- Mar 3, 2019
- 226
- 732
- Dec 21, 2020
- 1,523
- 3,588
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:
You don't have permission to view the spoiler content.
Log in or register now.
- Dec 31, 2016
- 316
- 708
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,
Last edited:
- Dec 21, 2020
- 1,523
- 3,588
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.
- Dec 31, 2016
- 316
- 708
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
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
- Mar 17, 2021
- 282
- 963
For a1111 the most important important thing is GPU driver.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.
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.
- Dec 21, 2020
- 1,523
- 3,588
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.
You don't have permission to view the spoiler content.
Log in or register now.
- Sep 15, 2021
- 827
- 3,121
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.
- Dec 23, 2018
- 474
- 1,961
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
- Dec 23, 2018
- 474
- 1,961
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
- Dec 21, 2020
- 1,523
- 3,588
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):
Last edited:
- Mar 24, 2019
- 960
- 3,196
You need strong GPU with at least 4, but preferable 8 GB+ VRAM. GTX 1060 6 GB is kinda minimum, I think.
- Dec 27, 2022
- 6
- 0
Would it still be possible for me to do stable diffusion? If not is there any great alternatives?
- Mar 3, 2019
- 226
- 732
There are a ton of online solutions for generating images with Stable Diffusion, where you can get started with the tech without needing any hardware of your own besides a browser. Some are free, some are paid, some are more limited than others, but if you're just getting started most of these should be good enough to learn the ropes:
You must be registered to see the links
You must be registered to see the links
You must be registered to see the links
You must be registered to see the links
You must be registered to see the links
You must be registered to see the links
- Jan 10, 2019
- 260
- 1,371
Has anyone tried it yet or even seen this in the past few days?
Claims that speeds up to 2x the generation speed with automatic1111:
Going to try this today and see if that helps.
Note of caution however from github:
When you install, install from URL using the above link to github. Once done, restart webui and then go to new tab and follow the steps.
More info is available here on the install:
Here on how to use with SDXL:
NB: a word of caution, i'm getting CUDA issues probably due to last version of CUDA not installed. Still installing and will edit/update the steps here as I do so. was not CUDA at all, see below workaround.
NB2: At the moment, install is not completing even with newest CUDA installed. Will persevere ... and then report here
NB3: quite a few bugs on the github page. I'd say wait a few days before trying to install unless you are feeling adventurous. Which i'm ... Boldly going on, as Captain Picard would, with the install
There appears to be quite a few users getting errors when trying to install (I was one). Solution that worked for me is detailed in one of the bugs in the github:
You must be registered to see the links
Claims that speeds up to 2x the generation speed with automatic1111:
You must be registered to see the links
Going to try this today and see if that helps.
Note of caution however from github:
When you install, install from URL using the above link to github. Once done, restart webui and then go to new tab and follow the steps.
More info is available here on the install:
You must be registered to see the links
Here on how to use with SDXL:
You must be registered to see the links
(not super helpful unless you want to join the patreon of the guy for x$ a month....) - Trying to find out how to do it another way - from the video, it sounds like this RT is not fully incorporated yet hence only 1.5 is supported in the main branch of automatic1111.NB3: quite a few bugs on the github page. I'd say wait a few days before trying to install unless you are feeling adventurous. Which i'm ... Boldly going on, as Captain Picard would, with the install
There appears to be quite a few users getting errors when trying to install (I was one). Solution that worked for me is detailed in one of the bugs in the github:
Last edited:
- Jan 10, 2019
- 260
- 1,371
Alright, so after a few hours, I still can't get SDXL on it so i guess i'll wait a bit. It does not support comfyUI at the moment. Also seems not to support controlnet and hires. So for the lovers of curvy beauties here, far from ideal.
It does go really much faster on SD1.5 but then the current limitations are probably not worthy (at least for me).
It does go really much faster on SD1.5 but then the current limitations are probably not worthy (at least for me).
- Jan 10, 2019
- 260
- 1,371
SO did I learn a thing or two today? Sure did teach!
- Dec 27, 2022
- 6
- 0
Browser AI image generation is a little limited, but is there an alternative to Stable Diffusion, that I can download and use offline? And what happens if I force my potato PC to operate Stable Diffusion?
- Dec 21, 2020
- 1,523
- 3,588
Welp, just do it and see what happens. I think the most optimized UI for desktop is ComfyUI. The "readme" says:
Works even if you don't have a GPU with: --cpu (slow)
So give it a try:
You must be registered to see the links
Just make sure to add that "--cpu" to the launch command.