Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | keep textual inversion dataset latents in CPU memory to save a bit of VRAM | AUTOMATIC | 2022-10-02 | 2 | -0/+5 |
| | |||||
* | preprocessing for textual inversion added | AUTOMATIC | 2022-10-02 | 3 | -3/+87 |
| | |||||
* | disabled SD model download after multiple complaints | AUTOMATIC | 2022-10-02 | 1 | -1/+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 | 2 | -10/+7 |
| | | | | | | use embeddings, you're welcome!) add option to input initialization text for embeddings | ||||
* | initial support for training textual inversion | AUTOMATIC | 2022-10-02 | 3 | -0/+366 |