Added base setup for training t2i adapters. Currently untested, saw something else shiny i wanted to finish sirst. Added content_or_style to the training config. It defaults to balanced, which is standard uniform time step sampling. If style or content is passed, it will use cubic sampling for timesteps to favor timesteps that are beneficial for training them. for style, favor later timesteps. For content, favor earlier timesteps.
This commit is contained in:
1 parent
17e4fe40d7
commit
27f343fc08
8 files changed
+314
-84
No files matched your search
+1
-1
@@ -1,7 +1,7 @@
|
||||
torch
|
||||
torchvision
|
||||
safetensors
|
||||
git+https://github.com/huggingface/diffusers.git
|
||||
diffusers==0.21.1
|
||||
transformers
|
||||
lycoris_lora
|
||||
flatten_json
|
||||
|
||||
Reference in new issue
Block a user