@imgly/plugin-ai-image-generation-web 0.2.9 → 0.2.11

package/CHANGELOG.md

@@ -2,6 +2,35 @@
 
 ## [Unreleased]
 
+## [0.2.11] - 2025-11-21
+
+### New Features
+
+-   [generation-web] **Input Placeholder Customization**: Added support for customizing placeholder text in input fields (e.g., prompt textarea) through the i18n translation system. Placeholders follow the same priority chain as labels:
+    1. Provider-specific: `ly.img.plugin-ai-{kind}-generation-web.{provider.id}.property.{field}.placeholder`
+    2. Global: `ly.img.plugin-ai-generation-web.property.{field}.placeholder`
+    3. Provider defaults: `ly.img.plugin-ai-{kind}-generation-web.{provider.id}.defaults.property.{field}.placeholder`
+    4. Global defaults: `ly.img.plugin-ai-generation-web.defaults.property.{field}.placeholder`
+-   [image-generation] **Gemini Provider Placeholders**: Added example placeholder text to Gemini providers (GeminiFlash25 and Gemini25FlashImageEdit) demonstrating provider-specific placeholder customization
+-   [image-generation] **NanoBananaPro Provider**: Added NanoBananaPro text-to-image provider via fal.ai, an enhanced version of NanoBanana with advanced configuration options including 10 aspect ratio presets (1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 9:21, 2.4:1), resolution multipliers (1K, 2K, 4K for standard/high/ultra quality), dynamic dimension calculation based on aspect ratio and resolution, and remixPageWithPrompt quick action support
+-   [image-generation] **NanoBananaProEdit Provider**: Added NanoBananaProEdit image-to-image provider via fal.ai for professional-grade image editing with text prompts, supporting resolution control (1K/2K/4K), all standard quick actions (editImage, swapBackground, styleTransfer, artistTransfer, createVariant, combineImages with up to 10 images, remixPage, remixPageWithPrompt), and automatic dimension preservation from source images
+
+## [0.2.10] - 2025-10-22
+
+### New Features
+
+-   [video-generation] **Google Veo 3.1 Provider Suite**: Added comprehensive Google Veo 3.1 video generation providers via fal.ai, offering multiple models optimized for different use cases:
+    - **Text-to-Video Providers**:
+        - `Veo31TextToVideo`: Standard quality text-to-video with configurable aspect ratios (16:9, 9:16, 1:1), variable duration (4s, 6s, 8s), resolution options (720p, 1080p), and optional audio generation
+        - `Veo31FastTextToVideo`: Faster and more cost-effective text-to-video variant with same capabilities as standard version
+    - **Image-to-Video Providers**:
+        - `Veo31ImageToVideo`: Standard quality image-to-video with auto aspect ratio detection, multiple preset options (16:9, 9:16, 1:1), resolution options (720p, 1080p), fixed 8-second duration, and optional audio generation
+        - `Veo31FastImageToVideo`: Faster and more cost-effective image-to-video variant with same capabilities
+    - **First-Last Frame Providers** (experimental dual-image transformation):
+        - `Veo31FirstLastFrameToVideo`: Standard quality interpolation between two images (first and last frame)
+        - `Veo31FastFirstLastFrameToVideo`: Faster variant with dual image input UI, multiple aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4), resolution options (480p, 720p, 1080p), adjustable duration (2-8 seconds), optional prompt guidance, and optional audio generation
+    - **Quick Action Support**: Added "Animate Between Images" quick action for creating smooth transitions between two selected images using the first-last-frame providers
+
 ## [0.2.9] - 2025-10-16
 
 ### New Features

package/README.md

@@ -718,7 +718,50 @@ cesdk.i18n.setTranslations({
 });
 ```
 
-#### 10. SeedreamV4 (Text-to-Image)
+#### 10. NanoBananaPro (Text-to-Image)
+
+An enhanced version of NanoBanana from fal.ai with advanced aspect ratio and resolution controls:
+
+```typescript
+text2image: FalAiImage.NanoBananaPro({
+  proxyUrl: 'http://your-proxy-server.com/api/proxy',
+  headers: {
+    'x-custom-header': 'value',
+    'x-client-version': '1.0.0'
+  },
+  // Optional: Configure default property values
+  properties: {
+    aspect_ratio: { default: '1:1' },  // Options: '1:1', '3:2', '2:3', '4:3', '3:4', '16:9', '9:16', '21:9', '9:21', '2.4:1'
+    resolution: { default: '1K' },     // Options: '1K', '2K', '4K'
+    output_format: { default: 'png' }     // Options: 'png', 'jpeg', 'webp'
+  }
+})
+```
+
+Key features:
+- Fast generation times for quick prototyping
+- 10 different aspect ratio options (square, portrait, landscape, ultra-wide, cinematic)
+- 3 resolution multipliers (1K, 2K, 4K) for scalable image quality
+- High-quality image output with flexible dimensions
+- Simple prompt-based interface
+- Support for multiple output formats (JPEG, PNG)
+- Configurable number of images (1-4)
+- Supports page remixing with custom prompts
+- Custom headers support for API requests
+
+**Custom Translations:**
+```typescript
+cesdk.i18n.setTranslations({
+  en: {
+    'ly.img.plugin-ai-image-generation-web.fal-ai/nano-banana-pro.property.prompt': 'Describe your image',
+    'ly.img.plugin-ai-image-generation-web.fal-ai/nano-banana-pro.property.aspect_ratio': 'Aspect Ratio',
+    'ly.img.plugin-ai-image-generation-web.fal-ai/nano-banana-pro.property.resolution': 'Resolution',
+    'ly.img.plugin-ai-image-generation-web.fal-ai/nano-banana-pro.property.output_format': 'Output Format'
+  }
+});
+```
+
+#### 11. SeedreamV4 (Text-to-Image)
 
 A powerful text-to-image model from ByteDance's Seedream 4.0 available through fal.ai:
 
@@ -802,6 +845,47 @@ cesdk.i18n.setTranslations({
 });
 ```
 
