aboutsummaryrefslogtreecommitdiffstats
path: root/modules/textual_inversion/dataset.py
AgeCommit message (Collapse)AuthorLines
2023-06-02Simplify a bunch of `len(x) > 0`/`len(x) == 0` style expressionsAarni Koskela-1/+1
2023-05-11Autofix Ruff W (not W605) (mostly whitespace)Aarni Koskela-2/+2
2023-05-09Fix up string formatting/concatenation to f-strings where feasibleAarni Koskela-1/+1
2023-02-19fix for #6700AUTOMATIC-1/+1
2023-02-15Add ability to choose using weighted loss or notShondoit-5/+10
2023-02-15Add PNG alpha channel as weight maps to data entriesShondoit-13/+38
2023-01-13print bucket sizes for training without resizing images #6620AUTOMATIC-0/+16
fix an error when generating a picture with embedding in it
2023-01-11Enable batch_size>1 for mixed-sized trainingdan-4/+32
2023-01-09remove/simplify some changes from #6481AUTOMATIC-9/+5
2023-01-08Move batchsize checkdan-2/+2
2023-01-08Add checkbox for variable training dimsdan-2/+2
2023-01-08Allow variable img sizedan-7/+11
2022-12-14Fix various typosJim Hays-5/+5
2022-11-30Use devices.autocast instead of torch.autocastbrkirch-2/+2
2022-11-27Merge pull request #4688 from parasi22/resolve-embedding-name-in-filewordsAUTOMATIC1111-1/+1
resolve [name] after resolving [filewords] in training
2022-11-21fix pin_memory with different latent sampling methodflamelaw-4/+19
2022-11-20fix random sampling with pin_memoryflamelaw-1/+1
2022-11-20remove unnecessary commentflamelaw-9/+0
2022-11-20Gradient accumulation, autocast fix, new latent sampling method, etcflamelaw-48/+86
2022-11-13resolve [name] after resolving [filewords] in trainingparasi-1/+1
2022-11-11Update dataset.pyKyuSeok Jung-1/+1
2022-11-11Update dataset.pyKyuSeok Jung-1/+1
2022-11-11adding tag drop out optionKyuSeok Jung-4/+4
2022-11-04change option position to Training settingTinkTheBoush-3/+2
2022-11-01append_tag_shuffleTinkTheBoush-2/+8
2022-10-29Additional assert on datasetMuhammad Rizqi Nur-0/+2
2022-10-28Fix random dataset shuffle on TIFlameLaw-2/+2
2022-10-21Allow datasets with only 1 image in TIguaneec-2/+2
2022-10-15Merge branch 'master' into masterAUTOMATIC1111-13/+20
2022-10-15add option to use batch size for trainingAUTOMATIC-12/+19
2022-10-14Raise an assertion error if no training images have been found.Melan-1/+2
2022-10-12train: change filename processing to be more simple and configurableAUTOMATIC-13/+34
train: make it possible to make text files with prompts train: rework scheduler so that there's less repeating code in textual inversion and hypernets train: move epochs setting to options
2022-10-11add an option to unload models during hypernetwork training to save VRAMAUTOMATIC-9/+20
2022-10-11Switched to exception handlingalg-wiki-5/+5
2022-10-11Added .webp .bmpalg-wiki-1/+1
2022-10-11Textual Inversion: Preprocess and Training will only pick-up image filesalg-wiki-1/+2
2022-10-10Custom Width and Heightalg-wiki-4/+3
2022-10-10Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki-3/+3
per input image in a single epoch
2022-10-04add support for gelbooru tags in filenames for textual inversionAUTOMATIC-2/+5
2022-10-02keep textual inversion dataset latents in CPU memory to save a bit of VRAMAUTOMATIC-0/+2
2022-10-02initial support for training textual inversionAUTOMATIC-0/+76
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-07 20:58:58 +0000