Age | Commit message (Collapse) | Author | |
---|---|---|---|
2023-12-06 | Removed changes in some scripts since the arguments for soft painting are no ↵ | CodeHatchling | |
longer passed through the same path as "mask_blur". | |||
2023-12-06 | A custom blending function can be provided by p, replacing the use of ↵ | CodeHatchling | |
soft_inpainting. | |||
2023-12-06 | add option: Live preview in full page image viewer | w-e-w | |
make #13459 "show the preview image in the modal view if available" optional | |||
2023-12-06 | [IPEX] Fix embedding | Nuullll | |
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 ``` | |||
2023-12-06 | Merge branch 'dev' into test-fp8 | Kohaku-Blueleaf | |
2023-12-06 | Fix forced reload | Kohaku-Blueleaf | |
2023-12-05 | change state dict comparison to ref compare | Jabasukuriputo Wang | |
2023-12-05 | Merge pull request #14203 from AUTOMATIC1111/remove-clean_text() | AUTOMATIC1111 | |
remove clean_text() | |||
2023-12-04 | Merge remote-tracking branch 'origin2/dev' into soft-inpainting | CodeHatchling | |
# Conflicts: # modules/processing.py | |||
2023-12-04 | Fixed unused import. | CodeHatchling | |
2023-12-04 | Fixed 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). | |||
2023-12-04 | Applies a convert('RGBA') operation early to mimic previous behaviour. | CodeHatchling | |
2023-12-04 | Restored original formatting. | CodeHatchling | |
2023-12-04 | Re-introduce latent blending step from the vanilla inpainting procedure. | CodeHatchling | |
2023-12-04 | Fixed issue with whitespace, removed commented out code that was meant to be ↵ | CodeHatchling | |
used as a reference. | |||
2023-12-04 | Cleaned up code, moved main code contributions into soft_inpainting.py | CodeHatchling | |
2023-12-05 | remove clean_text() | w-e-w | |
2023-12-04 | repair old handler for postprocessing API in a way that doesn't break interface | AUTOMATIC1111 | |
2023-12-04 | repair old handler for postprocessing API in a way that doesn't break interface | AUTOMATIC1111 | |
2023-12-04 | repair old handler for postprocessing API | AUTOMATIC1111 | |
2023-12-04 | repair old handler for postprocessing API | AUTOMATIC1111 | |
2023-12-04 | Enables the original functionality to be toggled on and off. | CodeHatchling | |
2023-12-04 | Merge branch 'dev' into test-fp8 | Kohaku-Blueleaf | |
2023-12-04 | Organized the settings and UI of soft inpainting to allow for toggling the ↵ | CodeHatchling | |
feature, and centralizes default values to reduce the amount of copy-pasta. | |||
2023-12-04 | make webui not crash when running with --disable-all-extensions option | AUTOMATIC1111 | |
2023-12-04 | Merge pull request #14192 from illtellyoulater/patch-1 | AUTOMATIC1111 | |
Update launch_utils.py - fixes repetead package reinstalls | |||
2023-12-03 | Lint | missionfloyd | |
2023-12-04 | Update launch_utils.py to fix wrong dep. checks and reinstalls | illtellyoulater | |
Fixes failing dependency checks for extensions having a different package name and import name (for example ffmpeg-python / ffmpeg), which currently is causing the unneeded reinstall of packages at runtime. In fact with current code, the same string is used when installing a package and when checking for its presence, as you can see in the following example: > launch_utils.run_pip("install ffmpeg-python", "required package") [ Installing required package: "ffmpeg-python" ... ] [ Installed ] > launch_utils.is_installed("ffmpeg-python") False ... which would actually return true with: > launch_utils.is_installed("ffmpeg") True | |||
2023-12-03 | "Uncrop" the original denoised image for the composite step, fixing a ↵ | CodeHatchling | |
"ValueError: Images do not match" *shudder* | |||
2023-12-03 | Fixed a math mistake. | CodeHatchling | |
2023-12-03 | Merge pull request #14186 from akx/torchvision-basicsr-hack | AUTOMATIC1111 | |
Add import_hook hack to work around basicsr/torchvision incompatibility | |||
2023-12-03 | Add import_hook hack to work around basicsr incompatibility | Aarni Koskela | |
Fixes #13985 | |||
2023-12-03 | rework mask and mask_composite logic | w-e-w | |
2023-12-03 | Merge pull request #14177 from catboxanon/fix/mask-composite-save | AUTOMATIC1111 | |
Fix `save_samples` being checked early when saving masked composite | |||
2023-12-02 | Merge remote-tracking branch 'origin/dev' into soft-inpainting | CodeHatchling | |
# Conflicts: # modules/processing.py | |||
2023-12-02 | Rewrote latent_blend() to use in-place operations and to aggressively "del" ↵ | CodeHatchling | |
references with the intention of minimizing allocations and easing garbage collection. | |||
2023-12-02 | Blend masks are now produced afterward, based on an estimate of the visual ↵ | CodeHatchling | |
difference between the original and modified latent images. This should remove ghosting and clipping artifacts from masks, while preserving the details of largely unchanged content. | |||
2023-12-03 | Merge branch 'dev' into test-fp8 | Kohaku-Blueleaf | |
2023-12-02 | Added utility functions related to processing masks. | CodeHatchling | |
2023-12-02 | Re-add setting lost as part of e294e46 | catboxanon | |
2023-12-02 | fix variable | drhead | |
2023-12-02 | Create alphas_cumprod_original on full precision path | drhead | |
2023-12-02 | Revert 309a606c | drhead | |
2023-12-02 | Fix `save_samples` being checked early when saving masked composite | catboxanon | |
2023-12-02 | fix linting | drhead | |
2023-12-02 | ensure that original alpha bar always exists | drhead | |
2023-12-02 | alternate implementation for unet forward replacement that does not depend ↵ | AUTOMATIC1111 | |
on hijack being applied | |||
2023-12-02 | Merge pull request #14171 from Nuullll/ipex | AUTOMATIC1111 | |
Initial IPEX support for Intel Arc GPU | |||
2023-12-02 | potential fix for #14172 | AUTOMATIC1111 | |
2023-12-02 | remove Train/Preprocessing tab and put all its functionality into extras ↵ | AUTOMATIC1111 | |
batch images mode |