+#### 13. NanoBananaProEdit (Image-to-Image)
+
+An enhanced image editing model from fal.ai (Pro version of Nano Banana) that transforms existing images using text prompts:
+
+```typescript
+image2image: FalAiImage.NanoBananaProEdit({
+  proxyUrl: 'http://your-proxy-server.com/api/proxy',
+  headers: {
+    'x-custom-header': 'value',
+    'x-client-version': '1.0.0'
+  },
+  // Optional: Configure default property values
+  properties: {
+    num_images: { default: 1 },           // Number of images (1-4)
+    aspect_ratio: { default: 'auto' },    // Aspect ratio (auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16)
+    resolution: { default: '1K' },        // Resolution (1K, 2K, 4K)
+    output_format: { default: 'png' }     // Options: 'png', 'jpeg', 'webp'
+  }
+})
+```
+
+Key features:
+- Professional-grade image editing with text prompts
+- Supports combining multiple images (up to 10 images)
+- Maintains original image dimensions automatically
+- Multiple aspect ratio and resolution options
+- Supports all standard image editing quick actions
+- Fast processing with optimized quality
+- Canvas quick-action integration
+- Custom headers support for API requests
+
+**Custom Translations:**
+```typescript
+cesdk.i18n.setTranslations({
+  en: {
+    'ly.img.plugin-ai-image-generation-web.fal-ai/nano-banana-pro/edit.property.prompt': 'Edit instructions',
+    'ly.img.plugin-ai-image-generation-web.fal-ai/nano-banana-pro/edit.property.image_url': 'Source Image'
+  }
+});
+```
+
 ### Customizing Labels and Translations
 
 You can customize all labels and text in the AI image generation interface using the translation system. This allows you to provide better labels for your users in any language.
@@ -1258,6 +1342,16 @@ FalAiImage.NanoBanana(config: {
 })
 ```
 
+#### NanoBananaPro
+
+```typescript
+FalAiImage.NanoBananaPro(config: {
+  proxyUrl: string;
+  headers?: Record<string, string>;
+  debug?: boolean;
+})
+```
+
 #### NanoBananaEdit
 
 ```typescript
@@ -1268,6 +1362,16 @@ FalAiImage.NanoBananaEdit(config: {
 })
 ```
 
+#### NanoBananaProEdit
+
+```typescript
+FalAiImage.NanoBananaProEdit(config: {
+  proxyUrl: string;
+  headers?: Record<string, string>;
+  debug?: boolean;
+})
+```
+
 #### SeedreamV4
 
 ```typescript
@@ -1383,7 +1487,9 @@ const myImageProvider = {
   - FluxProKontextEdit: `ly.img.ai.fal-ai/flux-pro/kontext`
   - FluxProKontextMaxEdit: `ly.img.ai.fal-ai/flux-pro/kontext/max`
   - NanoBanana: `ly.img.ai.fal-ai/nano-banana`
+  - NanoBananaPro: `ly.img.ai.fal-ai/nano-banana-pro`
   - NanoBananaEdit: `ly.img.ai.fal-ai/nano-banana/edit`
+  - NanoBananaProEdit: `ly.img.ai.fal-ai/nano-banana-pro/edit`
   - SeedreamV4: `ly.img.ai.fal-ai/bytedance/seedream/v4/text-to-image`
   - SeedreamV4Edit: `ly.img.ai.fal-ai/bytedance/seedream/v4/edit`
 
@@ -1402,7 +1508,9 @@ Generated images are automatically stored in asset sources with the following ID
 - FluxProKontextEdit: `fal-ai/flux-pro/kontext.history`
 - FluxProKontextMaxEdit: `fal-ai/flux-pro/kontext/max.history`
 - NanoBanana: `fal-ai/nano-banana.history`
+- NanoBananaPro: `fal-ai/nano-banana-pro.history`
 - NanoBananaEdit: `fal-ai/nano-banana/edit.history`
+- NanoBananaProEdit: `fal-ai/nano-banana-pro/edit.history`
 - SeedreamV4: `fal-ai/bytedance/seedream/v4/text-to-image.history`
 - SeedreamV4Edit: `fal-ai/bytedance/seedream/v4/edit.history`