: 'photorealistic'
+      subject: 'a futuristic spacecraft'
+      style: 'cinematic sci-fi'
+
+  - vars:
+      quality: 'highly detailed'
+      subject: 'starry night over a cyberpunk city'
+      style: 'Van Gogh painting'
+
+  - vars:
+      quality: 'minimalist'
+      subject: 'a zen garden at sunrise'
+      style: 'Japanese ink wash'
+
+  - vars:
+      quality: 'vibrant'
+      subject: 'tropical birds in a rainforest'
+      style: 'watercolor illustration'
+
+  - vars:
+      quality: 'dramatic'
+      subject: 'a medieval castle during a thunderstorm'
+      style: 'fantasy art'