- 01 1月, 2023 15 次提交
-
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
change karras scheduler sigmas to values recommended by SD from old 0.1 to 10 with an option to revert to old
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
fix 'RuntimeError: Expected all tensors to be on the same device' error preventing models from loading on lowvram/medvram.
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
make save to zip into its own button instead of a checkbox
-
由 AUTOMATIC 提交于
make it so that memory/embeddings info is displayed in a separate UI element from generation parameters, and is preserved when you change the displayed infotext by clicking on gallery images
-
由 AUTOMATIC 提交于
changed embedding accepted shape detection to use existing code and support the new alt-diffusion model, and reformatted messages a bit #6149
-
由 AUTOMATIC1111 提交于
validate textual inversion embeddings
-
由 AUTOMATIC1111 提交于
fix interrogate
-
由 Vladimir Mandic 提交于
-
- 31 12月, 2022 13 次提交
-
-
由 AUTOMATIC 提交于
-
由 Vladimir Mandic 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC 提交于
set sd_model for API later, inside the lock, to prevent multiple requests with different models ending up with incorrect results #5877 #6012
-
由 AUTOMATIC1111 提交于
fix(api): only begin/end state in lock
-
由 AUTOMATIC1111 提交于
Add memory cache for VAE weights
-
由 AUTOMATIC1111 提交于
fix rgba to rgb when using jpeg output
-
由 AUTOMATIC1111 提交于
add additional memory states
-
由 AUTOMATIC1111 提交于
remove unnecessary console message
-
由 AUTOMATIC1111 提交于
fix shared state dictionary
-
由 Vladimir Mandic 提交于
-
由 Vladimir Mandic 提交于
-
由 Vladimir Mandic 提交于
-
- 26 12月, 2022 2 次提交
-
-
由 Vladimir Mandic 提交于
-
由 AUTOMATIC 提交于
-
- 25 12月, 2022 10 次提交
-
-
由 hitomi 提交于
-
由 Philpax 提交于
-
由 AUTOMATIC 提交于
-
由 AUTOMATIC1111 提交于
Add CSS classes for the settings panels
-
由 AUTOMATIC1111 提交于
Fix F541: f-string without any placeholders
-
由 AUTOMATIC1111 提交于
Fix clip interrogate from the webui
-
由 AUTOMATIC1111 提交于
implement train api
-
由 AUTOMATIC 提交于
-
由 Allen Benz 提交于
A recent change made the image RGBA, which makes the clip interrogator unhappy. deepbooru and calling the interrogator from the api already do the conversion so this is the only place that needed it.
-
由 eaglgenes101 提交于
-