I had someone who wanted very plain instructions on how to get rolling with RunPod and my ComfyUI workflow, Yet Another Workflow. I've decided to put together an article. This process has gotten much simpler as I've had time to improve thing! The new RunPod template cuts out most of the steps. This is aimed at folks who want really basic instructions or are looking for help with problems. There are some gaps here in explaining some basic details of computers like how to use terminal and moving files around that I may flesh out later, but the intention is that following these steps gets you to making stuff.
A new version of this article will be updated with each major release of the workflow with new learnings.
The big news for this article update is that I've now created a custom RunPod template that completely automates using the workflow. Use use the template, and everything will be loaded and ready to go!
If you prefer the previous way, the last version of the article is still intact.
Pre-requisites
A general willingness to poke around. I'm not going to explain how to navigate the RunPod website or the basics of ComfyUI at the moment. Just be curious, and you'll get there.
You'll want to be willing to explore using the command line / terminal / Powershell. You will use it to get files back to your computer with runpotctrl. You don't need to know much, and it's a very useful thing to learn.
The goal I have here is to reduce friction, but I cannot eliminate it. Downloads can fail. Message me if you want hands on help.
Why RunPod?
If you're not using it, please use my link here. We'll both get some free credit. But why use it at all? GPU's are extremely expensive these days, and fast GPU's even more so. Once you break down the usage, the cost of hardware plus electricity doesn't make much sense. (I'm paying less than a $1 an hour for access to an L40S.) You're not locked in to your investment when you rent. When the next gen comes, you'll get a faster card for less than you would have paid upfront. Chances are you're not running your card 100% of the time, so for most folks, buying a card is absolutely the wrong answer in this market.
I've got some cost estimates on the workflow page, if you'd like to read a bit more.
How RunPod + Yet Another Workflow?
Once you have an account and some credit loaded on RunPod, go to the "Pods" section. I'll suggest $10 as a good test amount; it will get you ~11 hours of use. I try to keep my balace at about $5-10; if you hit $0, the pod will be killed which deletes everything, so give yourself a little buffer.
Select L40S (or whichever CUDA 12.8 GPU that you want). I've found the L40S to be the best value in terms of speed/cost. Adjust for your budget and patience.
There are options at the top: Additional Features > CUDA Version > 12.8
You might want to adjust the region: 'Any Region' by deault. Close to you will generally be more responsive.
Select the "Yet Another Workflow - ComfyUI - CUDA12.8 - Wan2.2" template.
Edit the template, set the Container Disk to 260 gb and Volume Disk to 0 gb. You will want to set this based on how many LoRA's you end up wanting to download. The videos you make are small, so you really just need enough room for the models and LoRA's. You can get away with less if you don't mind downloading models as you need them, or you can do more if you want the flexibility. Container Disk is very cheap! I do not recommend Volume Disk, see below.
If you want to download a few LoRA's, Expand the Environmental Variables and set the civitai_token to your CivitAI API key. Then change the LORAS_IDS_TO_DOWNLOAD to a comma separated list of CivitAI LoRA AIR codes (ex: 123456, 123457, 123458).
Double check your settings and press "Deploy on Demand".
The pod will initialize. Eventually, the Log will report that ComfyUI is up, and the service will show as ready. Start up time will take an average of 15 minutes to do all of the installation without extras.
Open one of the YAW workflows in the Workflows menu on the left. If it reports any issues with nodes, which may happen if there were download errors starting the pod, open the "Manager" with the button, and press the "Install Missing Node Groups" button: try and install/fix anything that shows up as having an issue. This can happen randomly. Restart ComfyUI after adressing all of the issues. You may need to repeat this, but probably not.
Press "Run" on the workflow, you should be good to go!
Additional steps you should take:
Install RunPodCtrl on your local machine. This is the best way to get your generations off the RunPod remote machines. Once installed, you can open Web Terminal and type:
runpodctrl send /ComfyUI/output/This will generate a .zip file of all of the videos you've made and create a link for you to run locally. Be patient, it can be slow to create the connect between the computers. Once you have it, paste it on your local command line, and it will send you the files very fast.
Addendum: Why not Volume Disk?
Someone asked about the startup time: Why do 15 minutes of initialization every time when you can store things on a their network storage volumes?
The spin-up time is mostly downloading models. You certainly CAN do this. I don't recommend it unless you want to to pay for Network Volume storage (and you are fine with the first point below), which I do not: I will explain. I'm very cheap about this, so adjust to your budget and time concerns. I want my money to go towards compute time, not storage.
First, an important point: Volume Disk is not portable! You have to create it at a specific datacenter. If your preferred datacenter does not have the GPU you want, you will have to wait till one becomes free. Container disk is always available.
300 gb of storage is $21 a month, so ~$0.70 a day. I'd probably end up closer to 400gb if I was keeping everything around, but we'll use 300gb as an example, since that's what I generally use.
The same 300gb container disk storage is about $0.04 cents an hour.
My total compute costs for L40S total about $0.90 per hour, so it's a ~$0.22 cent startup cost.
That $21 is just over 23 hours of compute time including the container disk, so it's a matter of perfering to maximize my resources that way for the minor inconvenience of waiting for the bootup. That time is never 0, the image still has to initialize, so we're talking 5-10 minutes of difference. Weirdly, so far as I can tell, the Volume Disk cannot act as the main disc for the container, a template must be initialized.
I don't make videos every day. If I take a break, I'm not spending.
So! All of that is to say, that's why I use container disk. I can often fill the boot-up time with other things I want to do: posting videos here on Civit, organizing files, making images for i2v.
As a point of clarification: I do actually use a volume for SD image making, because the space requirement is so much smaller and therefore cheaper. I mostly do this because LoRA management for SD models is a nightmare, where as Wan is very clean.