-
Notifications
You must be signed in to change notification settings - Fork 27.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Hanging on 100% issue #15744
Comments
I don't know what's causing issue but you got to realize 100% is not 100% the progress while we showing is only the sampling steps so if you "preemptively stops 1 step before the final" if it gets stuck afterwards like in VAE, it's still stuck I'm guessing the issue is during VAE your system doesn't have enough vram and start using system ram which causes massive slow down live preview works differently from normal image, (it essentially decodes the latent space using a different method by default using a cheaper method so it's quicker) if the issue is with VRAM usage during VAE pahse if the issue is it getting stuck during other post processing then more investigation needs to be done you should really fill in the issue report with the proper information we requested |
@w-e-w Updated Sysinfo |
as expected RTX 2060 with 6GB vram so I think it's highly likely it's caused by not enough VRAM it is possible in your situation |
@w-e-w I don't know if it's actually a vram issue. For a normal 50-90 second gen the vram will spike to 5.8~ on final and normal ram will bump up a bit. I just got a generation that took 8+ minutes but it also only spiked to 5.8 and bumped up normal ram a little, so there's no difference there besides the time it takes to finish. Between the 8 minute gen and the gen before it which took 54 seconds, the only difference was the seed and a slight change made to the prompt, the size and everything else was kept the same. I followed the instructions and turned CUDA - Sysmem Fallback Policy but it didn't do anything different when generating. I even tried making a couple images twice as large as I normally do, capped at vram 5.8 and uses a bunch of ram but no delay and no failure. |
Didn't have the same issue as the author of this post but enabling FP8 weight helped me when I had this error : |
I still have this issue but it doesn't show up as often as before |
What happened?
So the issue of the program getting stuck at 100% has been reported multiple times. In my case it seems to happen after changing the prompt, it'll run a hundred of the same prompt just fine but if I change it even slightly it'll have a chance to delay the final step for who knows how long (it took an hour once).
I only just started to use live preview (it existed before I did) and can see that every step before the final is done quickly,
so can I just change the code on my end so that it preemptively stops 1 step before the final and then save it as it would normally, skipping the 100% delay issue?
I'm not familiar with the project's code so I have no idea what would need changing to do this.
Steps to reproduce the problem
Generate
Change prompt.
Generate with a chance for delay.
What should have happened?
No delay at 100%. What is usually a minute per gen can take upwards of 10 minutes at times.
SysInfo
SysInfo
The text was updated successfully, but these errors were encountered: