SDXL 1.0 Speed Test How Fast Is ComfyUi vs Invoke ai vs Automatic1111?

SDXL 1.0 Speed Test How Fast Is ComfyUi vs Invoke ai vs Automatic1111? (UPDATED VIDEO TO COME)
I was very curious to compare these 3 platforms generation speeds for Stable Diffusion XL 1.0 and I was quite surprised from the results. I tested 768x1024 and 1024x1024 on all 3 platforms keeping the settings consistent through out. Now this wasn't a advanced benchmark test but it did give me a better idea on how each platform performs in comparison.

⏲Time Stamps
0:00 How I ran the tests
0:41 System Specs
1:19 Auto1111 768x1024
1:52 Auto1111 1024x1024
2:37 Invoke ai 768x1024
3:08 Invoke ai 1024x1024
3:36 ComfyUi 768x1024
4:01 ComfyUi 1024x1024
4:30 Benchmark Summary
5:12 Final thoughts

**Disclaimer Affiliate Links Below**

📸 Gear I use

🎵 Epidemic Sound

🔦 Find us on:

[MonzonMedia]

Hope you enjoyed this fun little test! I'm curious to know how fast these platforms run on your system? Let me know your specs and general speeds!

[aliusfzh]

Thank you for producing this video, it was very helpful for me
I am from Iran

[hleet]

Thanks for theses metric, really cool to know

[DoubleBob]

You have preview enabled on A1111, which means you have VAE decoding and rendering every few iterations. This changes the speed quite a lot on older hardware. Just deactivate preview and it should be as quick as the others.

[_grnchh]

Comfy is faster for me, I'm on a 4GB 1050 ti (I don't use XL but just SD 1.5) and Comfy is much faster. The problem is how complicated everything is to get set up and it seems that using ControlNet in Comfy is much slower than in A1111.

[SBaldo]

I believe the couple seconds difference between comfy and invoke can be attributed to the preview, none in comfy, quite a few intermediate images in invoke

[ВикторияКузьмина-мз]

Is there a setting somewhere in InvokeAI equivalent to AUTOMATIC1111's Clip Skip ?

[internetceo]

Thanks for that Video 👌. If you can, try comparing the speeds of even more programs.

[diva]

Thank you for the great comparison video! I've definitely seen that ComfyUi speeds are much faster than Automatic1111 in my own tests. I wonder how Fooocus holds up in a test like this?

[gatotboediman]

aha. you are the Playground sensei! I have subscribed, to both. thank you for the tutorials

[iqbalfajry]

hello I'm still a beginner and still learning SDXL, if I use Ryzen 5600x with VGA gtx 1660s which one do you think I should use, is it automatic 1111 comfy or invoke?

[MrAsmadaseggs]

This video will need reevaluating very shortly as new A1111 RC 1.6 build has vastly improved its SDXL method to be more competitive.

[Grimmona]

I have just six Gigabyte VRAM and I had to run on the lowram comment on automatic1111(one picture needs round about 8 minutes) to get any picture on SDXL i'm going to try today if it's still necessary or if I can use midram. If that's not working I will finally try ConfiUI

[jorgennorstrom]

i usually generate images in ComfyUI and then do afterwork in A1111

[udappkuma]

AUTOMATIC1111 v1.6.0-RC is almost fast as comfyUI for me, its three times faster than AUTOMATIC1111 v1.5, my generation time went from 57seconds to 17seconds for 1024X1024 generations..

[Heldn]

Can you redo this in least update for now day's

[rickykngo]

How is Ho Chi Minh appear on your intro?

[fixelheimer]

I guess with more vram the difference between these will become smaller.

[jaroslavstreit]

Seems it's wrongly tested... what about VRAM?

[DasLooney]

Thanks for the video it's nice to see how the different software affects render time on your system! However, without knowing your rig specs CPU GPU RAM it really isn't as helpful as it could be. That would be most helpful! (NOTE: I messed up and missed where you did exactly that. My apologies and thanks to the people that quickly pointed out my mistake.)