[Stable Diffusion] Prompt Sharing and Learning Thread

[theMickey_]

I've loaded some workflows, but they always have nodes that I don't have, and there are usually no instructions on where to put the files.

The first thing you should install with ComfyUI is the

You must be registered to see the links

. It's used to install custom nodes without you having to download those nodes manually via github and then add them to your CimfyUI installation yourself.

Also: if a imported/downloaded workflow has red nodes, which means your installation is missing those nodes -- you can just use the ComfyUI-Manager to "Install Missing Custom Nodes".

 

[Synalon]

I'm just starting to learn to use ComfyUI. My main use will be animation. What are some good resources I could use to learn (or things to download)? I've loaded some workflows, but they always have nodes that I don't have, and there are usually no instructions on where to put the files.

Youtube is a great resource for Comfy tutorials.
Look for Sebastian Kamph and/or Olivio Sarikas to get started, and there are many more.

If you browse through the video lists for the 2 I mentioned they show some nodes for animation, and how to download and set them up etc.

 

[Nano999]

I deleted venv folder because my generation was slow to update SD, but when launched it saw this:

Do you know what's the matter?

Is it because of python?

 

[me3]

I deleted venv folder because my generation was slow to update SD, but when launched it saw this:
View attachment 3430059
Do you know what's the matter?

Is it because of python?
View attachment 3431286
View attachment 3431289
View attachment 3431290

it doesn't find a matching version for torch to install. It's specifically looking for version 2.1.2 that fits your system and it's not gonna find one.
Far as i can tell atm pytorch 2.1.2 only supports up to python 3.11, you're seemingly using 3.12
You can either manually created the venv from the 3.10 version you seem to have installed or you can use a later torch version that supports 3.12.
Version 2.2.0 and 2.2.1 should support that. You're gonna need a later version of torchvision as well to match torch

 

[Nano999]

No idea why I was needed 3.12, so I just reverted back to 3.10 and now it's downloading venv folder
I used this method because I don't know how to update torch/torchvision
Hope this fixes my again arised issue with generating images with slowspeed

 

[Nano999]

Oh well, the generation speed is a turtle, something wrong with the optimization
Deleing venv did not help
Any idea how to fix it?

All was working just fine like 3 weeks ago (30-60 sec at max for generating 1 pc)
And now it's slow as hell

 

[Nano999]

I kinda found the core why it's so slow now

When I eject any lora the speed becomes a turtle, but if I remove the lora the speed is super fast (30-60 sec) as it should be and as it was before with any lora (or no matter how many loras are there)

Ha? Why

Also some checkpoints are super slow now, even with no lora ejected -_-

15 minutes for 1 image is crazy

I don't know, maybe to delete all loras? And upload them again 1 by 1 or smth?

 

[me3]

I kinda found the core why it's so slow now

When I eject any lora the speed becomes a turtle, but if I remove the lora the speed is super fast (30-60 sec) as it should be and as it was before with any lora (or no matter how many loras are there)

Ha? Why

Also some checkpoints are super slow now, even with no lora ejected -_-

15 minutes for 1 image is crazy

I don't know, maybe to delete all loras? And upload them again 1 by 1 or smth?

loras can add A LOT, depending on what type it is and how many you use. Which sampler you use affect the time as well.
50 steps is generally too much though unless you're doing it for every specific reasons/conditions, you shouldn't need to use that many so you can save yourself some time there.
Why are you running with the skip cuda test option though, if there's some kind of issue with torch and cuda it could be why things are slower.
If this started after upgrading to 1.8 there could obviously be an issue with the update.

 

[LongJohn77]

I was able to play decently with Stable-Diffusion with an AMD RX 5700XT (about 2 - 3.2 it/s, 512*512), but on linux (Ubuntu 22.04 with torch 1.13.1+rocm5.2 for compatibility). The only problem is that every image generated the memory of the PC is filled more and more until the desktop stops responding, forcing a restart (I have 32GB).

Is there any option to free memory?

 

[Nano999]

loras can add A LOT, depending on what type it is and how many you use. Which sampler you use affect the time as well.
50 steps is generally too much though unless you're doing it for every specific reasons/conditions, you shouldn't need to use that many so you can save yourself some time there.
Why are you running with the skip cuda test option though, if there's some kind of issue with torch and cuda it could be why things are slower.
If this started after upgrading to 1.8 there could obviously be an issue with the update.

Ok, will then update torch and see how things go

 

[DreamingAway]

SDXL is starting to become usable..
Right in time for it to be abandoned for SD3.

(First generation, no control net, no img2img, no in-painting fixups, no TI's, no adetailer, no negative prompts)

 

[sharlotte]

SDXL does beautiful pictures but I have always found it difficult to generate beautiful nude bodies. Not so much with clothes on, whether on comfyUI, A1111 or forge. Bit it does generate beautiful pictures - here some where I 'borrowed' the prompt from a French forum, used in comfyUI (please note some of the steps in the flow are disconnected as not needed for 'non human" representations) :

 

[me3]

Do anyone have any experience or ideas for ways to make SD NOT replace the face and instead purely "improve"/detail the existing one?
While i wasn't exactly prompting for it, the face that showed up fit very well, problem is that with almost any detailing/denoising it starts being replaced with a far more human and "pretty" face. Even at just 0.1 denoising it's the first ting that gets replaced. Prompt, seed, etc is all the same through out and there's no "face restore/detailing" used.

 

[Synalon]

Do anyone have any experience or ideas for ways to make SD NOT replace the face and instead purely "improve"/detail the existing one?
While i wasn't exactly prompting for it, the face that showed up fit very well, problem is that with almost any detailing/denoising it starts being replaced with a far more human and "pretty" face. Even at just 0.1 denoising it's the first ting that gets replaced. Prompt, seed, etc is all the same through out and there's no "face restore/detailing" used.
View attachment 3442884

Maybe turn off restore face and use an extension that sharpens the image, that may be all you need.

 

[devilkkw]

Oh well, the generation speed is a turtle, something wrong with the optimization
Deleing venv did not help
Any idea how to fix it?

All was working just fine like 3 weeks ago (30-60 sec at max for generating 1 pc)
And now it's slow as hell

View attachment 3432030
View attachment 3432051
View attachment 3432054
View attachment 3432056
View attachment 3432069
View attachment 3432058

What's about driver version?
Read

You must be registered to see the links

for switch fallback function memory added in nvidia driver.

 

[hkennereth]

Do anyone have any experience or ideas for ways to make SD NOT replace the face and instead purely "improve"/detail the existing one?
While i wasn't exactly prompting for it, the face that showed up fit very well, problem is that with almost any detailing/denoising it starts being replaced with a far more human and "pretty" face. Even at just 0.1 denoising it's the first ting that gets replaced. Prompt, seed, etc is all the same through out and there's no "face restore/detailing" used.
View attachment 3442884

At 0.1 denoise the image should barely change at all, nevermind replace the face; if this was happening with an upscaler it wouldn't even look upscaled since the denoise is too low. I'd say that there's probably something else going on there, but with the amount of information provided I can't really hazard any guesses as to what.

 

[Mr-Fox]

I was able to play decently with Stable-Diffusion with an AMD RX 5700XT (about 2 - 3.2 it/s, 512*512), but on linux (Ubuntu 22.04 with torch 1.13.1+rocm5.2 for compatibility). The only problem is that every image generated the memory of the PC is filled more and more until the desktop stops responding, forcing a restart (I have 32GB).

Is there any option to free memory?

Which Ui are you using? I would recommend Forge. It has a better memory management than A1111, it will clear the memory as a part of the generation process, especially before upscaling.

You must be registered to see the links

Tutorial:

You must be registered to see the links

 

[LongJohn77]

Which Ui are you using? I would recommend Forge. It has a better memory management than A1111, it will clear the memory as a part of the generation process, especially before upscaling.

You must be registered to see the links

Tutorial:

You must be registered to see the links

Thanks for the advice, I had read about Forge a few days ago but I have not tried yet.

 

[g900vroot]

So I followed the instructions and installed A1111 per the instructions in the OP... thank you for that!

Generated a bunch of images, but nothing just was really coming together well, and then blammo. Wow, can I marry this one?



Per the rules, the prompts are attached in the image, drop it in your PNG Info for details.

Thanks for turning me onto this software. My poor 3060Ti is getting a workout now.

 

[Sharinel]

So I followed the instructions and installed A1111 per the instructions in the OP... thank you for that!

Generated a bunch of images, but nothing just was really coming together well, and then blammo. Wow, can I marry this one?

View attachment 3456705

Per the rules, the prompts are attached in the image, drop it in your PNG Info for details.

Thanks for turning me onto this software. My poor 3060Ti is getting a workout now.

Ouchy mama, that negative prompt. You're running an XL checkpoint so 99.9% of that stuff isn't needed - I would keep it at " EasyNegative,ng_deepnegative_v1_75t " and get rid of the rest of War and Peace you have in there. Here's my own version with no negative prompts, slightly tweaked prompt parts (no EE breasts, doesn't work. I substituted 'huge') and slightly different cfg scale/steps as I dont use the lightning variant of Juggernaut (same seed)



And the same seed/data using different checkpoints - Proteus v0.3, Dreamshaper8XL and Prony2.5

Spoiler

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