| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | style: conform style | v0xie | 2023-10-22 | 1 | -1/+1 |
| | | |||||
| * | fix: multiplier applied twice in finalize_updown | v0xie | 2023-10-22 | 1 | -1/+22 |
| | | |||||
| * | refactor: remove used OFT functions | v0xie | 2023-10-22 | 1 | -72/+10 |
| | | |||||
| * | fix: use merge_weight to cache value | v0xie | 2023-10-22 | 1 | -17/+40 |
| | | |||||
| * | style: cleanup oft | v0xie | 2023-10-21 | 1 | -75/+7 |
| | | |||||
| * | fix: support multiplier, no forward pass hook | v0xie | 2023-10-21 | 1 | -10/+33 |
| | | |||||
| * | fix: return orig weights during updown, merge weights before forward | v0xie | 2023-10-21 | 1 | -21/+69 |
| | | |||||
| * | refactor: use forward hook instead of custom forward | v0xie | 2023-10-21 | 1 | -9/+24 |
| | | |||||
| * | style: fix ambiguous variable name | v0xie | 2023-10-19 | 1 | -2/+2 |
| | | |||||
| * | style: formatting | v0xie | 2023-10-19 | 2 | -37/+2 |
| | | |||||
| * | refactor: fix constraint, re-use get_weight | v0xie | 2023-10-19 | 1 | -24/+16 |
| | | |||||
| * | faster by calculating R in updown and using cached R in forward | v0xie | 2023-10-18 | 1 | -7/+8 |
| | | |||||
| * | faster by using cached R in forward | v0xie | 2023-10-18 | 1 | -3/+14 |
| | | |||||
| * | inference working but SLOW | v0xie | 2023-10-18 | 2 | -40/+75 |
| | | |||||
| * | wip incorrect OFT implementation | v0xie | 2023-10-18 | 2 | -0/+87 |
| | | |||||
| * | Merge pull request #13568 from AUTOMATIC1111/lora_emb_bundle | AUTOMATIC1111 | 2023-10-14 | 3 | -0/+75 |
| |\ | | | | | Add lora-embedding bundle system | ||||
| | * | remove duplicated code | AUTOMATIC1111 | 2023-10-14 | 1 | -29/+2 |
| | | | |||||
| | * | Fix lint | Kohaku-Blueleaf | 2023-10-10 | 1 | -1/+1 |
| | | | |||||
| | * | Add warning when meet emb name conflicting | Kohaku-Blueleaf | 2023-10-10 | 2 | -32/+81 |
| | | | | | | | | | Choose standalone embedding (in /embeddings folder) first | ||||
| | * | Remove dev debug print | Kohaku-Blueleaf | 2023-10-10 | 1 | -1/+0 |
| | | | |||||
| | * | Support string_to_param nested dict | Kohaku-Blueleaf | 2023-10-10 | 1 | -1/+6 |
| | | | | | | | | | | | format: bundle_emb.EMBNAME.string_to_param.KEYNAME | ||||
| | * | add lora bundle system | Kohaku-Blueleaf | 2023-10-09 | 2 | -0/+49 |
| | | | |||||
| * | | support inference with LyCORIS GLora networks | v0xie | 2023-10-12 | 2 | -0/+35 |
| |/ | |||||
| * | fix: lora-bias-backup don't reset cache | dongwenpu | 2023-09-10 | 1 | -0/+1 |
| | | |||||
| * | feat: display file metadata ss_output_name | bluelovers | 2023-08-28 | 1 | -0/+1 |
| | | | | | https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/12289 | ||||
| * | RAM optimization round 2 | AUTOMATIC1111 | 2023-08-16 | 1 | -1/+4 |
| | | |||||
| * | lint | AUTOMATIC1111 | 2023-08-15 | 1 | -2/+1 |
| | | |||||
| * | Merge pull request #12584 from AUTOMATIC1111/full-module-with-bias | AUTOMATIC1111 | 2023-08-15 | 1 | -1/+6 |
| |\ | | | | | Add ex_bias into full module | ||||
| | * | full module with ex_bias | Kohaku-Blueleaf | 2023-08-15 | 1 | -1/+6 |
| | | | |||||
| * | | store patches for Lora in a specialized module | AUTOMATIC1111 | 2023-08-15 | 3 | -61/+54 |
| |/ | |||||
| * | remove "if bias exist" check | Kohaku-Blueleaf | 2023-08-14 | 1 | -1/+1 |
| | | |||||
| * | Merge branch 'dev' into extra-norm-module | Kohaku-Blueleaf | 2023-08-14 | 4 | -33/+55 |
| |\ | |||||
| | * | Merge pull request #12510 from catboxanon/feat/extnet/hashes | AUTOMATIC1111 | 2023-08-13 | 1 | -1/+2 |
| | |\ | | | | | | | Support search and display of hashes for all extra network items | ||||
| | | * | Support search and display of hashes for all extra network items | catboxanon | 2023-08-13 | 1 | -1/+2 |
| | | | | |||||
| | * | | linter | AUTOMATIC1111 | 2023-08-13 | 1 | -1/+1 |
| | | | | |||||
| | * | | Lora: output warnings in UI rather than fail for unfitting loras; switch to ↵ | AUTOMATIC1111 | 2023-08-13 | 3 | -29/+50 |
| | |/ | | | | | | | logging for error output in console | ||||
| * / | Fix MHA updown err and support ex-bias for no-bias layer | Kohaku-Blueleaf | 2023-08-14 | 1 | -8/+29 |
| |/ | |||||
| * | remove debug print | Kohaku-Blueleaf | 2023-08-12 | 1 | -1/+0 |
| | | |||||
| * | return None if no ex_bias | Kohaku-Blueleaf | 2023-08-12 | 2 | -4/+4 |
| | | |||||
| * | Add extra norm module into built-in lora ext | Kohaku-Blueleaf | 2023-08-12 | 4 | -11/+105 |
| | | | | | | | refer to LyCORIS 1.9.0.dev6 add new option and module for training norm layer (Which is reported to be good for style) | ||||
| * | Fix to make LoRA old method setting work | catboxanon | 2023-08-11 | 1 | -1/+1 |
| | | |||||
| * | Lora cache in memory | AUTOMATIC1111 | 2023-08-09 | 2 | -3/+22 |
| | | |||||
| * | gradio 3.39 | AUTOMATIC1111 | 2023-08-04 | 1 | -1/+1 |
| | | |||||
| * | update lora extension to work with python 3.8 | AUTOMATIC1111 | 2023-07-27 | 1 | -0/+1 |
| | | |||||
| * | fix for #11963 | AUTOMATIC1111 | 2023-07-25 | 1 | -1/+6 |
| | | |||||
| * | Fix to parse TE in some LoRAs | catboxanon | 2023-07-24 | 1 | -1/+1 |
| | | |||||
| * | fix incorrect multiplier for Loras | AUTOMATIC1111 | 2023-07-18 | 1 | -1/+1 |
| | | |||||
| * | add backwards compatibility --lyco-dir-backcompat option, use that for ↵ | AUTOMATIC1111 | 2023-07-18 | 3 | -4/+5 |
| | | | | | | | LyCORIS directory instead of hardcoded value prevent running preload.py for disabled extensions | ||||
| * | add a bit more metadata info for the lora user metadata page | AUTOMATIC1111 | 2023-07-18 | 1 | -0/+6 |
| | | |||||
| * | use "is not None" for Tensor | Kohaku-Blueleaf | 2023-07-18 | 1 | -2/+2 |
| | | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |