aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-12-14Merge pull request #14300 from AUTOMATIC1111/oft_fixesAUTOMATIC1111
Fix wrong implementation in network_oft
2023-12-14better naming and correct order for device.Kohaku-Blueleaf
2023-12-14remove debug printKohaku-Blueleaf
2023-12-14Use self.scale instead of custom finalizeKohaku-Blueleaf
2023-12-14Fix network_oftKohaku-Blueleaf
2023-12-13Allow pasting in WIDTHxHEIGHT strings into the width/height fieldsAarni Koskela
2023-12-12Update webui.shHina
2023-12-11Remove unnecessary 'else', add 'lightboxModal' checkkaalibro
2023-12-10Fix linter issueskaalibro
2023-12-10Replace Ctrl+Alt+Enter with Esckaalibro
2023-12-10Number of columns slider: max count set to 20, add description infokaalibro
2023-12-10fix styles.csv filenamew-e-w
2023-12-10fix save stylesw-e-w
2023-12-09Assign id for "extra_options". Replace numeric field with slider in Settings.kaalibro
2023-12-09Add keyboard shortcuts for generationkaalibro
(Removed Alt+Enter) Ctrl+Enter to start/restart generation (New) Alt/Option+Enter to skip generation (New) Ctrl+Alt/Option+Enter to interrupt generation
2023-12-09Re-add setting lost as part of e294e46kaalibro
2023-12-09Fix formatNuullll
2023-12-09Fix ControlNetNuullll
2023-12-08Formatted soft_inpainting.CodeHatchling
2023-12-08soft_inpainting now appears in the "inpaint" section, and will not activate ↵CodeHatchling
unless inpainting is activated.
2023-12-08#13354: solve lora loading issueRene Kroon
2023-12-07Fixed grammar error.CodeHatchling
2023-12-07Fixed complaint about whitespace, updated help section for a parameter.CodeHatchling
2023-12-07Added parameters for the composite stage, fixed batched generation.CodeHatchling
2023-12-07Fixed error that occurs when using vanilla samplers (somehow).CodeHatchling
2023-12-07Moved image filters used by soft inpainting into soft_inpainting.py from ↵CodeHatchling
images.py
2023-12-07Fixed "No newline at end of file".CodeHatchling
2023-12-07Re-implemented soft inpainting via a script. Also fixed some mistakes with ↵CodeHatchling
the previous hooks, removed unnecessary formatting changes, removed code that I had forgotten to.
2023-12-07Merge remote-tracking branch 'origin/release_candidate' into test-fp8Kohaku-Blueleaf
2023-12-06Removed soft inpainting, added hooks for softpainting to work instead.CodeHatchling
2023-12-06Removed changes in some scripts since the arguments for soft painting are no ↵CodeHatchling
longer passed through the same path as "mask_blur".
2023-12-06A custom blending function can be provided by p, replacing the use of ↵CodeHatchling
soft_inpainting.
2023-12-06add option: Live preview in full page image viewerw-e-w
make #13459 "show the preview image in the modal view if available" optional
2023-12-06[IPEX] Fix embeddingNuullll
Cast `torch.bmm` args into same `dtype`. Fixes the following error when using Text Inversion embedding (#14224): ``` RuntimeError: could not create a primitive descriptor for a matmul primitive ```
2023-12-06Merge branch 'dev' into kingljl-patch-memory-leakfuchen.ljl
2023-12-06Long distance memory overflow issuefuchen.ljl
Problem: The memory will slowly increase with the drawing until restarting. Observation: GC analysis shows that no occupation has occurred, so it is suspected to be a problem with the underlying allocator. Reason: Under Linux, glibc is used to allocate memory. glibc uses brk and mmap to allocate memory, and the memory allocated by brk cannot be released until the high-address memory is released. That is to say, if you apply for two pieces of memory A and B through brk, it is impossible to release A before B is released, and it is still occupied by the process. Check the suspected "memory leak" through TOP. So I replaced TCMalloc, but found that libtcmalloc_minimal could not find ptthread_Key_Create. After analysis, it was found that pthread was not entered during compilation.
2023-12-06Merge branch 'dev' into test-fp8Kohaku-Blueleaf
2023-12-06Fix forced reloadKohaku-Blueleaf
2023-12-05change state dict comparison to ref compareJabasukuriputo Wang
2023-12-05Merge pull request #14203 from AUTOMATIC1111/remove-clean_text()AUTOMATIC1111
remove clean_text()
2023-12-05Merge pull request #14203 from AUTOMATIC1111/remove-clean_text()AUTOMATIC1111
remove clean_text()
2023-12-04Merge remote-tracking branch 'origin2/dev' into soft-inpaintingCodeHatchling
# Conflicts: # modules/processing.py
2023-12-04Fixed unused import.CodeHatchling
2023-12-04Fixed issue where batched inpainting (batch size > 1) wouldn't work because ↵CodeHatchling
of mismatched tensor sizes. The 'already_decoded' decoded case should also be handled correctly (tested indirectly).
2023-12-04Applies a convert('RGBA') operation early to mimic previous behaviour.CodeHatchling
2023-12-04Restored original formatting.CodeHatchling
2023-12-04Re-introduce latent blending step from the vanilla inpainting procedure.CodeHatchling
2023-12-04Fixed issue with whitespace, removed commented out code that was meant to be ↵CodeHatchling
used as a reference.
2023-12-04Cleaned up code, moved main code contributions into soft_inpainting.pyCodeHatchling
2023-12-05remove clean_text()w-e-w