Age | Commit message (Collapse) | Author | Lines | |
---|---|---|---|---|
2023-11-05 | Merge branch 'dev' into master | AUTOMATIC1111 | -553/+1442 | |
2023-11-05 | compact prompt option disabled by default | AUTOMATIC1111 | -1/+1 | |
2023-11-05 | added compact prompt option | AUTOMATIC1111 | -168/+314 | |
2023-11-05 | Use devices.torch_gc() instead of empty_cache() | Ritesh Gangnani | -5/+1 | |
2023-11-05 | Added memory clearance after deletion | Ritesh Gangnani | -1/+5 | |
2023-11-05 | Add SSD-1B as a supported model | Ritesh Gangnani | -3/+21 | |
2023-11-05 | properly apply sort order for extra network cards when selected from dropdown | AUTOMATIC1111 | -13/+22 | |
allow selection of default sort order in settings remove 'Default' sort order, replace with 'Name' | ||||
2023-11-05 | eslint | AUTOMATIC1111 | -9/+11 | |
2023-11-05 | Merge pull request #13855 from gibiee/patch-1 | AUTOMATIC1111 | -1/+1 | |
Corrected a typo in `modules/cmd_args.py` | ||||
2023-11-05 | add a visible checkbox to input accordion | AUTOMATIC1111 | -25/+59 | |
2023-11-05 | correct a typo | gibiee | -1/+1 | |
modify "defaul" to "default" | ||||
2023-11-04 | Merge pull request #2 from v0xie/network-oft-change-impl | v0xie | -17/+27 | |
Use same updown implementation for LyCORIS OFT as kohya-ss OFT | ||||
2023-11-04 | refactor: remove unused function | v0xie | -47/+0 | |
2023-11-04 | refactor: use same updown for both kohya OFT and LyCORIS diag-oft | v0xie | -17/+74 | |
2023-11-03 | Merge pull request #1 from v0xie/oft-faster | v0xie | -17/+135 | |
Support LyCORIS diag-oft OFT implementation (minus MultiheadAttention layer), maintains support for kohya-ss OFT | ||||
2023-11-03 | refactor: move factorization to lyco_helpers, separate calc_updown for kohya ↵ | v0xie | -101/+77 | |
and kb | ||||
2023-11-03 | skip multihead attn for now | v0xie | -17/+37 | |
2023-11-03 | Merge pull request #13718 from avantcontra/bugfix_gfpgan_custom_path | AUTOMATIC1111 | -5/+20 | |
fix bug when using --gfpgan-models-path | ||||
2023-11-03 | Merge pull request #13733 from dben/patch-1 | AUTOMATIC1111 | -2/+15 | |
Update prompts_from_file script to allow concatenating entries with the general prompt. | ||||
2023-11-03 | Merge pull request #13762 from wkpark/nextjob | AUTOMATIC1111 | -2/+2 | |
call state.jobnext() before postproces*() | ||||
2023-11-03 | Merge pull request #13797 from Meerkov/master | AUTOMATIC1111 | -1/+1 | |
Fix #13796 | ||||
2023-11-03 | Merge pull request #13829 from AUTOMATIC1111/paren-fix | AUTOMATIC1111 | -1/+1 | |
Fix parenthesis auto selection | ||||
2023-11-03 | add changelog entry | AUTOMATIC1111 | -0/+5 | |
2023-11-03 | Merge pull request #13839 from AUTOMATIC1111/httpx==0.24.1 | AUTOMATIC1111 | -0/+1 | |
requirements_versions httpx==0.24.1 | ||||
2023-11-03 | Merge pull request #13839 from AUTOMATIC1111/httpx==0.24.1 | AUTOMATIC1111 | -0/+1 | |
requirements_versions httpx==0.24.1 | ||||
2023-11-04 | Update requirements_versions.txt | w-e-w | -0/+1 | |
2023-11-03 | Fix parenthesis auto selection | missionfloyd | -1/+1 | |
Fixes #13813 | ||||
2023-11-02 | added accordion settings options | Emily Zeng | -250/+254 | |
2023-11-02 | no idea what i'm doing, trying to support both type of OFT, kblueleaf ↵ | v0xie | -47/+145 | |
diag_oft has MultiheadAttn which kohya's doesn't?, attempt create new module based off network_lora.py, errors about tensor dim mismatch | ||||
2023-11-02 | detect diag_oft type | v0xie | -0/+7 | |
2023-11-01 | test implementation based on kohaku diag-oft implementation | v0xie | -21/+38 | |
2023-10-29 | Fix #13796 | Meerkov | -1/+1 | |
Fix comment error that makes understanding scheduling more confusing. | ||||
2023-10-25 | call state.jobnext() before postproces*() | Won-Kyu Park | -2/+2 | |
2023-10-23 | linting issue | David Benson | -1/+1 | |
2023-10-23 | Update prompts_from_file script to allow concatenating entries with the ↵ | David Benson | -2/+15 | |
general prompt. | ||||
2023-10-22 | style: conform style | v0xie | -1/+1 | |
2023-10-22 | fix: multiplier applied twice in finalize_updown | v0xie | -1/+22 | |
2023-10-22 | refactor: remove used OFT functions | v0xie | -72/+10 | |
2023-10-21 | fix: use merge_weight to cache value | v0xie | -17/+40 | |
2023-10-21 | style: cleanup oft | v0xie | -75/+7 | |
2023-10-21 | fix: support multiplier, no forward pass hook | v0xie | -10/+33 | |
2023-10-21 | fix: return orig weights during updown, merge weights before forward | v0xie | -21/+69 | |
2023-10-21 | refactor: use forward hook instead of custom forward | v0xie | -9/+24 | |
2023-10-22 | fix Blank line contains whitespace | avantcontra | -1/+1 | |
2023-10-22 | fix bug when using --gfpgan-models-path | avantcontra | -5/+20 | |
2023-10-21 | fix the situation with emphasis editing (aaaa:1.1) bbbb (cccc:1.1) | AUTOMATIC1111 | -0/+6 | |
2023-10-21 | rework some of changes for emphasis editing keys, force conversion of ↵ | AUTOMATIC1111 | -57/+47 | |
old-style emphasis | ||||
2023-10-19 | style: fix ambiguous variable name | v0xie | -2/+2 | |
2023-10-19 | style: formatting | v0xie | -37/+2 | |
2023-10-19 | refactor: fix constraint, re-use get_weight | v0xie | -24/+16 | |