[Stable Diffusion] Prompt Sharing and Learning Thread

[me3]

I find that strange because... yeah, A1111 is always pretty slow, and I don't know exactly what hardware you're running it in, but on my RTX 3060 with 8GB VRAM, which is okay but not amazing for SD, generating images with highres fix would take about 2 minutes to render, which a lot longer compared to what I get on ComfyUI (that's more in the 30 seconds range), but definitely not the 10-15 minutes range you're describing.

I know I must sound like a broken record, but you guys really should look into using ComfyUI. A1111 is just too poorly optimized to use comfortably with low-end hardware. Hell, even

You must be registered to see the links

would give you a better experience, even if a more limited one.

Ah the dream of having something that fast
Running a 1060 6gb, a 20 step 512x512 image takes about 15sec. Haven't really used Comfy in a while so i can't remember what its speed was for the same. I was mainly using it to test SDXL as it could actually run it unlike a1111 which still struggle with, which is really poor considering how long comfy has been able to. Haven't looked at SD.next in a while though, which is a fork of a1111, that is claimed to be an improvement in many things.

Not really a fan of the node setup in Comfy, i get the idea for it and the more options/control it provide, but unfamiliar things often end up suffering because you more easily fall back on what's familiar. What i REALLY don't like with comfy though is the way it generates random seed. Not sure if it's a workflow setup thing, but for me the random seed shown at the end of generation isn't what was used for the generation. It's the "next one", so you have to find the previous in some way as i've not seen a easy button for it.

I wasn't aware there was a substantial performance improvement - Sepheyer was too busy telling us how easy it is to use (if you enjoy gazing at plates of spaghetti!)

I'm experiencing a lot of issues with A1111 atm, including all kinds of errors on start-up. Also, generating an image takes about 3mins with 60 HiRes steps.

May well install it and have a go, when I get time.

Assuming those "errors" are the same as the ones i'm getting it's technically not errors, it's deprecation warnings. Which is something about a1111 that annoy me, they know those warnings are there, but instead of updating the code, ppl just get told to turn the warnings off...
They have to update the code eventually and it might actually get better too, but i guess it's why there's so many things that could be optimized as well.

 

[Sepheyer]

I wasn't aware there was a substantial performance improvement - Sepheyer was too busy telling us how easy it is to use (if you enjoy gazing at plates of spaghetti!)

I'm experiencing a lot of issues with A1111 atm, including all kinds of errors on start-up. Also, generating an image takes about 3mins with 60 HiRes steps.

May well install it and have a go, when I get time.

There are solid attempts to declutter the space in CUI. Just watch these pieces for 20 seconds each, even without sound, to get the feeling how the workspace with the new custom nodes differs from old approaches:

You must be registered to see the links

You must be registered to see the links

Clearly the community recognizes the clutter as an issue and attempts to find a solution for it.

Rando chick to reinforce the point:

 

[hkennereth]

Not really a fan of the node setup in Comfy, i get the idea for it and the more options/control it provide, but unfamiliar things often end up suffering because you more easily fall back on what's familiar.

I can surely understand that, and there is definitely a steeper learning curve to understand how it works at first, and sometimes trying some slightly different process may require spending some time messing around with your workflow instead of just pushing some buttons. I personally do find that rewarding because it allows you to better understand what is actually happening behind the scenes, which in turn allows you to better fine tune the process. But it's a fair concern.

What i REALLY don't like with comfy though is the way it generates random seed. Not sure if it's a workflow setup thing, but for me the random seed shown at the end of generation isn't what was used for the generation. It's the "next one", so you have to find the previous in some way as i've not seen a easy button for it.

THAT I am 100% behind, and I wish there was a way to change this behavior. Indeed the way Comfy handles seeds is that when you set it to change the value by either randomization or addition is to change the value AFTER you queue the image for generation, instead of BEFORE generating like on every other UI out there.

