@imgly/plugin-ai-video-generation-web 0.2.12 → 0.2.15

package/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 ## [Unreleased]
 
+## [0.2.15] - 2026-01-12
+
+### New Features
+
+-   [all] **EachLabs Partner Integration**: Added EachLabs as a new AI provider service with unified API access to multiple image and video generation models.
+    - **Image Generation**: Flux 2 Pro, Flux 2, Flux 2 Flex, Nano Banana Pro, OpenAI GPT Image, Seedream v4.5, Gemini 3 Pro (all with text-to-image and image-to-image variants)
+    - **Video Generation**: Kling v2.6 Pro, Kling O1, Veo 3.1 (text-to-video and image-to-video variants)
+
+## [0.2.14] - 2025-12-15
+
+## [0.2.13] - 2025-12-15
+
+### New Features
+
+-   [all] **Runware Partner Integration**: Added Runware as a new AI provider service, offering access to multiple image and video generation models through a unified API. Runware provides a single endpoint for accessing various AI models with consistent configuration.
+    - **Image Generation**: FLUX.2 [dev], FLUX.2 [pro], FLUX.2 [flex], Seedream 4.0, Seedream 4.5, Nano Banana 2 Pro, GPT Image 1, GPT Image 1 Mini (all with text-to-image and image-to-image variants)
+    - **Video Generation**: Google Veo 3.1, Veo 3.1 Fast, OpenAI Sora 2, Sora 2 Pro (all with text-to-video and image-to-video variants)
+
 ## [0.2.12] - 2025-11-21
 
 ## [0.2.11] - 2025-11-21

package/README.md

@@ -33,6 +33,8 @@ To use the plugin, import it and configure it with your preferred providers:
 import CreativeEditorSDK from '@cesdk/cesdk-js';
 import VideoGeneration from '@imgly/plugin-ai-video-generation-web';
 import FalAiVideo from '@imgly/plugin-ai-video-generation-web/fal-ai';
+// For Runware providers
+import RunwareVideo from '@imgly/plugin-ai-video-generation-web/runware';
 
 // Initialize CreativeEditor SDK
 CreativeEditorSDK.create(domElement, {
@@ -498,6 +500,213 @@ Key features:
 
 **Note:** This provider uses a custom UI implementation with two image input fields (first_frame_url and last_frame_url) instead of the standard single image selector. This is a proof-of-concept implementation for handling multiple image inputs in video generation.
 
