aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2022-11-26no-half support for SD 2.0MrCheeze
2022-11-26make SD2 compatible with --medvram settingAUTOMATIC
2022-11-27set TI AdamW default weight decay to 0flamelaw
2022-11-26restore hypernetworks to seemingly working stateAUTOMATIC
2022-11-26add 1024 module for hypernets for the new open clipAUTOMATIC
2022-11-26Add support Stable Diffusion 2.0AUTOMATIC
2022-11-25fixes #3449 - VRAM leak when switching to/from inpainting modelJay Smith
2022-11-25Merge branch 'AUTOMATIC1111:master' into draftxucj98
2022-11-24Fix other apisSena
2022-11-24Support NAI exif for PNG InfoNandaka
2022-11-23add filename santizationAlex "mcmonkey" Goodwin
Probably redundant, considering the model name *is* a filename, but I suppose better safe than sorry.
2022-11-23add model_name pattern for savingAlex "mcmonkey" Goodwin
2022-11-23last_layer_dropout default to Falseflamelaw
2022-11-23fix dropout, implement train/eval modeflamelaw
2022-11-23Fix bare base64 not acceptSena
2022-11-23small fixesflamelaw
2022-11-22safetensors optional for nowTim Patton
2022-11-22Update launch.pyuservar
2022-11-22Update requirements_versions.txtuservar
2022-11-22Update requirements.txtuservar
2022-11-22Add DPM++ SDE sampleruservar
2022-11-22Update k-diffusion to Release 0.0.11uservar
2022-11-22fix null negative_prompt on get requestsRogerooo
Small typo that causes a bug when returning negative prompts from the get request.
2022-11-21Use GPU for loading safetensors, disable exportTim Patton
2022-11-21Ignore safetensor filesTim Patton
2022-11-21Patch line ui endingsTim Patton
2022-11-21Supporting `*.safetensors` format.Nicolas Patry
If a model file exists with extension `.safetensors` then we can load it more safely than with PyTorch weights.
2022-11-21Change .cuda() to .to(devices.device)brkirch
2022-11-21Add fixes for PyTorch 1.12.1brkirch
Fix typo "MasOS" -> "macOS" If MPS is available and PyTorch is an earlier version than 1.13: * Monkey patch torch.Tensor.to to ensure all tensors sent to MPS are contiguous * Monkey patch torch.nn.functional.layer_norm to ensure input tensor is contiguous (required for this program to work with MPS on unmodified PyTorch 1.12.1)
2022-11-21remove cmd args requirement for deepdanboorudtlnor
2022-11-21fix pin_memory with different latent sampling methodflamelaw
2022-11-20made selected_gallery_index query selectors more restrictiveLiam
2022-11-20Generalize SD torch load/save to implement safetensor merging compatTim Patton
2022-11-20Move progress info to beginning of titleJonas Böer
because who has so few tabs open that they can see the end of a tab name?
2022-11-20Merge pull request #4120 from aliencaocao/enable-override-hypernetAUTOMATIC1111
Enable override_settings to take effect for hypernetworks
2022-11-20moved deepdanbooru to pure pytorch implementationAUTOMATIC
2022-11-20fix random sampling with pin_memoryflamelaw
2022-11-20remove unnecessary commentflamelaw
2022-11-20Gradient accumulation, autocast fix, new latent sampling method, etcflamelaw
2022-11-19Label and load SD .safetensors model filesTim Patton
2022-11-19Merge branch 'master' into cors-regexKeavon Chambers
2022-11-19revert change to webui-user.batAUTOMATIC
2022-11-19Add API for scripts to add elements anywhere in UI.AUTOMATIC
2022-11-19Merge pull request #4717 from papuSpartan/securityAUTOMATIC1111
Add --server-name to the list of arguments considered insecure
2022-11-19Merge pull request #4664 from piraka9011/fix-env-namesAUTOMATIC1111
Fix env var name typos
2022-11-19Merge pull request #4733 from MaikoTan/api-authorizationAUTOMATIC1111
feat: add http basic authentication for api
2022-11-19make it possible to change models etc by editing options using APIAUTOMATIC
2022-11-19Merge branch 'master' into api-authorizationMaiko Tan
2022-11-19Merge pull request #4358 from bamarillo/masterAUTOMATIC1111
[API][Feature] Add Skip endpoint
2022-11-19Minor fixesVladimir Repin
Remove unused test completely Change job name Don't use empty.pt as CLIP weights - it wont work. Use latest version of actions/cache