aboutsummaryrefslogtreecommitdiffstats
path: root/modules/textual_inversion
AgeCommit message (Collapse)AuthorLines
2022-10-11Textual Inversion: Preprocess and Training will only pick-up image filesalg-wiki-3/+6
2022-10-10convert back to rgb as some hosts add alphaDepFA-1/+1
2022-10-10add pixel data footerDepFA-2/+46
2022-10-10Merge branch 'master' into embed-embeddings-in-imagesDepFA-14/+22
2022-10-10Custom Width and Heightalg-wiki-19/+18
2022-10-10Fixed progress bar output for epochalg-wiki-1/+1
2022-10-10Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki-8/+17
per input image in a single epoch
2022-10-10Custom Width and Heightalg-wiki-19/+18
2022-10-10Fixed progress bar output for epochalg-wiki-1/+1
2022-10-10Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki-8/+17
per input image in a single epoch
2022-10-09refactored the deepbooru module to improve speed on running multiple ↵JC_Array-2/+20
interogations in a row. Added the option to generate deepbooru tags for textual inversion preproccessing.
2022-10-10remove braces from stepsDepFA-1/+1
2022-10-10change caption methodDepFA-9/+21
2022-10-09change source of step countDepFA-8/+2
2022-10-09source checkpoint hash from current checkpointDepFA-4/+2
2022-10-09correct case on embeddingFromB64DepFA-1/+1
2022-10-09change json tensor key nameDepFA-3/+3
2022-10-09add encoder and decoder classesDepFA-0/+21
2022-10-09add alternate checkpoint hash sourceDepFA-2/+5
2022-10-09add embedding load and save from b64 jsonDepFA-9/+21
2022-10-09Update textual_inversion.pyDepFA-3/+22
2022-10-07hypernetwork training mk1AUTOMATIC-1/+0
2022-10-06removed unused import, fixed typoRaphael Stoeckli-2/+1
2022-10-06Add sanitizer for captions in Textual inversionRaphael Stoeckli-0/+28
2022-10-04add support for gelbooru tags in filenames for textual inversionAUTOMATIC-3/+8
2022-10-03fix broken date in TIAUTOMATIC-1/+1
2022-10-02keep textual inversion dataset latents in CPU memory to save a bit of VRAMAUTOMATIC-0/+5
2022-10-02preprocessing for textual inversion addedAUTOMATIC-3/+87
2022-10-02disabled SD model download after multiple complaintsAUTOMATIC-1/+1
2022-10-02add checkpoint info to saved embeddingsAUTOMATIC-1/+12
2022-10-02fix using aaaa-100 embedding when the prompt has aaaa-10000 and you have ↵AUTOMATIC-1/+2
both aaaa-100 and aaaa-10000 in the directory with embeddings.
2022-10-02fix for incorrect embedding token length calculation (will break seeds that ↵AUTOMATIC-10/+7
use embeddings, you're welcome!) add option to input initialization text for embeddings
2022-10-02initial support for training textual inversionAUTOMATIC-0/+366