-
Notifications
You must be signed in to change notification settings - Fork 29
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
Comfy not doing anything when queueing #92
Comments
The recent ComfyUI update completely broke my Parameter Generator. I just updated it to fix the problem; please try the latest version. |
Sorry, no. Still same problem. Updated everything, click on queue prompt and nothing happens |
Am I really the only one with this issue? What am I doing wrong? |
After a system restart the missing fields popped up, but pretty much any image I put in reads out "The workflow is overly complex, or unsupported custom nodes have been used. Please see the README for more details. I'll read the readme. |
I don't know if this is why yours isn't working, but mine stops queuing when I set seed to be an input to the parameter generator (which you're also doing). If I let the parameter generator control the seed everything works fine. |
I updated everything, but it does not work... |
Hi, this worked for me, thank you! |
So over the last few days I've been using this awesome node to achieve something it probably wasn't intended to do: batch conversion. My potato GPU takes a lot of time to produce something reasonably nice so I use it to get me a ton of quick results with random orientation and very low sampling steps. Then I select the compositions I like and throw them in a folder. From there I fire up this batch reader, select the folder I created, keep the checkpoint/prompts/seed/width/height, add the loras I used for this particular subject, select the "nice" sampler settings and step counts, click on queue and wait for an hour for it to spit out the 20 images which then go up on CivitAI. So far so good.
However, sometimes the queue prompt button doesn't do anything at all and I can't figure out what I'm doing wrong. I click it and nothing happens. An error message would point me in the right direction, but neither the UI nor the console window do or show anything, not even the "got prompt". I've tried to manually load one image - nothing. Double and triple checked connections - nothing.
Unfortunately, I haven't been able to find an image on my drive where the workflow worked so I can't reproduce it. Help me Obi-Wan Kenobi. You're my only hope...
SDprompt.json
The text was updated successfully, but these errors were encountered: