aboutsummaryrefslogtreecommitdiffstats
path: root/modules/processing.py
Commit message (Collapse)AuthorAgeFilesLines
...
| * | | fix styles missing from the prompt in infotext when making a grid of batch ↵AUTOMATIC11112023-08-091-2/+7
| | | | | | | | | | | | | | | | of multiplie images
| * | | Merge pull request #12412 from dhwz/devAUTOMATIC11112023-08-081-1/+1
| |\ \ \ | | | | | | | | | | fix typo
| | * | | fix typodhwz2023-08-081-1/+1
| | | |/ | | |/|
* | | | fix webui not switching back to original model from refiner when batch count ↵AUTOMATIC11112023-08-081-0/+2
| | | | | | | | | | | | | | | | is greater than 1
* | | | Merge branch 'dev' into refinerAUTOMATIC11112023-08-081-3/+0
|\| | |
| * | | REMOVEAUTOMATIC11112023-08-081-3/+0
| |/ /
* | | add infotextAUTOMATIC11112023-08-061-0/+10
| | | | | | | | | | | | | | | add proper support for recalculating conds in k-diffusion samplers remove support for compvis samplers
* | | initial refiner supportAUTOMATIC11112023-08-061-0/+4
|/ /
* | enable cond cache by defaultAUTOMATIC11112023-08-061-13/+18
| |
* | fix rework saving incomplete imagesAUTOMATIC11112023-08-061-1/+1
| |
* | do the same for s_tmax #12345AUTOMATIC11112023-08-061-2/+2
| |
* | Merge branch 'dev' into fix/s-noiseAUTOMATIC11112023-08-061-9/+12
|\ \
| * | rework saving incomplete imagesAUTOMATIC11112023-08-061-9/+9
| | |
| * | Merge pull request #12338 from AUTOMATIC1111/dont-save-incomplete-imagesAUTOMATIC11112023-08-061-8/+11
| |\ \ | | | | | | | | don't save incomplete images
| | * | Option to not save incomplete imagesw-e-w2023-08-051-8/+11
| | | |
| * | | Attempt to read s_tmax from arg first if option not foundcatboxanon2023-08-061-1/+1
| | | |
| * | | Add s_tmaxcatboxanon2023-08-061-1/+1
| | | |
* | | | Correct s_noise fixcatboxanon2023-08-061-2/+2
| | | |
* | | | Allow s_noise override to actually be usedcatboxanon2023-08-061-1/+1
|/ / /
* / / do not add VAE Encoder/Decoder to infotext if it's the defaultAUTOMATIC11112023-08-051-3/+9
|/ /
* | Fix some merge mistakesKohaku-Blueleaf2023-08-051-1/+2
| |
* | Merge branch 'dev' into efficient-vae-methodsKohaku-Blueleaf2023-08-051-32/+66
|\ \
| * \ Merge pull request #12181 from AUTOMATIC1111/hires_checkpointAUTOMATIC11112023-08-051-31/+66
| |\ \ | | | | | | | | Hires fix change checkpoint
| | * | fix "clamp_scalar_cpu" not implemented for 'Half'AUTOMATIC11112023-07-311-1/+1
| | | |
| | * | repair AttributeError: 'NoneType' object has no attribute 'conditioning_key'AUTOMATIC11112023-07-311-7/+7
| | | |
| | * | set the field to None insteadAUTOMATIC11112023-07-311-2/+2
| | | |
| | * | delete the field that is preventing the model from being unloaded and is ↵AUTOMATIC11112023-07-301-0/+4
| | | | | | | | | | | | | | | | causing increased RAM usage
| | * | make it so that VAE NaNs autodetection also works during first pass of hires fixAUTOMATIC11112023-07-301-1/+1
| | | |
| | * | this time for sureAUTOMATIC11112023-07-301-3/+13
| | | |
| | * | make it possible to use checkpoints of different types (SD1, SDXL) in first ↵AUTOMATIC11112023-07-301-3/+7
| | | | | | | | | | | | | | | | and second pass of hires fix
| | * | repair non-latent upscaling broken for SDXLAUTOMATIC11112023-07-301-0/+1
| | | |
| | * | linterAUTOMATIC11112023-07-301-1/+1
| | | |
| | * | make it work with SDXLAUTOMATIC11112023-07-301-2/+5
| | | |
| | * | hires fix checkpoint selectionAUTOMATIC11112023-07-301-17/+30
| | |/
* | | add infotextKohaku-Blueleaf2023-08-051-0/+3
| | |
* | | replace get_first_stage_encodingKohaku-Blueleaf2023-08-041-7/+5
| | |
* | | Revert "change all encode"Kohaku-Blueleaf2023-08-041-6/+8
| | | | | | | | | | | | This reverts commit 094c416a801b16c7d8e1944e2e9fae2c9e98bf12.
* | | change all encodeKohaku-Blueleaf2023-08-041-8/+6
| | |
* | | Merge branch 'dev' into efficient-vae-methodsKohaku-Blueleaf2023-08-041-7/+1
|\| |
| * | resolve some of circular import issues for kohakuAUTOMATIC11112023-08-041-6/+1
| | |
* | | add TAESD for i2i and t2iKohaku-Blueleaf2023-08-041-7/+6
|/ /
* | add NV option for Random number generator source setting, which allows to ↵AUTOMATIC11112023-08-021-3/+3
| | | | | | | | generate same pictures on CPU/AMD/Mac as on NVidia videocards.
* | add yet another torch_gc to reclaim some of VRAM after the initial stage of ↵AUTOMATIC11112023-08-021-0/+1
|/ | | | img2img
* simplify PostprocessBatchListArgsAUTOMATIC11112023-07-261-12/+3
|
* attempt 2AUTOMATIC11112023-07-261-12/+16
|
* alternative solution for infotext issueAUTOMATIC11112023-07-261-35/+27
|
* simplifyljleb2023-07-241-3/+5
|
* use local varsljleb2023-07-241-6/+6
|
* add postprocess_batch_list callbackljleb2023-07-241-1/+23
|
* automatically switch to 32-bit float VAE if the generated picture has NaNs.AUTOMATIC11112023-07-191-5/+36
|