vladmandic / automatic

SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
https://github.com/vladmandic/automatic
GNU Affero General Public License v3.0
5.61k stars 411 forks source link

[Issue]: xyz script not working as expected #3180

Closed fraxyl closed 4 months ago

fraxyl commented 4 months ago

Issue Description

Since the latest update, x/y/z script no longer does it's thing. I filled it out exactly the same way as I did in previous versions, only when I hit generate, it generates one image over and over, seemingly only using the first prompt and not updating it when moving along to the next.

I am not sure if it's related to modern ui or not. Here's a test image where I only filled out the X section with a prompt s/r

image

Also first time creating an issue on git, if you require anything else please let me know.

Version Platform Description

No response

Relevant log output

02:33:22-431003 INFO     Starting SD.Next
02:33:22-438995 INFO     Logger: file="E:\automatic\sdnext.log" level=INFO size=9388387 mode=append
02:33:22-442995 INFO     Python 3.10.6 on Windows
02:33:22-699052 INFO     Version: app=sd.next updated=2024-05-29 hash=d19fc8c7 branch=master
                         url=https://github.com/vladmandic/automatic/tree/master
02:33:23-326205 INFO     Platform: arch=AMD64 cpu=AMD64 Family 23 Model 1 Stepping 1, AuthenticAMD system=Windows
                         release=Windows-10-10.0.19045-SP0 python=3.10.6

Backend

Diffusers

Branch

Master

Model

SD 1.5

Acknowledgements

vladmandic commented 4 months ago

i cannot reproduce, see screenshot below. image

can you post your screenshot so both prompt and xyz grid prompt s/r fields are visible?

vladmandic commented 4 months ago

ah, reproduced with modernui.

vladmandic commented 4 months ago

fixed.