+### Runware Providers
+
+Runware provides access to multiple AI video models through a unified API. These providers require a Runware proxy URL for authentication.
+
+#### 14. Veo31 (Text-to-Video & Image-to-Video) via Runware
+
+Google's Veo 3.1 model accessed through Runware:
+
+```typescript
+// Text-to-Video
+text2video: RunwareVideo.Veo31.Text2Video({
+    proxyUrl: 'http://your-runware-proxy.com/api/proxy'
+})
+
+// Image-to-Video
+image2video: RunwareVideo.Veo31.Image2Video({
+    proxyUrl: 'http://your-runware-proxy.com/api/proxy'
+})
+```
+
+Key features:
+- Google's latest video generation model via Runware
+- Text-to-video and image-to-video support
+- Aspect ratios: 16:9, 9:16
+- Duration: Fixed at 8 seconds
+- Optional audio generation
+- Async delivery with polling
+
+#### 15. Veo31Fast (Text-to-Video & Image-to-Video) via Runware
+
+Faster version of Google's Veo 3.1 model:
+
+```typescript
+// Text-to-Video
+text2video: RunwareVideo.Veo31Fast.Text2Video({
+    proxyUrl: 'http://your-runware-proxy.com/api/proxy'
+})
+
+// Image-to-Video
+image2video: RunwareVideo.Veo31Fast.Image2Video({
+    proxyUrl: 'http://your-runware-proxy.com/api/proxy'
+})
+```
+
+Key features:
+- Faster generation times
+- Same capabilities as Veo31
+- More cost-effective
+- Aspect ratios: 16:9, 9:16
+- Duration: Fixed at 8 seconds
+
+#### 16. Sora2 (Text-to-Video & Image-to-Video) via Runware
+
+OpenAI's Sora 2 video generation model:
+
+```typescript
+// Text-to-Video
+text2video: RunwareVideo.Sora2.Text2Video({
+    proxyUrl: 'http://your-runware-proxy.com/api/proxy'
+})
+
+// Image-to-Video
+image2video: RunwareVideo.Sora2.Image2Video({
+    proxyUrl: 'http://your-runware-proxy.com/api/proxy'
+})
+```
+
+Key features:
+- OpenAI's advanced video generation model
+- Text-to-video and image-to-video support
+- Accurate physics simulation
+- Synchronized dialogue and high-fidelity visuals
+- Resolutions: 1280×720, 720×1280
+- Durations: 4, 8, or 12 seconds
+
+#### 17. Sora2Pro (Text-to-Video & Image-to-Video) via Runware
+
+Professional version of OpenAI's Sora 2:
+
+```typescript
+// Text-to-Video
+text2video: RunwareVideo.Sora2Pro.Text2Video({
+    proxyUrl: 'http://your-runware-proxy.com/api/proxy'
+})
+
+// Image-to-Video
+image2video: RunwareVideo.Sora2Pro.Image2Video({
+    proxyUrl: 'http://your-runware-proxy.com/api/proxy'
+})
+```
+
+Key features:
+- Enhanced quality over standard Sora 2
+- Text-to-video and image-to-video support
+- Professional-grade output
+- Resolutions: 1280×720, 720×1280, 1792×1024 (7:4), 1024×1792 (4:7)
+- Durations: 4, 8, or 12 seconds
+
+### EachLabs Providers
+
+EachLabs provides access to multiple AI video models through a unified API. These providers require an EachLabs proxy URL for authentication.
+
+#### 18. KlingV26ProTextToVideo (Text-to-Video) via EachLabs
+
+Kling v2.6 Pro text-to-video model accessed through EachLabs:
+
+```typescript
