Getting Started
Introduction
RunComfy lets you take any ComfyUI workflow and instantly turn it into a serverless API, giving you a direct path from prototype to production without the operational headaches. Your generative AI pipelines become scalable, production-ready endpoints, no servers to maintain, no GPUs to provision, no dependency conflicts to chase down.
Behind the scenes, RunComfy packages your entire workflow, nodes, models, dependencies, and hardware settings into a fully reproducible cloud environment. Containerization ensures that what you deploy today will run exactly the same tomorrow, while cloud orchestration scales on demand. You get to focus on building and iterating, while RunComfy handles everything else.
Deploy your cloud-saved ComfyUI workflows as serverless APIs in just a few clicks, with full control over hardware selection (GPUs from 16GB to 80GB) and autoscaling behavior. Your deployments automatically adjust instance counts based on traffic, with options to fine-tune minimum/maximum instances, queue size, and keep-warm durations, giving you the balance between cost efficiency and responsiveness. Dynamic Overrides for Customization
Send inference requests that override only the inputs you want to change, such as prompts, seeds, or media URLs/Base64 data, without resending the entire workflow JSON. This keeps requests lightweight and enables fast, flexible adjustments while preserving default settings for everything else. Monitoring and Retrieval
Stay in control of your asynchronous inference jobs: poll for status updates, fetch results like images or videos when they’re ready, and cancel queued requests if needed. You decide when and how to interact with your running jobs. Versioning and Iteration
Manage workflow updates with confidence through built-in versioning. Test new versions in isolation, then roll them out to production without downtime or disruption to existing deployments. Pay-Per-Use Pricing
Only pay for the GPU time you actually use. Whether your workload is steady or comes in bursts, transparent pay-per-use billing keeps costs predictable and under control.
Key Features
Workflow Deployment and ManagementDeploy your cloud-saved ComfyUI workflows as serverless APIs in just a few clicks, with full control over hardware selection (GPUs from 16GB to 80GB) and autoscaling behavior. Your deployments automatically adjust instance counts based on traffic, with options to fine-tune minimum/maximum instances, queue size, and keep-warm durations, giving you the balance between cost efficiency and responsiveness. Dynamic Overrides for Customization
Send inference requests that override only the inputs you want to change, such as prompts, seeds, or media URLs/Base64 data, without resending the entire workflow JSON. This keeps requests lightweight and enables fast, flexible adjustments while preserving default settings for everything else. Monitoring and Retrieval
Stay in control of your asynchronous inference jobs: poll for status updates, fetch results like images or videos when they’re ready, and cancel queued requests if needed. You decide when and how to interact with your running jobs. Versioning and Iteration
Manage workflow updates with confidence through built-in versioning. Test new versions in isolation, then roll them out to production without downtime or disruption to existing deployments. Pay-Per-Use Pricing
Only pay for the GPU time you actually use. Whether your workload is steady or comes in bursts, transparent pay-per-use billing keeps costs predictable and under control.