You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, thank you for developing this great repo. I am trying to use this repo to finetune sdxl in full mode for inpainting. The input includes depth, partial image and mask. Instead of using ControlNet, I modify the first layer of unet to take in the conditions as input.
I have created a dataset for this task. I am wondering if current data backend supports loading multiple image conditions as input. If not, could you please give some hints on where to modify the code? thanks!
This discussion was converted from issue #1249 on December 28, 2024 13:46.
Heading
Bold
Italic
Quote
Code
Link
Numbered list
Unordered list
Task list
Attach files
Mention
Reference
Menu
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi, thank you for developing this great repo. I am trying to use this repo to finetune sdxl in full mode for inpainting. The input includes depth, partial image and mask. Instead of using ControlNet, I modify the first layer of unet to take in the conditions as input.
I have created a dataset for this task. I am wondering if current data backend supports loading multiple image conditions as input. If not, could you please give some hints on where to modify the code? thanks!
Best,
L
Beta Was this translation helpful? Give feedback.
All reactions