+import EachLabsVideo from '@imgly/plugin-ai-video-generation-web/eachlabs';
+
+text2video: EachLabsVideo.KlingV26ProTextToVideo({
+    proxyUrl: 'http://your-eachlabs-proxy.com/api/proxy',
+    // Optional: Configure default values
+    middlewares: [rateLimitMiddleware, errorMiddleware]
+})
+```
+
+Key features:
+- Kling v2.6 Pro - latest high-quality video generation
+- Aspect ratios: 16:9, 9:16, 1:1
+- Duration: 5 or 10 seconds
+- Native audio generation (Chinese/English)
+- Async delivery with polling
+
+#### 19. KlingV26ProImageToVideo (Image-to-Video) via EachLabs
+
+Kling v2.6 Pro image-to-video model:
+
+```typescript
+import EachLabsVideo from '@imgly/plugin-ai-video-generation-web/eachlabs';
+
+image2video: EachLabsVideo.KlingV26ProImageToVideo({
+    proxyUrl: 'http://your-eachlabs-proxy.com/api/proxy',
+    // Optional: Configure default values
+    middlewares: [rateLimitMiddleware, errorMiddleware]
+})
+```
+
+Key features:
+- Transform existing images into videos
+- Duration: 5 or 10 seconds
+- Native audio generation (Chinese/English)
+- Canvas quick-action integration
+- Maintains image aspect ratio
+
+#### 20. KlingO1ImageToVideo (Image-to-Video) via EachLabs
+
+Kling O1 image-to-video model:
+
+```typescript
+import EachLabsVideo from '@imgly/plugin-ai-video-generation-web/eachlabs';
+
+image2video: EachLabsVideo.KlingO1ImageToVideo({
+    proxyUrl: 'http://your-eachlabs-proxy.com/api/proxy',
+    // Optional: Configure default values
+    middlewares: [rateLimitMiddleware, errorMiddleware]
+})
+```
+
+Key features:
+- Transform existing images into videos
+- Duration: 5 or 10 seconds
+- Canvas quick-action integration
+- Maintains image aspect ratio
+
+#### 22. Veo31TextToVideo (Text-to-Video) via EachLabs
+
+Google's Veo 3.1 text-to-video model accessed through EachLabs:
+
+```typescript
+import EachLabsVideo from '@imgly/plugin-ai-video-generation-web/eachlabs';
+
+text2video: EachLabsVideo.Veo31TextToVideo({
+    proxyUrl: 'http://your-eachlabs-proxy.com/api/proxy',
+    // Optional: Configure default values
+    middlewares: [rateLimitMiddleware, errorMiddleware]
+})
+```
+
+Key features:
+- Google's Veo 3.1 - high-quality text-to-video generation
+- Aspect ratios: 16:9, 9:16
+- Resolution: 720p or 1080p
+- 8-second video duration
+- Optional audio generation
+- Async delivery with polling
+
+#### 23. Veo31ImageToVideo (Image-to-Video) via EachLabs
+
+Google's Veo 3.1 image-to-video model:
+
+```typescript
+import EachLabsVideo from '@imgly/plugin-ai-video-generation-web/eachlabs';
+
+image2video: EachLabsVideo.Veo31ImageToVideo({
+    proxyUrl: 'http://your-eachlabs-proxy.com/api/proxy',
+    // Optional: Configure default values
+    middlewares: [rateLimitMiddleware, errorMiddleware]
+})
+```
+
+Key features:
+- Transform existing images into videos
+- Resolution: 720p or 1080p
+- 8-second video duration
+- Optional audio generation
+- Canvas quick-action integration
+
 ### Feature Control
 
