Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| imagen4 | Imagen 4 - Google's latest text-to-image model |
| flux_kontext | FLUX Kontext Pro - State-of-the-art prompt adherence and typography |
| ideogram_v3 | Ideogram V3 - Advanced typography and realistic outputs |
| recraft_v3 | Recraft V3 - Professional design and illustration |
| stable_diffusion_35 | Stable Diffusion 3.5 Large - Improved image quality and performance |
| flux_dev | FLUX Dev - High-quality 12B parameter model |
| hidream | HiDream I1 - High-resolution image generation |
| janus | Janus - Multimodal understanding and generation |
| veo3 | Veo 3 - Google DeepMind's latest with speech and audio |
| kling_master_text | Kling 2.1 Master - Premium text-to-video with motion fluidity |
| pixverse_text | Pixverse V4.5 - Advanced text-to-video generation |
| magi | Magi - Creative video generation |
| luma_ray2 | Luma Ray 2 - Latest Luma Dream Machine |
| wan_pro_text | Wan Pro - Professional video effects |
| vidu_text | Vidu Q1 - High-quality text-to-video |
| ltx_video | LTX Video - Fast and high-quality image-to-video conversion |
| kling_master_image | Kling 2.1 Master I2V - Premium image-to-video conversion |
| pixverse_image | Pixverse V4.5 I2V - Advanced image-to-video |
| wan_pro_image | Wan Pro I2V - Professional image animation |
| hunyuan_image | Hunyuan I2V - Open-source image-to-video |
| vidu_image | Vidu I2V - High-quality image animation |
| luma_ray2_image | Luma Ray 2 I2V - Latest Luma image-to-video |
| list_available_models | List all available models in the current registry with their capabilities |
| execute_custom_model | Execute any FAL model by specifying the endpoint directly |