aboutsummaryrefslogtreecommitdiffstats
path: root/modules
AgeCommit message (Collapse)AuthorLines
2022-10-22fix part2Greendayle-1/+1
2022-10-22Deepdanbooru linux fixGreendayle-1/+2
2022-10-22typoAUTOMATIC-1/+1
2022-10-22added callback for creating new settings in extensionsAUTOMATIC-3/+33
2022-10-22small fixdiscus0434-4/+3
2022-10-22Merge branch 'AUTOMATIC1111:master' into masterdiscus0434-0/+14
2022-10-22small fixdiscus0434-8/+5
2022-10-22add an option to avoid dying reludiscus0434-6/+6
2022-10-22added a guard for hypernet training that will stop early if weights are ↵AUTOMATIC-0/+11
getting no gradients
2022-10-22fix for extensions without style.cssAUTOMATIC-0/+3
2022-10-22Merge branch 'master' of upstreamdiscus0434-354/+1360
2022-10-22add dropoutdiscus0434-51/+70
2022-10-22remove parsing command line from devices.pyAUTOMATIC-14/+9
2022-10-22Merge branch 'master' into cuda-device-id-selectionAUTOMATIC1111-552/+667
2022-10-22further support for extensionsAUTOMATIC-18/+45
2022-10-22removed aesthetic gradients as built-inAUTOMATIC-406/+244
added support for extensions
2022-10-22inspiration perfectedyfszzx-4/+5
2022-10-22inspiration perfectedyfszzx-2/+5
2022-10-22inspiration perfectedyfszzx-32/+39
2022-10-22implement CUDA device selection, --device-id argExtraltodeus-0/+1
2022-10-22implement CUDA device selection by IDExtraltodeus-3/+18
2022-10-22inspiration finishedyfszzx-67/+133
2022-10-21Merge remote-tracking branch 'historytab/master'AUTOMATIC-133/+383
2022-10-21prevent error spam when processing images without txt files for captionsAUTOMATIC-5/+4
2022-10-21Merge branch 'master' into fix/train-preprocess-keep-ratioAUTOMATIC1111-112/+976
2022-10-21loading SD VAE, see PR #3303AUTOMATIC-1/+4
2022-10-21make aspect ratio overlay work regardless of selected localizationAUTOMATIC-2/+2
2022-10-21Change option description of unload_models_when_trainingRcmcpe-1/+1
2022-10-21Remove unused variable.timntorres-1/+0
2022-10-21Refer to Hypernet's name, sensibly, by its name variable.timntorres-1/+1
2022-10-21Match hypernet name with filename in all cases.timntorres-1/+7
2022-10-21Sanitize hypernet name input.timntorres-0/+3
2022-10-21Update image_embedding.pyDepFA-2/+2
2022-10-21Use opts in textual_inversion image_embedding.py for dynamic fontsDepFA-0/+1
2022-10-21make aestetic embedding ciompatible with prompts longer than 75 tokensAUTOMATIC-1/+1
2022-10-21do not load aesthetic clip model until it's neededAUTOMATIC-38/+88
add refresh button for aesthetic embeddings add aesthetic params to images' infotext
2022-10-21Merge branch 'ae'AUTOMATIC-21/+324
2022-10-21Fix Hypernet infotext string split bug for PR #3283AUTOMATIC-1/+1
2022-10-21turns out LayerNorm also has weight and bias and needs to be pre-multiplied ↵AUTOMATIC-2/+2
and trained for hypernets
2022-10-21Merge branch 'master' into training-help-textAUTOMATIC1111-82/+552
2022-10-21Remove redundant try/except.timntorres-5/+1
2022-10-21Revise comments.timntorres-2/+2
2022-10-21Do nothing if image file already exists.timntorres-1/+5
2022-10-21Issue #2921-Give PNG info to Hypernet previews.timntorres-2/+7
2022-10-21Allow datasets with only 1 image in TIguaneec-2/+2
2022-10-21interrogate: Fix CLIP-interrogation on CPUPatryk Wychowaniec-3/+9
Currently, trying to perform CLIP interrogation on a CPU fails, saying: ``` RuntimeError: "slow_conv2d_cpu" not implemented for 'Half' ``` This merge request fixes this issue by detecting whether the target device is CPU and, if so, force-enabling `--no-half` and passing `device="cpu"` to `clip.load()` (which then does some extra tricks to ensure it works correctly on CPU).
2022-10-21Merge branch 'master' into masterAUTOMATIC1111-36/+493
2022-10-21a more strict check for activation type and a more reasonable check for type ↵AUTOMATIC-3/+9
of layer in hypernets
2022-10-21Merge pull request #3199 from discus0434/masterAUTOMATIC1111-11/+23
Add features to insert activation functions to hypernetworks
2022-10-21sort file list in alphabetical ordering in extraswinterspringsummer-1/+1
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-17 18:11:45 +0000