The only reason this doesn't bother me more is because... it's actually pretty trivial to find an image's seed and change settings for adjustments: if you drag any PNG generated with Comfy into its window, it will load the entire flow used to build it with all the original settings. So if I make a bunch of images and want to adjust one of them, I drag them back to Comfy from the file manager, change the seed generation values to Fixed where it's relevant, alter any settings I want, and make the image again.

 

[hkennereth]

I wasn't aware there was a substantial performance improvement - Sepheyer was too busy telling us how easy it is to use (if you enjoy gazing at plates of spaghetti!)

Oh yeah, it's A LOT faster. I was always a reluctant A1111 user because I always found it too unstable and its settings very confusing, so I would usually prefer to use EasyDiffusion when making simple images, but on both of those making standard 512 x 512 px images with SD1.5 models could take about 1 minute (at first, ED got a lot faster on later versions), without using any enhancements like highres fix. My average render time rendering the same basic 512px² image with ComfyUI is... let's check...

 

[Sepheyer]

I personally do find that rewarding because it allows you to better understand what is actually happening behind the scenes, which in turn allows you to better fine tune the process.

100%. Realizing that with SD you actually have a stream where you are moving latents thru transformers is priceless and I think an exclusively CUI experience:

Spoiler: Illustration

You don't have permission to view the spoiler content. Log in or register now.

 

[Jimwalrus]

I can surely understand that, and there is definitely a steeper learning curve to understand how it works at first, and sometimes trying some slightly different process may require spending some time messing around with your workflow instead of just pushing some buttons. I personally do find that rewarding because it allows you to better understand what is actually happening behind the scenes, which in turn allows you to better fine tune the process. But it's a fair concern.


THAT I am 100% behind, and I wish there was a way to change this behavior. Indeed the way Comfy handles seeds is that when you set it to change the value by either randomization or addition is to change the value AFTER you queue the image for generation, instead of BEFORE generating like on every other UI out there.

The only reason this doesn't bother me more is because... it's actually pretty trivial to find an image's seed and change settings for adjustments: if you drag any PNG generated with Comfy into its window, it will load the entire flow used to build it with all the original settings. So if I make a bunch of images and want to adjust one of them, I drag them back to Comfy from the file manager, change the seed generation values to Fixed where it's relevant, alter any settings I want, and make the image again.

I may well use some of yours or Sepheyer's to give me a grounding - I always hate starting from a blank sheet.

So, if my celeb flight attendants start looking a little more... ...'buxom', you know whose I've copied!

 

[Sepheyer]

I may well use some of yours or Sepheyer's to give me a grounding - I always hate starting from a blank sheet.

So, if my celeb flight attendants start looking a little more... ...'buxom', you know whose I've copied!

I just can't get enough of these. Literally as if I won a billion dollar jackpot and now can snort cocaine all day long without (finally!) being afraid of getting fired:

 

[hkennereth]

Here is that IPAdapter worklow. Purple are samplers that bash the latents together either which way. That's how you can realize you can have fifty of these lined up, each doing either promp, adding, subtracting, generally acting like Photoshop layers and you go - FML, now I get where this comes from. If y'all wanna try out the actual workflow - they are here:
View attachment 3017817

BTW, thanks for not making actual "spaghetti" flows that try too hard to create interfaces but you can't understand what's happening, and instead having clear and organized flows where you can see how things are connected and how data is passing through. THAT is what makes Comfy good to use!

 

[me3]

i don't know how much this affects, but having to upgrade comfyui i came across some dependency problems.
A simple install of "torch" installs version 2.1 for cuda 11.8, but it seems that xformers that gets installed along with it is for cuda 12.
Considering a1111, kohya_ss and comfy all use this it might be worth keeping in mind if planing to update.
When i updated xformers some days ago to, to some dev version of 0.0.23, it didn't have a cuda 12 dependency. Now it seems to be the case for most recent version of 0.0.22 and dev of 0.0.23

 

[hkennereth]

i don't know how much this affects, but having to upgrade comfyui i came across some dependency problems.
A simple install of "torch" installs version 2.1 for cuda 11.8, but it seems that xformers that gets installed along with it is for cuda 12.
Considering a1111, kohya_ss and comfy all use this it might be worth keeping in mind if planing to update.
When i updated xformers some days ago to, to some dev version of 0.0.23, it didn't have a cuda 12 dependency. Now it seems to be the case for most recent version of 0.0.22 and dev of 0.0.23

I just use the portable version of Comfy, so it doesn't depend on whatever version you have for other things at all.

