Model registry
See all available model APIs provided by fal.ai
Run Stable Diffusion with customizable LoRA weights.
Run SDXL at the speed of light
Whisper is a model for speech transcription and translation.
Produce high-quality images with minimal inference steps.
Produce high-quality images with minimal inference steps. Optimized for 512x512 input image size.
Execute Comfy workflows in fal.
Default parameters with automated optimizations and quality improvements.
SAM.
Animate Your Texts!
Create illusions conditioned on image.
Create depth maps using Midas depth estimation.
Stylize your videos
Remove the background from an image.
Upscale images by a given factor.
Generate Images with ControlNet.
Inpaint images with SD and SDXL
Animate Your Texts with Latent Consistency Models!
Generate short video clips from your images.