textual-inversion-diff - textual-inversion-diff

	Commit message (Collapse)	Author	Age	Files	Lines
*	Added multi-vector embeddings	Volpeon	2022-12-31	8	-81/+299
\|
*	Misc improvements	Volpeon	2022-12-30	3	-78/+56
\|
*	Training script improvements	Volpeon	2022-12-30	5	-25/+89
\|
*	Update	Volpeon	2022-12-29	2	-11/+16
\|
*	Training improvements	Volpeon	2022-12-29	3	-29/+42
\|
*	Updated 1-cycle scheduler	Volpeon	2022-12-28	2	-9/+15
\|
*	Integrated updates from diffusers	Volpeon	2022-12-28	5	-39/+59
\|
*	Improved learning rate finder	Volpeon	2022-12-27	3	-23/+30
\|
*	Added validation phase to learn rate finder	Volpeon	2022-12-27	2	-15/+31
\|
*	Added learning rate finder	Volpeon	2022-12-27	4	-162/+257
\|
*	Set default dimensions to 768; add config inheritance	Volpeon	2022-12-26	7	-26/+36
\|
*	Code simplifications, avoid autocast	Volpeon	2022-12-25	4	-82/+92
\|
*	Update	Volpeon	2022-12-25	3	-3/+3
\|
*	Update	Volpeon	2022-12-24	1	-3/+3
\|
*	Fixed Textual Inversion	Volpeon	2022-12-24	3	-13/+21
\|
*	Training update	Volpeon	2022-12-24	3	-24/+8
\|
*	Update	Volpeon	2022-12-24	3	-10/+26
\|
*	Fix	Volpeon	2022-12-24	1	-1/+1
\|
*	Fix again	Volpeon	2022-12-24	1	-1/+1
\|
*	Fix	Volpeon	2022-12-24	2	-3/+6
\|
*	Better dataset prompt handling	Volpeon	2022-12-23	3	-11/+18
\|
*	num_class_images is now class images per train image	Volpeon	2022-12-23	3	-4/+4
\|
*	Improved class prompt handling	Volpeon	2022-12-23	5	-63/+31
\|
*	Fix	Volpeon	2022-12-23	1	-3/+1
\|
*	Simplified trainable embedding code again	Volpeon	2022-12-23	1	-19/+6
\|
*	Fixed and simplified trainable embeddings code	Volpeon	2022-12-23	1	-12/+12
\|
*	Fixed Textual Inversion	Volpeon	2022-12-22	3	-14/+13
\|
*	Improved Textual Inversion: Completely exclude untrained embeddings from ↵	Volpeon	2022-12-22	2	-18/+76
\| \| \| \|	training
*	Some LoRA fixes (still broken)	Volpeon	2022-12-21	2	-138/+89
\|
*	Moved common training code into separate module	Volpeon	2022-12-21	4	-231/+203
\|
*	Fix training	Volpeon	2022-12-20	5	-15/+1073
\|
*	Dependency cleanup/upgrades	Volpeon	2022-12-20	2	-27/+12
\|
*	Fix Textual Inversion dataset filtering	Volpeon	2022-12-20	1	-1/+5
\|
*	Upstream patches	Volpeon	2022-12-19	1	-5/+17
\|
*	Improved dataset prompt handling, fixed	Volpeon	2022-12-19	4	-23/+25
\|
*	Avoid increased VRAM usage on validation	Volpeon	2022-12-15	4	-12/+29
\|
*	More generic datset filter	Volpeon	2022-12-14	5	-13/+25
\|
*	Unified loading of TI embeddings	Volpeon	2022-12-13	4	-65/+54
\|
*	Optimized Textual Inversion training by filtering dataset by existence of ↵	Volpeon	2022-12-13	3	-10/+47
\| \| \| \|	added tokens
*	Fixed sample/checkpoint frequency	Volpeon	2022-12-13	2	-14/+10
\|
*	Add support for resume in Textual Inversion	Volpeon	2022-12-13	4	-111/+101
\|
*	Dreambooth: Support loading Textual Inversion embeddings	Volpeon	2022-12-12	4	-31/+57
\|
*	Remove embedding checkpoints from Dreambooth training	Volpeon	2022-12-11	1	-40/+16
\|
*	Package updates	Volpeon	2022-12-11	1	-3/+3
\|
*	Training improvements such as tag dropout	Volpeon	2022-12-11	2	-36/+68
\|
*	Support attention_mask of text encoder	Volpeon	2022-12-10	4	-15/+29
\|
*	Various updated; shuffle prompt content during training	Volpeon	2022-12-10	3	-18/+48
\|
*	Fix sample steps	Volpeon	2022-12-06	2	-2/+2
\|
*	Update	Volpeon	2022-12-04	4	-18/+15
\|
*	Update	Volpeon	2022-12-01	2	-6/+6
\|