 

[Sepheyer]

i don't know how much this affects, but having to upgrade comfyui i came across some dependency problems.
A simple install of "torch" installs version 2.1 for cuda 11.8, but it seems that xformers that gets installed along with it is for cuda 12.
Considering a1111, kohya_ss and comfy all use this it might be worth keeping in mind if planing to update.
When i updated xformers some days ago to, to some dev version of 0.0.23, it didn't have a cuda 12 dependency. Now it seems to be the case for most recent version of 0.0.22 and dev of 0.0.23

I second hkennereth. I originally had the "git clone" ComfyUI but along the way I messed up the torch/xformers and for the life of me couldn't undo it despite throwing two weeks of time at it and trying different combinations including these two bits:

Spoiler: More

You don't have permission to view the spoiler content. Log in or register now.

So, yea, do grab the portable version. It does have an inconvenience, when installing Face Restore or the Node Manager, need to make sure that you get appropriate versions of each, namely for the PE CUI.

 

[me3]

I just use the portable version of Comfy, so it doesn't depend on whatever version you have for other things at all.

this was when updating the portable version, using the update comfy and python. They all 3 are isolated in a similar way, so they won't affect eachother, but the dependency conflict still happens because it's between the version of torch that is default and default for xformers.

Multiple edits for correction:
For comfyui, check the update file to see if it links to cuda 118, if it does, fix the link or grab a new version of update files.
For kohya_ss, long as requirement files are intact it should work fine.
For A11111, xformers isn't a requirement any more so needs to be installed manually, and it doesn't seem to have a version restriction for torch. So if it uses a cuda118 version of torch, try xformers 0.0.21,

 

[Sepheyer]

this was when updating the portable version, using the update comfy and python. They all 3 are isolated in a similar way, so they won't affect eachother, but the dependency conflict still happens because it's between the version of torch that is default and default for xformers.

torch defaults to torch==2.1.0 cuda118
xformers defaults to versions that are compiled for cuda 12
so if you update xformers you need to manually update torch to 2.1.0 cuda120 or 2.1.0 cuda121

edit, their update bat isn't updating and it refers to cuda 11.8, so if you haven't updated the bat files in a while, that's there the version specific torch comes from

Why weren't you upfront that you had issues with the portable version to start with? You omitted a material fact making both of us waste time answering something that is completely irrelevant to the problem you have. The PV is meant to be a self-enclosed package preventing you from having the issues you are having. Good on you for showing how unique you are once more. The appropriate place for this type of question is the "issues" for the respective github repository.

Going forward it would be really cool if in your questions you present all relevant facts upfront saving everyone's time.

- Doctor my husband lost his head.
- Oh, ms. Jenkins, give him... [medical advise, suggests doctors, clinics, exams].
- His head is two feet away from his body.
- Why are you calling me? Call the police.

 

[me3]

Yes i should have said that specifically for comfy i had the portable version, but this is a problem for a1111 as well.
If you for some reason update xformers there, xformers is something you need to deal with manually for a1111, you'll get a version that's potentially at conflict with torch.
Also cuda 12 won't run on cuda 11 apperently

 

[devilkkw]

I wasn't aware there was a substantial performance improvement - Sepheyer was too busy telling us how easy it is to use (if you enjoy gazing at plates of spaghetti!)

I'm experiencing a lot of issues with A1111 atm, including all kinds of errors on start-up. Also, generating an image takes about 3mins with 60 HiRes steps.

May well install it and have a go, when I get time.