 You can control various aspects of the video generation plugin using the Feature API:
@@ -871,6 +1080,90 @@ FalAiVideo.Veo31FastFirstLastFrameToVideo(config: {
 }): AiVideoProvider
 ```
 
+### Runware Providers
+
+All Runware video providers use the following configuration:
+
+```typescript
+interface RunwareProviderConfiguration {
+  proxyUrl: string;        // HTTP endpoint URL for the Runware proxy
+  debug?: boolean;         // Enable debug logging
+  middlewares?: any[];     // Optional middleware functions
+  history?: false | '@imgly/local' | '@imgly/indexedDB' | (string & {});
+}
+```
+
+#### Veo31.Text2Video / Veo31.Image2Video
+
+```typescript
+RunwareVideo.Veo31.Text2Video(config: RunwareProviderConfiguration)
+RunwareVideo.Veo31.Image2Video(config: RunwareProviderConfiguration)
+```
+
+#### Veo31Fast.Text2Video / Veo31Fast.Image2Video
+
+```typescript
+RunwareVideo.Veo31Fast.Text2Video(config: RunwareProviderConfiguration)
+RunwareVideo.Veo31Fast.Image2Video(config: RunwareProviderConfiguration)
+```
+
+#### Sora2.Text2Video / Sora2.Image2Video
+
+```typescript
+RunwareVideo.Sora2.Text2Video(config: RunwareProviderConfiguration)
+RunwareVideo.Sora2.Image2Video(config: RunwareProviderConfiguration)
+```
+
+#### Sora2Pro.Text2Video / Sora2Pro.Image2Video
+
+```typescript
+RunwareVideo.Sora2Pro.Text2Video(config: RunwareProviderConfiguration)
+RunwareVideo.Sora2Pro.Image2Video(config: RunwareProviderConfiguration)
+```
+
+### EachLabs Providers
+
+All EachLabs video providers use the following configuration:
+
+```typescript
+interface EachLabsProviderConfiguration {
+  proxyUrl: string;        // HTTP endpoint URL for the EachLabs proxy
+  debug?: boolean;         // Enable debug logging
+  middlewares?: any[];     // Optional middleware functions
+  history?: false | '@imgly/local' | '@imgly/indexedDB' | (string & {});
+}
+```
+
+#### KlingV26ProTextToVideo
+
+```typescript
+EachLabsVideo.KlingV26ProTextToVideo(config: EachLabsProviderConfiguration)
+```
+
+#### KlingV26ProImageToVideo
+
+```typescript
+EachLabsVideo.KlingV26ProImageToVideo(config: EachLabsProviderConfiguration)
+```
+
+#### KlingO1ImageToVideo
+
+```typescript
+EachLabsVideo.KlingO1ImageToVideo(config: EachLabsProviderConfiguration)
+```
+
+#### Veo31TextToVideo
+
+```typescript
+EachLabsVideo.Veo31TextToVideo(config: EachLabsProviderConfiguration)
+```
+
+#### Veo31ImageToVideo
+
+```typescript
+EachLabsVideo.Veo31ImageToVideo(config: EachLabsProviderConfiguration)
+```
+
 ## UI Integration
 
 The plugin automatically registers the following UI components:
@@ -899,6 +1192,19 @@ The plugin automatically registers the following UI components:
     -   Veo31ImageToVideo: `ly.img.ai.fal-ai/veo3.1/image-to-video`
     -   Veo31FastImageToVideo: `ly.img.ai.fal-ai/veo3.1/fast/image-to-video`
     -   Veo31FastFirstLastFrameToVideo: `ly.img.ai.fal-ai/veo3.1/fast/first-last-frame-to-video`
+    -   Runware Veo31.Text2Video: `ly.img.ai.runware/google/veo-3-1`
+    -   Runware Veo31.Image2Video: `ly.img.ai.runware/google/veo-3-1/image2video`
+    -   Runware Veo31Fast.Text2Video: `ly.img.ai.runware/google/veo-3-1-fast`
+    -   Runware Veo31Fast.Image2Video: `ly.img.ai.runware/google/veo-3-1-fast/image2video`
+    -   Runware Sora2.Text2Video: `ly.img.ai.runware/openai/sora-2`
+    -   Runware Sora2.Image2Video: `ly.img.ai.runware/openai/sora-2/image2video`
+    -   Runware Sora2Pro.Text2Video: `ly.img.ai.runware/openai/sora-2-pro`
+    -   Runware Sora2Pro.Image2Video: `ly.img.ai.runware/openai/sora-2-pro/image2video`
+    -   EachLabs KlingV26ProTextToVideo: `ly.img.ai.eachlabs/kling-v2-6-pro-text-to-video`
+    -   EachLabs KlingV26ProImageToVideo: `ly.img.ai.eachlabs/kling-v2-6-pro-image-to-video`
+    -   EachLabs KlingO1ImageToVideo: `ly.img.ai.eachlabs/kling-o1-image-to-video`
+    -   EachLabs Veo31TextToVideo: `ly.img.ai.eachlabs/veo3-1-text-to-video`
+    -   EachLabs Veo31ImageToVideo: `ly.img.ai.eachlabs/veo3-1-image-to-video`
 
 ### Asset History
 
@@ -918,6 +1224,19 @@ Generated videos are automatically stored in asset sources with the following ID
 -   Veo31ImageToVideo: `fal-ai/veo3.1/image-to-video.history`
 -   Veo31FastImageToVideo: `fal-ai/veo3.1/fast/image-to-video.history`
 -   Veo31FastFirstLastFrameToVideo: `fal-ai/veo3.1/fast/first-last-frame-to-video.history`
+-   Runware Veo31.Text2Video: `runware/google/veo-3-1.history`
+-   Runware Veo31.Image2Video: `runware/google/veo-3-1/image2video.history`
+-   Runware Veo31Fast.Text2Video: `runware/google/veo-3-1-fast.history`
+-   Runware Veo31Fast.Image2Video: `runware/google/veo-3-1-fast/image2video.history`
+-   Runware Sora2.Text2Video: `runware/openai/sora-2.history`
+-   Runware Sora2.Image2Video: `runware/openai/sora-2/image2video.history`
+-   Runware Sora2Pro.Text2Video: `runware/openai/sora-2-pro.history`
+-   Runware Sora2Pro.Image2Video: `runware/openai/sora-2-pro/image2video.history`
+-   EachLabs KlingV26ProTextToVideo: `eachlabs/kling-v2-6-pro-text-to-video.history`
+-   EachLabs KlingV26ProImageToVideo: `eachlabs/kling-v2-6-pro-image-to-video.history`
+-   EachLabs KlingO1ImageToVideo: `eachlabs/kling-o1-image-to-video.history`
+-   EachLabs Veo31TextToVideo: `eachlabs/veo3-1-text-to-video.history`
+-   EachLabs Veo31ImageToVideo: `eachlabs/veo3-1-image-to-video.history`
 
 ### Dock Integration