aboutsummaryrefslogtreecommitdiff
path: root/modules
AgeCommit message (Collapse)Author
2022-10-22Merge pull request #3414 from discus0434/masterAUTOMATIC1111
[Hypernetworks] Add a feature to use dropout / more activation functions
2022-10-22fix part2Greendayle
2022-10-22Deepdanbooru linux fixGreendayle
2022-10-22typoAUTOMATIC
2022-10-22added callback for creating new settings in extensionsAUTOMATIC
2022-10-22small fixdiscus0434
2022-10-22Merge branch 'AUTOMATIC1111:master' into masterdiscus0434
2022-10-22small fixdiscus0434
2022-10-22add an option to avoid dying reludiscus0434
2022-10-22added a guard for hypernet training that will stop early if weights are ↵AUTOMATIC
getting no gradients
2022-10-22fix for extensions without style.cssAUTOMATIC
2022-10-22Merge branch 'master' of upstreamdiscus0434
2022-10-22add dropoutdiscus0434
2022-10-22remove parsing command line from devices.pyAUTOMATIC
2022-10-22Merge branch 'master' into cuda-device-id-selectionAUTOMATIC1111
2022-10-22further support for extensionsAUTOMATIC
2022-10-22removed aesthetic gradients as built-inAUTOMATIC
added support for extensions
2022-10-22inspiration perfectedyfszzx
2022-10-22inspiration perfectedyfszzx
2022-10-22inspiration perfectedyfszzx
2022-10-22implement CUDA device selection, --device-id argExtraltodeus
2022-10-22implement CUDA device selection by IDExtraltodeus
2022-10-22inspiration finishedyfszzx
2022-10-21Merge remote-tracking branch 'historytab/master'AUTOMATIC
2022-10-21prevent error spam when processing images without txt files for captionsAUTOMATIC
2022-10-21Merge branch 'master' into fix/train-preprocess-keep-ratioAUTOMATIC1111
2022-10-21loading SD VAE, see PR #3303AUTOMATIC
2022-10-21make aspect ratio overlay work regardless of selected localizationAUTOMATIC
2022-10-21Change option description of unload_models_when_trainingRcmcpe
2022-10-21Remove unused variable.timntorres
2022-10-21Refer to Hypernet's name, sensibly, by its name variable.timntorres
2022-10-21Match hypernet name with filename in all cases.timntorres
2022-10-21Sanitize hypernet name input.timntorres
2022-10-21Update image_embedding.pyDepFA
2022-10-21Use opts in textual_inversion image_embedding.py for dynamic fontsDepFA
2022-10-21make aestetic embedding ciompatible with prompts longer than 75 tokensAUTOMATIC
2022-10-21do not load aesthetic clip model until it's neededAUTOMATIC
add refresh button for aesthetic embeddings add aesthetic params to images' infotext
2022-10-21Merge branch 'ae'AUTOMATIC
2022-10-21Fix Hypernet infotext string split bug for PR #3283AUTOMATIC
2022-10-21turns out LayerNorm also has weight and bias and needs to be pre-multiplied ↵AUTOMATIC
and trained for hypernets
2022-10-21Merge branch 'master' into training-help-textAUTOMATIC1111
2022-10-21Remove redundant try/except.timntorres
2022-10-21Revise comments.timntorres
2022-10-21Do nothing if image file already exists.timntorres
2022-10-21Issue #2921-Give PNG info to Hypernet previews.timntorres
2022-10-21Allow datasets with only 1 image in TIguaneec
2022-10-21interrogate: Fix CLIP-interrogation on CPUPatryk Wychowaniec
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
2022-10-21a more strict check for activation type and a more reasonable check for type ↵AUTOMATIC
of layer in hypernets
2022-10-21Merge pull request #3199 from discus0434/masterAUTOMATIC1111
Add features to insert activation functions to hypernetworks
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-20 17:37:01 +0000