# How OpenArt scaled their Gen AI art platform on hundreds of GPUs

DevFeed: [How OpenArt scaled their Gen AI art platform on hundreds of GPUs](<https://devfeed.tech/articles/how-openart-scaled-their-gen-ai-art-platform-on-hundreds-of-gpus-79912.md>)

Original publisher: [Read original article](<https://modal.com/blog/openart-case-study>)

Author: Modal

Published: 2024-11-20T12:00:00Z

Content type: article

Language: en

Sources: [Modal](<https://devfeed.tech/sources/modal.md>)

Topics: [comfyui](<https://devfeed.tech/topics/comfyui.md>), [Cloud Gaming](<https://devfeed.tech/topics/cloud-gaming.md>), [internal developer platform](<https://devfeed.tech/topics/internal-developer-platform.md>), [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [CUDA](<https://devfeed.tech/topics/cuda.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [autoscaling](<https://devfeed.tech/tags/autoscaling.md>), [aws](<https://devfeed.tech/tags/aws.md>), [developer](<https://devfeed.tech/tags/developer.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [gcp](<https://devfeed.tech/tags/gcp.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [modal](<https://devfeed.tech/tags/modal.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

## AI overview

OpenArt uses Modal to deploy customized ComfyUI image-generation workflows. The case study describes switching from inflexible model APIs and slow self-managed AWS and GCP deployments to programmatic cloud deployment, reducing deployment time from hours to minutes. Modal autoscaling supports hundreds of GPU containers, and the platform powers more than 100 OpenArt workflows.

## Source excerpt

Find out how OpenArt uses Modal to deploy highly customized ComfyUI workflows used by millions of customers