Which interface are you primarily using for Stable diffusion?

3 years ago by Zarxrax to c/stable_diffusion

I was using stable diffusion a lot previously, but haven't really touched it in the past several months. I was wondering what interfaces people are using these days?

Automatic1111 still seems to be popular, and that's the one I am most familiar with. I know there are some others now though, like comfy, and I guess maybe invokeAI is still going?

Flicsmo 7 points 3 years ago

Automatic1111's Stable Diffusion WebUI is hard to give up, with how many features it has that are missing in other frontends. I use anapnoe's fork for a slightly better UI. I would use vladmandic's fork, but some of the changes have caused issues for my particular setup.

path: 0 738680, hotness: undefined, score: 7, children: 0
2dollarsim 7 points 3 years ago

Automatic1111 is the second one I tried and I never left. It's the best.

path: 0 754645, hotness: undefined, score: 7, children: 0
Swexti 4 points 3 years ago

Is no-one here running ComfyUI? It's one of my favorite UI's as it's completely node based and extensive! Has everything auto1111 has and even more! EDIT: It's not really everything, but almost!

path: 0 825880, hotness: undefined, score: 4, children: 1
KiranWells 1 point 3 years ago

I'm also using ComfyUI. It just has the ability to do so much more than something like Automatic1111, even if it is missing a couple of features. For example, I have several workflows that do incremental changes to a photo, changing the prompt halfway through the generation, or even upscaling halfway through the generation.

I can't really imagine going back, unless there is some killer feature that Comfy is missing.

path: 0 825880 1233248, hotness: undefined, score: 1, children: 0
the_ramzay 2 points 3 years ago

Draw Things and InvokeAI on my MacBook Pro m1 pro

path: 0 776067, hotness: undefined, score: 2, children: 0
Xandar437 2 points 3 years ago

Automatic1111

path: 0 812996, hotness: undefined, score: 2, children: 0
red_dragon 2 points 3 years ago

SD.next (Vladmandic)

path: 0 760215, hotness: undefined, score: 2, children: 0
pennomi 1 point 3 years ago
path: 0 770477, hotness: undefined, score: 1, children: 0
IntheTreetop 1 point 3 years ago

I'm stuck with an AMD card for other purposes so I pretty much have to use the DirectML fork which is okay, but it's very slow and despite having 12gb of video ram, I still get the out of ram messages all the time. But, hopefully some progress will be made somewhat soon on those cards.

But it is fun, that's for sure.

path: 0 796434, hotness: undefined, score: 1, children: 0
danielbln 1 point 3 years ago

Auto1111 on RunDiffusion.

path: 0 800460, hotness: undefined, score: 1, children: 0
WildBanjos 1 point 3 years ago path: 0 903235, hotness: undefined, score: 1, children: 0
Ecker 1 point 3 years ago

I think Automatic is already great, but you should at least mention Easy Diffusion. Also very easy to use.

path: 0 940700, hotness: undefined, score: 1, children: 0
radialmonster 1 point 3 years ago

i used to use invoke ai,. invoke ai just realeased version 3 beta. i will wait for a few more betas or rc for 3 to use it again.
These days I usually use Makeayo

path: 0 961141, hotness: undefined, score: 1, children: 0
haakon 1 point 3 years ago

I use DiffusionBee on Mac. It’s simple and good enough for my needs

path: 0 740366, hotness: undefined, score: 1, children: 0
Dax87 -2 points 3 years ago

The porn industry is doomed!

Edit: well I think the title of this post changed or my comment ended up on the wrong post so my comment is irrelevant lol

path: 0 738584, hotness: undefined, score: -2, children: 7
2dollarsim 1 point 3 years ago

Not for videos, we are still quite a way from that yet.

path: 0 738584 754655, hotness: undefined, score: 1, children: 6
Dax87 2 points 3 years ago

yeah it was a joke. Doesn't look like it resonated well lol.

path: 0 738584 754655 758648, hotness: undefined, score: 2, children: 5
2dollarsim 1 point 3 years ago

Haha it won't be a joke next week when the new text-to-video model comes out

path: 0 738584 754655 758648 759368, hotness: undefined, score: 1, children: 4
pokexpert30 2 points 3 years ago

With how unstable (lol) txt2img is, I don't believe a stable enough for porn txt2video model is coming soon.

path: 0 738584 754655 758648 759368 764913, hotness: undefined, score: 2, children: 2
Dax87 1 point 3 years ago

👀

path: 0 738584 754655 758648 759368 760798, hotness: undefined, score: 1, children: 0
stable_diffusion
stable_diffusion

@lemmy.dbzer0.com

login for more options
5717
1469
89

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

go to feed...