aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2023-10-29Add assertions for checking additional settings freezing parametersNick Harrison
2023-10-29Add new arguments to known command promptsNick Harrison
2023-10-28Add MPS manual castKohakuBlueleaf
2023-10-28ManualCast for 10/16 series gpuKohaku-Blueleaf
2023-10-25call state.jobnext() before postproces*()Won-Kyu Park
2023-10-25change torch versionKohaku-Blueleaf
2023-10-25ignore mps for fp8Kohaku-Blueleaf
2023-10-25Fix alphas cumprodKohaku-Blueleaf
2023-10-25Fix alphas_cumprod dtypeKohaku-Blueleaf
2023-10-25fp8 for TEKohaku-Blueleaf
2023-10-24Fix lintKohaku-Blueleaf
2023-10-24Add CPU fp8 supportKohaku-Blueleaf
Since norm layer need fp32, I only convert the linear operation layer(conv2d/linear) And TE have some pytorch function not support bf16 amp in CPU. I add a condition to indicate if the autocast is for unet.
2023-10-23linting issueDavid Benson
2023-10-23Update prompts_from_file script to allow concatenating entries with the ↵David Benson
general prompt.
2023-10-22style: conform stylev0xie
2023-10-22fix: multiplier applied twice in finalize_updownv0xie
2023-10-22refactor: remove used OFT functionsv0xie
2023-10-21fix: use merge_weight to cache valuev0xie
2023-10-21style: cleanup oftv0xie
2023-10-21fix: support multiplier, no forward pass hookv0xie
2023-10-21fix: return orig weights during updown, merge weights before forwardv0xie
2023-10-21refactor: use forward hook instead of custom forwardv0xie
2023-10-22fix Blank line contains whitespaceavantcontra
2023-10-22fix bug when using --gfpgan-models-pathavantcontra
2023-10-21fix the situation with emphasis editing (aaaa:1.1) bbbb (cccc:1.1)AUTOMATIC1111
2023-10-21rework some of changes for emphasis editing keys, force conversion of ↵AUTOMATIC1111
old-style emphasis
2023-10-19style: fix ambiguous variable namev0xie
2023-10-19style: formattingv0xie
2023-10-19refactor: fix constraint, re-use get_weightv0xie
2023-10-19Add sdxl only argKohaku-Blueleaf
2023-10-19Add fp8 for sd unetKohaku-Blueleaf
2023-10-18faster by calculating R in updown and using cached R in forwardv0xie
2023-10-18faster by using cached R in forwardv0xie
2023-10-18inference working but SLOWv0xie
2023-10-17wip incorrect OFT implementationv0xie
2023-10-16feat: refactorAnthony Fu
2023-10-16Interrupt after current generationAnthony Fu
2023-10-15Merge pull request #13644 from XpucT/devAUTOMATIC1111
Start / Restart generation by Ctrl (Alt) + Enter
2023-10-15Add files via uploadKhachatur Avanesian
LF
2023-10-15Update script.jsKhachatur Avanesian
2023-10-15Update script.jsKhachatur Avanesian
LF instead CRLF
2023-10-15Update script.jsKhachatur Avanesian
Exclude lambda
2023-10-15respect keyedit_precision_attention setting when converting from old ↵AUTOMATIC1111
(((attention))) syntax
2023-10-15Merge pull request #13533 from missionfloyd/edit-attention-fixAUTOMATIC1111
Edit-attention fixes
2023-10-15repair unload sd checkpoint buttonAUTOMATIC1111
2023-10-15add an option to not print stack traces on ctrl+c.AUTOMATIC1111
2023-10-15Start / Restart generation by Ctrl (Alt) + EnterKhachatur Avanesian
Add ability to interrupt current generation and start generation again by Ctrl (Alt) + Enter
2023-10-14Merge pull request #13638 from wkpark/user-settings-2AUTOMATIC1111
webui.settings.bat support
2023-10-15support webui.settings.batWon-Kyu Park
2023-10-14Merge pull request #13568 from AUTOMATIC1111/lora_emb_bundleAUTOMATIC1111
Add lora-embedding bundle system
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-25 04:24:09 +0000