For a1111 the most important important thing is GPU driver.
Last good fast version is 532.03, after this version they added a push to ram way that slow generation.
Tested many time, on 532.03 i get 14 sec to made 896x1152 image.
on upper version i get around 2 min for image.
Also i'm fixed on a1111 1.5.2, because 1.6.0(actually last version) have different memory work for optimizing sdxl model, but with this new memory, i'm unable to load sd1.5 model over 6Gb, and get OOM error fast.
Tested with a clean install, nothing work good for me in v1.6.0.

I don't know your pc spec. but on my (rtx 3060 6Gb) better way is a1111 v1.5.2 and nvidia driver 532.03.

 

[Sepheyer]

Here's a test that convinced me that IPAdapter doesn't transfer likeness, and LORAs are still the way to go. I'll change my opinion when these will start resembling the original person.

Spoiler: The Original Person - don't click right away

You don't have permission to view the spoiler content. Log in or register now.

 

[Jimwalrus]

For a1111 the most important important thing is GPU driver.
Last good fast version is 532.03, after this version they added a push to ram way that slow generation.
Tested many time, on 532.03 i get 14 sec to made 896x1152 image.
on upper version i get around 2 min for image.
Also i'm fixed on a1111 1.5.2, because 1.6.0(actually last version) have different memory work for optimizing sdxl model, but with this new memory, i'm unable to load sd1.5 model over 6Gb, and get OOM error fast.
Tested with a clean install, nothing work good for me in v1.6.0.

I don't know your pc spec. but on my (rtx 3060 6Gb) better way is a1111 v1.5.2 and nvidia driver 532.03.

I've got an RTX3060 12GB, so I don't have to worry as much about it hitting the vRAM limit and failing over into system RAM (and yeah, that sure as hell slows it down!). Unfortunately A1111 is so poorly optimised that it's running a couple of GB in vRAM even when idling. I don't think it's the Checkpoint as even when I've loaded a 7GB one the vRAM shows as ~2GB.

 

[Sharinel]

I've got an RTX3060 12GB, so I don't have to worry as much about it hitting the vRAM limit and failing over into system RAM (and yeah, that sure as hell slows it down!). Unfortunately A1111 is so poorly optimised that it's running a couple of GB in vRAM even when idling. I don't think it's the Checkpoint as even when I've loaded a 7GB one the vRAM shows as ~2GB.

Have a play about with Miaoshou assistant, it can be set to release vram after every batch or even manually

You must be registered to see the links

 

[Sharinel]

I just can't get enough of these. Literally as if I won a billion dollar jackpot and now can snort cocaine all day long without (finally!) being afraid of getting fired:

View attachment 3017836

Here's why I don't like ComfyUI as much as 1111. I copied in your pic and got the following.



So it looks like I have the rest of the facerestore stuff, just not that one



I then use ComfyUI manager to try and install missing custom nodes.



There aint nothing to install.

Looking at the cmd prompt window :-



So I try to install/update that reactor node. Nothing.

So I'm stuck with a non-working workflow as one tiny piece isn't installed? Installed but not functioning? Not updating? I have no idea. And there's no instructions as to how to get it added. Tough luck mate, try again?

So back to Automatic1111 I go

 

[Sepheyer]

Here's why I don't like ComfyUI as much as 1111. I copied in your pic and got the following.

View attachment 3019500

So it looks like I have the rest of the facerestore stuff, just not that one

View attachment 3019501

I then use ComfyUI manager to try and install missing custom nodes.

View attachment 3019504

There aint nothing to install.

Looking at the cmd prompt window :-

View attachment 3019505

So I try to install/update that reactor node. Nothing.

So I'm stuck with a non-working workflow as one tiny piece isn't installed? Installed but not functioning? Not updating? I have no idea. And there's no instructions as to how to get it added. Tough luck mate, try again?

So back to Automatic1111 I go

Wait, wait, you are really close. You are mere ~15 minutes away from making it work.

Do you have the node manager installed? This:

You must be registered to see the links

. There are 3 installation options, pick the right one depending on your CUI install.

Or, if the Manager is glitching, then install face restore directly from here, but pick the right install option:

You must be registered to see the links

Should look like this (the dev changed module names when moving from 0.9 to 1.0):