feat: add EachLabs partner integration #144
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add scaffolding for EachLabs partner integration with empty provider implementations ready for model additions: - Create eachlabs directories in image and video generation packages - Add provider configuration types and client stubs - Configure package.json exports and esbuild entry points - Add EachLabs as selectable partner in AI example app
…ucture Add Claude skill configuration for EachLabs provider integration: - SKILL.md with provider implementation guidelines - Discovery and implementation checklists - Model discovery script for API exploration - Initial provider specifications document
…age providers Adds complete EachLabs NanoBananaPro provider implementation with: - Text-to-image with 10 aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21, 2.4:1) and multiple resolutions (1K, 2K, 4K) - Image-to-image transformation with resolution options - Full EachLabs API client with prediction polling - Image URL conversion utilities for blob/local URLs - Documentation and translations
…provider Maps aspect ratio values to closest available icons for UI display.
… providers Add Flux 2 Pro provider support via EachLabs API with both T2I and I2I capabilities. The I2I provider supports up to 4 reference images and includes quick action mappings for common editing workflows.
Add missing documentation for EachLabs Flux 2 Pro text-to-image and image-to-image providers including provider descriptions, API reference, panel IDs, and asset history IDs.
…-image providers Add OpenAI GPT Image generation via EachLabs API with: - Text-to-image with 3 format options (Square, Landscape, Portrait) - Image-to-image with full quick actions support (edit, swap background, style transfer, artist transfer, variants, combine images, remix page) - Support for up to 16 reference images in I2I mode
Add documentation for OpenAI GPT Image T2I/I2I providers including API reference, panel IDs, and asset history entries.
…age providers Add ByteDance Seedream v4.5 providers via EachLabs API with support for text-to-image generation and image-to-image editing. Features: - 6 image size options (square HD, square, portrait/landscape 4:3/16:9) - Image-to-image supports up to 10 reference images - Full quick actions support (edit, background swap, style transfer, etc.) - Improved facial details and text generation over v4.0
…ge providers Add Google Gemini 3 Pro image generation via EachLabs: Text-to-Image: - 8 aspect ratio options (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9) - 3 resolution options (1K, 2K, 4K) - Provider ID: eachlabs/gemini-3-pro-image Image-to-Image: - Supports up to 10 reference images - Full quick action support (edit, swap background, style transfer, etc.) - Provider ID: eachlabs/gemini-3-pro-image/edit
- Add provider documentation to README (sections 30-31, API reference) - Update panel IDs and asset history sections - Mark gemini-3-pro-image-preview as implemented in providers.md - Fix ui-guidelines.md to document correct available format icons
Add storage upload functionality to EachLabs clients, aligning with fal.ai and runware implementations. Images are now uploaded to EachLabs storage via the /api/v1/upload endpoint instead of being converted to data URIs. - Add storage.upload() method to image and video clients - Add uploadImageInputToEachLabsIfNeeded() utility functions - Update createImageProvider to use upload instead of data URI conversion - Keep legacy convertImageUrlForEachLabs() for backward compatibility
…viders Add standard Flux 2 providers from Black Forest Labs with 6 image size options and full quick actions support for the image-to-image variant.
Add missing i18n translations for the EachLabs Flux 2 and Seedream v4.5 text-to-image and image-to-image providers including prompt, format (image_size), and source image property labels.
Add .eachlabs/ pattern to the provider-specific translation detection in testTranslations utility so EachLabs provider translations show the @ prefix instead of & when testing translations.
…e providers Add Flux 2 Flex providers with automatic prompt expansion capability: - Text-to-image with 6 image size options - Image-to-image with auto image size detection - Full quick actions support for I2I variant
…ideo providers Add EachLabs video generation support with Kling v2.6 Pro model: - Text-to-video with aspect ratio (16:9, 9:16, 1:1) and duration (5s, 10s) - Image-to-video with duration options and quick action support - Updated createVideoProvider factory for EachLabs video providers - Added translations with placeholder text for prompts
…oviders Add Google Veo 3.1 video generation providers via EachLabs API: - Text-to-video with aspect ratio (16:9, 9:16), resolution (720p, 1080p), and audio options - Image-to-video with resolution options and canvas quick-action integration - Both providers generate 8-second videos with optional audio
Add new EachLabs provider for Kling O1 image-to-video generation which transforms images into 5 or 10 second videos using Kuaishou's Kling O1 model.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Test plan
pnpm --filter "@imgly/plugin-ai-*" check:all