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
Copy file name to clipboardExpand all lines: CHANGELOG.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -13,12 +13,14 @@ and this project adheres to [Semantic Versioning 2.0](https://semver.org/spec/v2
13
13
- Added Prompt Amplifier to Inference - click the magic wand 🪄 in the prompt editor to expand and enrich your ideas. Tailor the vibe with the ‘Feel’ selector and watch as your generations come to life with extra detail, coherence, and flair!
14
14
### Changed
15
15
- Updated install for kohya_ss to support RTX 5000-series GPUs
16
+
- (pre.2 re-release) Merged Inference GGUF workflows into the UNet model loader option (no longer need to choose GGUF separately)
16
17
- Performance optimizations for Checkpoint Manager (progress indicators now fully uses Compiled Bindings)
17
18
### Fixed
18
19
- Fixed Inference ControlNet Preprocessors using incorrect resolution and increased maximum of smallest dimension to 16384
19
20
- Fixed Triton/Sage install option showing for incompatible GPUs
20
21
- Fixed errors from invalid pip specifiers in requirements files
21
22
- Fixed package images sometimes showing as blank due to concurrent image caching. Requests to same image resources are now de-duplicated
23
+
- (pre.2 re-release) Fixed Inference Extra Networks card not allowing for more than one model at a time
22
24
- Reduced memory usage from `ShowDisabledTooltipExtension`
0 commit comments