27 Commits (ac085628540d0ec6a988fad93f5b8f2154209571)

Author	SHA1	Message	Date
Cheka	2fd7935ef4	Remove wrong self reference in CUDA support for invokeai	3 years ago
C43H66N12O12S2	c71008c741	Update sd_hijack_optimizations.py	3 years ago
C43H66N12O12S2	84823275e8	readd xformers attnblock	3 years ago
C43H66N12O12S2	2043c4a231	delete xformers attnblock	3 years ago
brkirch	861db783c7	Use apply_hypernetwork function	3 years ago
brkirch	574c8e554a	Add InvokeAI and lstein to credits, add back CUDA support	3 years ago
brkirch	98fd5cde72	Add check for psutil	3 years ago
brkirch	c0484f1b98	Add cross-attention optimization from InvokeAI ... * Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS) * Add command line option for it * Make it default when CUDA is unavailable	3 years ago
AUTOMATIC	873efeed49	rename hypernetwork dir to hypernetworks to prevent clash with an old filename that people who use zip instead of git clone will have	3 years ago
AUTOMATIC	530103b586	fixes related to merge	3 years ago
AUTOMATIC	948533950c	replace duplicate code with a function	3 years ago
C43H66N12O12S2	3e7a981194	remove functorch	3 years ago
Fampai	122d42687b	Fix VRAM Issue by only loading in hypernetwork when selected in settings	3 years ago
AUTOMATIC	e6e42f98df	make --force-enable-xformers work without needing --xformers	3 years ago
AUTOMATIC	f9c5da1592	add fallback for xformers_attnblock_forward	3 years ago
AUTOMATIC	dc1117233e	simplify xfrmers options: --xformers to enable and that's it	3 years ago
AUTOMATIC	7ff1170a2e	emergency fix for xformers (continue + shared)	3 years ago
AUTOMATIC1111	48feae37ff	Merge pull request #1851 from C43H66N12O12S2/flash ... xformers attention	3 years ago
C43H66N12O12S2	69d0053583	update sd_hijack_opt to respect new env variables	3 years ago
C43H66N12O12S2	76a616fa6b	Update sd_hijack_optimizations.py	3 years ago
C43H66N12O12S2	5d54f35c58	add xformers attnblock and hypernetwork support	3 years ago
brkirch	f2055cb1d4	Add hypernetwork support to split cross attention v1 ... * Add hypernetwork support to split_cross_attention_forward_v1 * Fix device check in esrgan_model.py to use devices.device_esrgan instead of shared.device	3 years ago
C43H66N12O12S2	c9cc65b201	switch to the proper way of calling xformers	3 years ago
AUTOMATIC	bad7cb29ce	added support for hypernetworks (???)	3 years ago
C43H66N12O12S2	f174fb2922	add xformers attention	3 years ago
Jairo Correa	ad0cc85d1f	Merge branch 'master' into stable	3 years ago
AUTOMATIC	820f1dc96b	initial support for training textual inversion	3 years ago