# What's the cheapest way to keep my ComfyUI setup between cloud GPU sessions without paying for idle GPUs or re-downloading models every time?

> Never keep a GPU machine running just to keep a setup: stop or terminate it, and keep the setup somewhere that bills for storage only. A network volume does that inside one region of one provider; a nest does it outside any one provider. Either way the models still have to come down onto the next machine. What you save is the reinstalling and the trial and error, not the download.

Canonical page: https://renest.ai/answers/keep-setup-between-sessions

<h2 id="idle">How do I avoid paying for RunPod when I'm not actually using ComfyUI?</h2>

<p>Stop or terminate the pod as soon as you're done, and don't let keeping your setup be the
reason it stays on. A stopped pod still bills for its disk, and the GPU it had may be gone
when you come back. A terminated pod bills nothing, and everything not saved elsewhere is
gone with it. So the real question is where your setup lives while no machine is
running.</p>

<h2 id="where">Where should my setup live between sessions?</h2>

<ul>
  <li><strong>A network volume</strong> keeps your files in one region of one provider and
  bills while idle. It suits you if you rent often, always in that region. Your Python
  packages and system libraries still live in the container, so a new pod may need
  reinstalling.</li>
  <li><strong>A nest on your Renest drive</strong> keeps the files, the exact package versions
  and the record of what the machine provided, away from any one provider. It suits you if
  you use a GPU now and then, or take whichever provider and region has a card free.</li>
</ul>

<p><a href="/answers/volume-image-snapshot-compared">Volume, image, snapshot or nest</a>
compares them in full.</p>

<h2 id="steps">How do I pause a cloud GPU and resume later without losing my ComfyUI setup?</h2>

<p>At the end of a session, once the workflow has rendered, pack it to your drive — from the
<a href="/docs/plugin-nest-this-run">ComfyUI panel</a>, or:</p>

<pre>$ renest pack --dir ./run --workflow workflow-api.json --out ./nests --dest hosted</pre>

<p>Once it reports the nest stored, terminate the machine. If a large upload ends with "Uploaded, not confirmed yet", every byte is already on your drive and the server is still checking it: don't pack again, and run the check command it prints before you terminate. Next time, rent any machine
(the <a href="/docs/guide-runpod">RunPod</a> and <a href="/docs/guide-vast">vast.ai</a>
guides show how), open the nest in the web console, choose <strong>Restore</strong>, and paste
the command it gives you:</p>

<pre>$ cd /workspace 2&gt;/dev/null || cd ~
$ renest restore --grant grant.json --dir ./run
$ renest start --dir ./run</pre>

<p>The restore checks the machine before downloading, checks every file against its recorded
checksum, reinstalls the exact package versions and runs your workflow once. The code isn't
tied to one machine: if that pod turns out broken, terminate it and paste the same command on
another. Packing again later adds a new version of the same nest, and files already stored
aren't stored again — see <a href="/docs/whole-file-dedup">Whole-file
deduplication</a>.</p>

<h2 id="download">Do I still have to re-download my models every session?</h2>

<p>Yes — onto a fresh machine the bytes have to come down from somewhere, whichever way you
keep them. A network volume avoids that only when the next pod mounts the same volume in the
same region. What a nest saves is the part after the download: reinstalling nodes and
packages, and working out what broke.</p>

<h2 id="cost">What does keeping a setup on Renest cost?</h2>

<p>Storage on the drive is priced by plan; see <a href="/pricing">Pricing</a>. The GPU
machine is rented by you, from whichever provider you choose, and billed by them.</p>

<h2 id="not">When Renest isn't the answer</h2>

<ul>
  <li><strong>You rent every day in the same region</strong> — a network volume is the
  simpler choice.</li>
  <li><strong>You want the cheapest GPU</strong> — Renest isn't a GPU provider and doesn't
  compare them; it only lets your setup follow you to whichever one you pick.</li>
  <li><strong>Your setup has never worked yet</strong> — get it working first; Renest packs
  runs that already worked.</li>
</ul>

<p>Related: <a href="/answers/what-to-back-up">What a ComfyUI backup has to include</a> ·
<a href="/docs/restore">Restore a nest</a> ·
<a href="/docs/escape-hatch">The escape hatch</a></p>