Available Models
modelBridge.ai connects to 900+ generative AI models hosted on fal.ai, organized into 11 categories. New models appear automatically as fal.ai adds them — the plugin’s schema-driven architecture means no plugin update is needed.
Full Model Capability
Section titled “Full Model Capability”modelBridge passes through every model’s full capability as published by fal.ai. No parameters are removed, no outputs are restricted, and no model behavior is modified. If a model supports a feature on fal.ai, it is available in modelBridge. For model-specific details, see the model’s page on fal.ai/models.
Model Categories
Section titled “Model Categories”| Category | Description | Example Models |
|---|---|---|
| Text-to-Video | Generate video from a text prompt alone | Kling v3, Wan 2.6, LTX 2.3, Veo 3 |
| Image-to-Video | Animate a still image into video | Kling v3, Wan Image-to-Video, Seedance |
| Video-to-Video | Transform existing video with AI | Style transfer, video enhancement |
| Audio-to-Video | Generate video driven by audio input | Music visualizers, audio-reactive video |
| Category | Description | Example Models |
|---|---|---|
| Text-to-Image | Generate images from text prompts | FLUX Pro, FLUX Dev, Stable Diffusion |
| Image-to-Image | Transform, modify, or inpaint existing images | Style transfer, upscaling, inpainting |
| Category | Description | Example Models |
|---|---|---|
| Text-to-Audio | Generate sound effects and music from text | Ambient sounds, music generation |
| Text-to-Speech | Convert text into spoken audio | ElevenLabs, Kokoro, Qwen-TTS |
| Audio-to-Audio | Transform existing audio | Voice conversion, audio enhancement |
| Video-to-Audio | Extract or generate audio from video | Soundtrack generation, audio extraction |
| Speech-to-Speech | Transform spoken audio to different speech | Voice cloning, accent modification |
Finding Models
Section titled “Finding Models”Search
Section titled “Search”Use the search bar at the top of the Models tab to find models by name, creator, or keyword. Search results show model name, category, and a brief description.
Filter Chips
Section titled “Filter Chips”Filter chips below the search bar let you narrow results by category. Click a chip to show only models in that category. Multiple filters can be active at the same time.
Model Cards
Section titled “Model Cards”Each model displays:
- Name and creator
- Category badge
- Media requirements — what input types the model accepts (video, image, audio, text-only)
- Cost estimate — pre-generation pricing when available
Schema-Driven UI
Section titled “Schema-Driven UI”When you select a model, modelBridge.ai fetches the model’s OpenAPI schema from fal.ai and generates the input form dynamically. This means:
- Every parameter the model supports is available in the UI
- Dropdowns, sliders, checkboxes, and text fields are generated based on the schema
- Parameter constraints (min, max, allowed values) are enforced automatically
- No plugin update is needed when a model adds new parameters
Adding Models by ID
Section titled “Adding Models by ID”If you know a model’s fal.ai endpoint path, you can add it directly:
- Go to the Models tab
- Use the “Add model by ID” input
- Enter the endpoint path (e.g.,
fal-ai/kling-video/v3/pro/text-to-video) - The plugin fetches the schema and adds the model to your collection
Category Gating
Section titled “Category Gating”modelBridge.ai only allows models from the 11 supported categories listed above. This ensures that every model in the plugin works end-to-end — from input validation through generation to result import. Unknown or unsupported categories are blocked at all entry points (search, add by ID, import).