aboutsummaryrefslogtreecommitdiffstats
path: root/modules/textual_inversion/textual_inversion.py
Commit message (Collapse)AuthorAgeFilesLines
...
| * formattingDepFA2022-10-121-11/+11
| |
| * spacingDepFA2022-10-111-1/+1
| |
| * update importsDepFA2022-10-111-0/+3
| |
| * correct conflict resolution typoDepFA2022-10-111-1/+1
| |
| * shift embedding logic out of textual_inversionDepFA2022-10-111-119/+6
| |
| * Merge branch 'master' into embed-embeddings-in-imagesDepFA2022-10-111-5/+8
| |\
| * | use simple lcg in xorDepFA2022-10-111-2/+8
| | |
| * | colour depth conversion fixDepFA2022-10-101-1/+1
| | |
| * | add dependencyDepFA2022-10-101-1/+1
| | |
| * | update data dis[play styleDepFA2022-10-101-23/+65
| | |
| * | convert back to rgb as some hosts add alphaDepFA2022-10-101-1/+1
| | |
| * | add pixel data footerDepFA2022-10-101-2/+46
| | |
| * | Merge branch 'master' into embed-embeddings-in-imagesDepFA2022-10-101-3/+11
| |\ \
| * | | remove braces from stepsDepFA2022-10-091-1/+1
| | | |
| * | | change caption methodDepFA2022-10-091-9/+21
| | | |
| * | | change source of step countDepFA2022-10-091-8/+2
| | | |
| * | | source checkpoint hash from current checkpointDepFA2022-10-091-4/+2
| | | |
| * | | correct case on embeddingFromB64DepFA2022-10-091-1/+1
| | | |
| * | | change json tensor key nameDepFA2022-10-091-3/+3
| | | |
| * | | add encoder and decoder classesDepFA2022-10-091-0/+21
| | | |
| * | | add alternate checkpoint hash sourceDepFA2022-10-091-2/+5
| | | |
| * | | add embedding load and save from b64 jsonDepFA2022-10-091-9/+21
| | | |
| * | | Update textual_inversion.pyDepFA2022-10-091-3/+22
| | | |
* | | | apply lr schedule to hypernetsAUTOMATIC2022-10-111-40/+4
| | | |
* | | | Merge branch 'learning_rate-scheduling' into learnscheduleAUTOMATIC11112022-10-111-9/+11
|\ \ \ \
| * | | | add an option to unload models during hypernetwork training to save VRAMAUTOMATIC2022-10-111-1/+1
| | | | |
| * | | | Merge pull request #2201 from alg-wiki/textual__inversionAUTOMATIC11112022-10-111-6/+3
| |\ \ \ \ | | |_|_|/ | |/| | | Textual Inversion: Preprocess and Training will only pick-up image files instead
| | * | | Removed my local edits to checkpoint image generationalg-wiki2022-10-111-5/+2
| | | | |
| | * | | Switched to exception handlingalg-wiki2022-10-111-10/+8
| | | | |
| | * | | Added .webp .bmpalg-wiki2022-10-101-1/+1
| | | | |
| | * | | Merge branch 'master' into textual__inversionalg-wiki2022-10-101-0/+1
| | |\ \ \ | | | | |/ | | | |/|
| | * | | Textual Inversion: Preprocess and Training will only pick-up image filesalg-wiki2022-10-101-1/+2
| | | | |
| | * | | Custom Width and Heightalg-wiki2022-10-101-6/+5
| | | | |
| | * | | Fixed progress bar output for epochalg-wiki2022-10-101-1/+1
| | | | |
| | * | | Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki2022-10-101-3/+12
| | | |/ | | |/| | | | | | | | | per input image in a single epoch
| * | | fixes related to mergeAUTOMATIC2022-10-111-5/+7
| | |/ | |/|
* / | Refactored learning rate codeFampai2022-10-101-4/+47
|/ /
* | Custom Width and Heightalg-wiki2022-10-101-6/+5
| |
* | Fixed progress bar output for epochalg-wiki2022-10-101-1/+1
| |
* | Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki2022-10-101-3/+12
|/ | | | per input image in a single epoch
* fix broken date in TIAUTOMATIC2022-10-031-1/+1
|
* keep textual inversion dataset latents in CPU memory to save a bit of VRAMAUTOMATIC2022-10-021-0/+3
|
* preprocessing for textual inversion addedAUTOMATIC2022-10-021-0/+1
|
* add checkpoint info to saved embeddingsAUTOMATIC2022-10-021-1/+12
|
* fix using aaaa-100 embedding when the prompt has aaaa-10000 and you have ↵AUTOMATIC2022-10-021-1/+2
| | | | both aaaa-100 and aaaa-10000 in the directory with embeddings.
* fix for incorrect embedding token length calculation (will break seeds that ↵AUTOMATIC2022-10-021-8/+5
| | | | | | use embeddings, you're welcome!) add option to input initialization text for embeddings
* initial support for training textual inversionAUTOMATIC2022-10-021-0/+258