Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | apply lr schedule to hypernets | AUTOMATIC | 2022-10-11 | 1 | -40/+4 |
| | |||||
* | Merge branch 'learning_rate-scheduling' into learnschedule | AUTOMATIC1111 | 2022-10-11 | 1 | -9/+11 |
|\ | |||||
| * | add an option to unload models during hypernetwork training to save VRAM | AUTOMATIC | 2022-10-11 | 1 | -1/+1 |
| | | |||||
| * | Merge pull request #2201 from alg-wiki/textual__inversion | AUTOMATIC1111 | 2022-10-11 | 1 | -6/+3 |
| |\ | | | | | | | Textual Inversion: Preprocess and Training will only pick-up image files instead | ||||
| | * | Removed my local edits to checkpoint image generation | alg-wiki | 2022-10-11 | 1 | -5/+2 |
| | | | |||||
| | * | Switched to exception handling | alg-wiki | 2022-10-11 | 1 | -10/+8 |
| | | | |||||
| | * | Added .webp .bmp | alg-wiki | 2022-10-10 | 1 | -1/+1 |
| | | | |||||
| | * | Merge branch 'master' into textual__inversion | alg-wiki | 2022-10-10 | 1 | -0/+1 |
| | |\ | |||||
| | * | | Textual Inversion: Preprocess and Training will only pick-up image files | alg-wiki | 2022-10-10 | 1 | -1/+2 |
| | | | | |||||
| | * | | Custom Width and Height | alg-wiki | 2022-10-10 | 1 | -6/+5 |
| | | | | |||||
| | * | | Fixed progress bar output for epoch | alg-wiki | 2022-10-10 | 1 | -1/+1 |
| | | | | |||||
| | * | | Textual Inversion: Added custom training image size and number of repeats ↵ | alg-wiki | 2022-10-10 | 1 | -3/+12 |
| | | | | | | | | | | | | | | | | per input image in a single epoch | ||||
| * | | | fixes related to merge | AUTOMATIC | 2022-10-11 | 1 | -5/+7 |
| | |/ | |/| | |||||
* / | | Refactored learning rate code | Fampai | 2022-10-10 | 1 | -4/+47 |
|/ / | |||||
* | | Custom Width and Height | alg-wiki | 2022-10-10 | 1 | -6/+5 |
| | | |||||
* | | Fixed progress bar output for epoch | alg-wiki | 2022-10-10 | 1 | -1/+1 |
| | | |||||
* | | Textual Inversion: Added custom training image size and number of repeats ↵ | alg-wiki | 2022-10-10 | 1 | -3/+12 |
|/ | | | | per input image in a single epoch | ||||
* | fix broken date in TI | AUTOMATIC | 2022-10-03 | 1 | -1/+1 |
| | |||||
* | keep textual inversion dataset latents in CPU memory to save a bit of VRAM | AUTOMATIC | 2022-10-02 | 1 | -0/+3 |
| | |||||
* | preprocessing for textual inversion added | AUTOMATIC | 2022-10-02 | 1 | -0/+1 |
| | |||||
* | add checkpoint info to saved embeddings | AUTOMATIC | 2022-10-02 | 1 | -1/+12 |
| | |||||
* | fix using aaaa-100 embedding when the prompt has aaaa-10000 and you have ↵ | AUTOMATIC | 2022-10-02 | 1 | -1/+2 |
| | | | | both aaaa-100 and aaaa-10000 in the directory with embeddings. | ||||
* | fix for incorrect embedding token length calculation (will break seeds that ↵ | AUTOMATIC | 2022-10-02 | 1 | -8/+5 |
| | | | | | | use embeddings, you're welcome!) add option to input initialization text for embeddings | ||||
* | initial support for training textual inversion | AUTOMATIC | 2022-10-02 | 1 | -0/+258 |