Deploy fully customizable image and video pipelines
“As a startup, you need to iterate on things quickly. So it’s really helpful when the development speed is suddenly 10x. It’s a lot easier to deploy a ComfyUI workflow because Modal is serverless, so it auto-scales really well.”
“We are constantly shipping the most cutting-edge creative AI machine learning techniques so our customers have access to the best creative models. Modal has helped us streamline the process from idea to deployed pipeline, allowing us to both deploy quickly & scale rapidly.”
For companies graduating from image and video APIs
Custom models
Deploy fine-tuned or proprietary models
Multiple adapters
Layer on any combination of adapters, from LoRA to ControlNet
Custom workflows
Deploy complex ComfyUI workflows that use custom nodes
Reliably autoscale to thousands of GPUs
Modal’s Rust-based container stack spins up GPUs in < 1s.
Modal autoscales up and down for max cost efficiency.
Modal’s proprietary cloud capacity orchestrator guarantees high GPU availability.
Deploy low-latency image and video apps
Serve interactive experiences anywhere with our global GPU fleet.
Reduce cold starts by 10x for models and custom ComfyUI nodes with GPU memory snapshotting.
Achieve 20ms networking latency for video streams using WebRTC on Modal.