Run Stable Diffusion and Flux as an API
Host SDXL, Flux, or any diffusion checkpoint behind a cloud API.
Fast inference for image generation
Serve generative models behind an autoscaling API on managed GPUs.
Serve any checkpoint or LoRA
Load SDXL, Flux, SD 1.5, or your own fine-tuned weights from Hugging Face or a volume, and stack LoRAs at runtime.
Explore docsGPU Checkpoint Restore
Speed up cold boots by creating snapshots of the GPU state, so containers don't reload model weights into vRAM when they spin up.
Explore docsScale with bursts
Image traffic is spiky. Endpoints scale out on demand and back to zero.
Explore docsHosted image outputs
Save results with Output and return public URLs straight from your endpoint, so you don't have to push results to S3.
Explore docsWeights cached in volumes
Keep multi-gigabyte checkpoints on a persistent volume shared across containers. Storage is not billed yet. Planned: $0.0001 per GB-hour of data stored, with no free allowance.
Explore docsGPUs from 4090s to B300s
Run lighter checkpoints on 4090s and reserve B300s for big models. Switching takes one line.
Explore docsSwitching to Beam has been really helpful. It has addressed all the pain points we had with Replicate, enabling us to provide a better, more reliable service to our customers.
Simon Brami, Founder, Gepetto
faster cold boots than their previous provider
saved monthly
production uptime
Ship an image API in three steps
Load the pipeline once
Load your checkpoint when the container boots, so requests reuse the warm pipeline instead of reloading weights.
Deploy the endpoint
beam deploy gives you an authenticated HTTPS URL backed by autoscaling GPUs.
Generate over HTTP
POST a prompt and get back a hosted image URL. Beam handles queuing, scaling, and auth.
$ beam deploy app.py:generate
=> Deployed 🎉
=> https://sdxl-abc123.app.beam.cloud
$ curl -X POST https://sdxl-abc123.app.beam.cloud \
-H 'Authorization: Bearer YOUR_TOKEN' \
-d '{"prompt": "isometric voxel city at dusk"}'
{"url": "https://app.beam.cloud/output/id/8b0d..."}Frequently asked questions
Which models can I host?
Anything diffusers can load: SDXL, SD 1.5, Flux, plus your own fine-tuned checkpoints and LoRAs.
How does this compare to per-image APIs like Replicate or fal?
Per-image platforms charge a markup on every generation, and your model options are limited to their catalog. On Beam you deploy your own checkpoints and LoRAs, pay per-second for the GPU while it's generating, and your code stays private.
How are images returned?
Save them with Output and return a hosted public URL, or base64-encode them into the JSON response.
What about cold starts with large checkpoints?
Keep weights on a volume so containers skip the download, and use on_start so each container loads the pipeline exactly once.
Can I keep an endpoint warm?
Yes. Set keep_warm_seconds to hold containers hot for latency-sensitive apps, and let everything else scale to zero.
Do I need to manage queues for burst traffic?
No. Autoscaling is managed by Beam. Set your scaling policy and containers are added as request volume grows.
Related use cases
Turn ComfyUI workflows into production APIs
Turn ComfyUI workflows into autoscaling API endpoints.
Training & Fine-tuningFine-tune models on GPUs
LoRA and QLoRA fine-tuning on serverless GPUs.
InferenceGenerative media on serverless GPUs
Text-to-video on H100s with hosted outputs and no reserved GPUs.
Give your agents their own machines
Sign up, install the CLI, and launch a sandbox, VM, or GPU from your terminal or your coding agent.