aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* amend the error in previous commitAUTOMATIC2023-01-301-1/+1
|
* make linux launch.py use XFORMERS_PACKAGE var too; thanks, acncaguaAUTOMATIC2023-01-301-1/+1
|
* Add --skip-version-check to disable messages asking users to upgrade torch.AUTOMATIC2023-01-302-1/+11
|
* disable EMA weights for instructpix2pix model, whcih should get memory usage ↵AUTOMATIC2023-01-301-2/+1
| | | | as well as image quality to what it was before d2ac95fa7b2a8d0bcc5361ee16dba9cbb81ff8b2
* make the program read Discard penultimate sigma from generation parametersAUTOMATIC2023-01-301-0/+1
|
* make the program read Eta and Eta DDIM from generation parametersAUTOMATIC2023-01-304-5/+9
|
* split samplers into one more files for k-diffusionAUTOMATIC2023-01-304-348/+22
|
* Split history sd_samplers.py to sd_samplers_kdiffusion.pyAndrey2023-01-301-0/+0
|
* Split history sd_samplers.py to sd_samplers_kdiffusion.pyAndrey2023-01-301-0/+339
|\
| * Split history sd_samplers.py to sd_samplers_kdiffusion.pyAndrey2023-01-301-0/+0
| |
* | Split history sd_samplers.py to sd_samplers_kdiffusion.pyAndrey2023-01-301-0/+0
|/
* split compvis sampler and shared sampler stuff into their own filesAUTOMATIC2023-01-303-1117/+28
|
* Split history sd_samplers.py to sd_samplers_common.pyAndrey2023-01-301-0/+0
|
* Split history sd_samplers.py to sd_samplers_common.pyAndrey2023-01-301-0/+552
|\
| * Split history sd_samplers.py to sd_samplers_common.pyAndrey2023-01-301-0/+0
| |
* | Split history sd_samplers.py to sd_samplers_common.pyAndrey2023-01-301-0/+0
|/
* Split history sd_samplers.py to sd_samplers_compvis.pyAndrey2023-01-301-0/+0
|
* Split history sd_samplers.py to sd_samplers_compvis.pyAndrey2023-01-301-0/+552
|\
| * Split history sd_samplers.py to sd_samplers_compvis.pyAndrey2023-01-301-0/+0
| |
* | Split history sd_samplers.py to sd_samplers_compvis.pyAndrey2023-01-301-0/+0
|/
* add an environment variable for selecting xformers packageAUTOMATIC2023-01-301-1/+2
|
* add override settings component to img2imgAUTOMATIC2023-01-292-3/+8
|
* make it possible to search checkpoint by its hashAUTOMATIC2023-01-291-1/+2
|
* update prompt token counts after using the paste params buttonAUTOMATIC2023-01-292-11/+31
|
* change disable_weights_auto_swap to true by defaultAUTOMATIC2023-01-291-1/+1
|
* make it so that setting options in pasted infotext (like Clip Skip and ENSD) ↵AUTOMATIC2023-01-295-80/+210
| | | | do not get applied directly and instead are added as temporary overrides
* remove Batch size and Batch pos from textinfo (goodbye)AUTOMATIC2023-01-291-2/+0
|
* do not display the message for TI unless the list of loaded embeddings changedAUTOMATIC2023-01-291-3/+7
|
* add buttons for auto-search in subdirectories for extra tabsAUTOMATIC2023-01-293-1/+41
|
* Merge pull request #7353 from EllangoK/preview-fixAUTOMATIC11112023-01-291-1/+1
|\ | | | | Fixes thumbnail cards not loading the preview image
| * only returns ckpt directories if they are not noneEllangoK2023-01-291-1/+1
| |
* | support for searching subdirectory names for extra networksAUTOMATIC2023-01-298-4/+20
| |
* | Merge pull request #7344 from glop102/masterAUTOMATIC11112023-01-291-0/+2
|\ \ | |/ |/| Reduce grid rows if larger than number of images available
| * Reduce grid rows if larger than number of images availableglop1022023-01-291-0/+2
|/ | | | | | | | When a set number of grid rows is specified in settings, then it leads to situations where an entire row in the grid is empty. The most noticable example is the processing preview when the row count is set to 2, where it shows the preview just fine but with a black rectangle under it.
* make it so that clicking on hypernet/lora card one more time removes the ↵AUTOMATIC2023-01-281-1/+30
| | | | related from the prompt
* add checkpoints tab for extra networks UIAUTOMATIC2023-01-288-8/+94
|
* Merge pull request #7231 from EllangoK/masterAUTOMATIC11112023-01-283-2/+26
|\ | | | | Fixes X/Y/Z Plot parameters not being restored from images
| * uses autos new regex, checks len of re_paramEllangoK2023-01-281-2/+2
| |
| * adds components to infotext_fieldsEllangoK2023-01-262-0/+24
| | | | | | | | allows for loading script params
| * re_param captures quotes with commas properlyEllangoK2023-01-261-3/+3
| | | | | | | | and removes unnecessary regex
* | Merge pull request #7309 from brkirch/fix-embeddingsAUTOMATIC11112023-01-286-14/+26
|\ \ | | | | | | Fix embeddings, upscalers, and refactor `--upcast-sampling`
| * | Remove MPS fix no longer needed for PyTorchbrkirch2023-01-281-3/+0
| | | | | | | | | | | | The torch.narrow fix was required for nightly PyTorch builds for a while to prevent a hard crash, but newer nightly builds don't have this issue.
| * | Add --no-half-vae to default macOS argumentsbrkirch2023-01-281-1/+1
| | | | | | | | | | | | Apparently the version of PyTorch macOS users are currently at doesn't always handle half precision VAEs correctly. We will probably want to update the default PyTorch version to 2.0 when it comes out which should fix that, and at this point nightly builds of PyTorch 2.0 are going to be recommended for most Mac users. Unfortunately someone has already reported that their M2 Mac doesn't work with the nightly PyTorch 2.0 build currently, so we can add --no-half-vae for now and give users that can install nightly PyTorch 2.0 builds a webui-user.sh configuration that overrides the default.
| * | Refactor conditional casting, fix upscalersbrkirch2023-01-285-10/+25
| | |
| * | Fix embeddings dtype mismatchbrkirch2023-01-261-1/+1
| | |
* | | Merge pull request #7258 from ItsOlegDm/masterAUTOMATIC11112023-01-281-6/+34
|\ \ \ | | | | | | | | Css fixes
| * | | Train tab fixItsOlegDm2023-01-281-1/+0
| | | |
| * | | img2img styled padding fixItsOlegDm2023-01-281-3/+2
| | | |
| * | | Removed buttons centeringItsOlegDm2023-01-281-1/+0
| | | |
| * | | css fixesItsOlegDm2023-01-261-7/+38
| | | |
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-03 05:40:03 +0000