Real-time
generative media
inference
Build the next generation of creativity with fal. Lightning fast inference.
Realtime Models#
Stable Diffusion Turbo (v1.5/XL)Run SDXL at the speed of light
text-to-image
real-time
optimized
Stable Diffusion Turbo (v1.5/XL)Run SDXL at the speed of lightimage-to-image
real-time
optimized
Stable Diffusion Turbo (v1.5/XL)Run SDXL at the speed of lightimage-to-image
real-time
inpainting
Latent Consistency Models (v1.5/XL)Run SDXL at the speed of lighttext-to-image
real-time
lcm
Latent Consistency Models (v1.5/XL)Run SDXL at the speed of lightimage-to-image
real-time
lcm
Latent Consistency Models (v1.5/XL)Run SDXL at the speed of lightimage-to-image
real-time
lcm
Stable Diffusion XL LightningRun SDXL at the speed of lighttext-to-image
real-time
optimized
Hyper SDXLHyper-charge SDXL's performance and creativity.text-to-image
real-time
optimized
Latent Consistency (SDXL & SDv1.5)Produce high-quality images with minimal inference steps.text-to-image
real-time
lcm
Optimized Latent Consistency (SDv1.5)Produce high-quality images with minimal inference steps. Optimized for 512x512 input image size.image-to-image
real-time
lcm
SDXL Realtime#
This fast inference capability opens up new possibilities for application types that were previously not feasible, such as real-time creativity tools and using the camera as a real-time model input.
# of steps2
Inference time0.214s
Fal Demos for Realtime#
Face Control - Realtime
Control the face of a character in real-time.
Live Portrait - Realtime
Turn live footage of yourself into an animated portrait of any character.
Realtime Birefnet
Realtime Birefnet - API demo by fal.ai
Realtime Camera
Turn live footage into artistic images or simulations at over 30+ fps.