# Remote VAEs for decoding with Inference Endpoints 🤗

DevFeed: [Remote VAEs for decoding with Inference Endpoints 🤗](<https://devfeed.tech/articles/remote-vaes-for-decoding-with-inference-endpoints-7456.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/remote_vae>)

Author: hlky; Sayak Paul

Published: 2025-02-24T00:00:00Z

Content type: tutorial

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [VAE](<https://devfeed.tech/topics/vae.md>), [inference-endpoints](<https://devfeed.tech/topics/inference-endpoints.md>), [diffusers](<https://devfeed.tech/topics/diffusers.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Deadlock](<https://devfeed.tech/topics/deadlock.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [concurrency](<https://devfeed.tech/tags/concurrency.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [data](<https://devfeed.tech/tags/data.md>), [diffusers](<https://devfeed.tech/tags/diffusers.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [generate](<https://devfeed.tech/tags/generate.md>), [generation](<https://devfeed.tech/tags/generation.md>), [getting-started](<https://devfeed.tech/tags/getting-started.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hdd](<https://devfeed.tech/tags/hdd.md>), [inference](<https://devfeed.tech/tags/inference.md>), [inference-endpoints](<https://devfeed.tech/tags/inference-endpoints.md>), [nvme](<https://devfeed.tech/tags/nvme.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [queue](<https://devfeed.tech/tags/queue.md>), [remote](<https://devfeed.tech/tags/remote.md>), [tensors](<https://devfeed.tech/tags/tensors.md>), [time](<https://devfeed.tech/tags/time.md>), [vae](<https://devfeed.tech/tags/vae.md>)

## AI overview

This article presents an experimental approach for decoding latent-space diffusion outputs with remote VAEs hosted on Inference Endpoints. It explains how remote decoding can reduce consumer GPU memory pressure, avoid the quality loss associated with tiled decoding, and improve concurrency by queueing generation requests. The article includes setup and usage examples for random tensors and pipelines involving SD v1.5, Flux, and HunyuanVideo.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.