Enable Replicate and fal.ai alongside existing Gemini integration
Phases:
1. Provider Infrastructure: API key storage and settings UI
2. Model Discovery: Dynamic model fetching from provider APIs
3. Generate Node Refactor: Multi-model support in generic Generate node
4. Model Search Dialog: Floating icons and searchable model browser
5. Image URL Server: Local endpoint for URL-based providers
6. Video & Polish: Video playback and parameter customization
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
shrimbly