feat(models): add Klein, Klein-Large, and Wan models with updated tests - #29
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
ℹ️ Recent review infoConfiguration used: defaults Review profile: CHILL Plan: Free 📒 Files selected for processing (2)
📝 WalkthroughWalkthroughAdds Klein image models and Wan video model, introduces model legacy flags and active/legacy APIs, implements a full-featured lightbox edit/compare UI with related hooks and utilities, updates pricing/schema and branding text, and includes many test and config changes across the codebase. Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Lightbox as "Lightbox UI"
participant Hook as "useImageEdit Hook"
participant API as "Generation API"
participant Storage as "Image Storage Service"
User->>Lightbox: open edit panel / submit edit (prompt, model, tier)
Lightbox->>Hook: submitEdit(prompt, model, dimensions)
Hook->>API: POST /generate (params, sourceImage)
API-->>Hook: 202 Accepted / jobId
Hook->>Lightbox: update isGenerating state -> show GenerationLoadingOverlay
API->>Storage: async store generated artifact / callback
Storage-->>Hook: notify completion (url, metadata)
Hook->>Lightbox: onSuccess(receive image, versions) -> update versions and UI
Lightbox->>User: display new version in LightboxVersionStrip
Estimated code review effort🎯 5 (Critical) | ⏱️ ~120 minutes Poem
Tip Issue Planner is now in beta. Read the docs and try it out! Share your feedback on Discord. Note 🎁 Summarized by CodeRabbit FreeYour organization is on the Free plan. CodeRabbit will generate a high-level summary and a walkthrough for each pull request. For a comprehensive line-by-line review, please upgrade your subscription to CodeRabbit Pro by visiting https://app.coderabbit.ai/login. Comment |
|
@coderabbitai review |
✅ Actions performedReview triggered.
|
Mark paid-only models as legacy (isLegacy: true): - Image: gptimage-large, seedream-pro, nanobanana-pro, kontext, turbo, seedream, nanobanana - Video: seedance-pro, veo, wan Active models kept for generation: - flux, zimage, klein, klein-large, gptimage, seedance Marketing updates: - Competitor comparison: 180 -> 900,000 images (Flux Schnell baseline) - Model showcase: Complete rebuild with active models only - Features: 13+ -> 6 AI Models - SEO: Updated all meta descriptions - README: Updated feature list - Upgrade modal: Fixed model count and references All tests passing (2319/2320)
Klein 9B (klein-large) API enforces different constraints than Klein 4B: - maxPixels: 1,048,576 (1MP) instead of 4MP - minDimension: 256px instead of 64px - supportedTiers: SD/HD only (2K exceeds 1MP limit) Added separate FLUX_KLEIN_9B_ASPECT_RATIOS optimized for 1MP budget. Co-authored-by: Cursor <cursoragent@cursor.com>
Summary by CodeRabbit
New Features
Tests
Chores