11 Commits

Author	SHA1	Message	Date
Mihai	071f65a892	Enable even larger images with one simple torch.nn.functional.silu import (#653) ... Fixes: File "stable-diffusion/ldm/modules/diffusionmodules/model.py", line 37, in nonlinearity return x*torch.sigmoid(x) RuntimeError: CUDA out of memory. Tried to allocate 1.56 GiB [..] Now up to 1536x1280 is possible on 8GB VRAM. Also remove unused SiLU class.	2022-09-17 18:03:52 -04:00
Mihai	dedf8a3692	Remove pointless del statements in diffusionmodules.model. (#520)	2022-09-12 17:39:06 -04:00
Mihai	0bc6779361	Disable autocast for cpu to fix error. Remove unused precision arg. (#518) ... When running on just cpu (intel), a call to torch.layer_norm would error with RuntimeError: expected scalar type BFloat16 but found Float Fix buggy device handling in model.py. Tested with scripts/dream.py --full_precision on just cpu on intel laptop. Works but slow at ~10s/it.	2022-09-12 16:55:21 -04:00
Any-Winter-4079	25d9ccc509	Update model.py	2022-09-11 22:37:45 -04:00
Lincoln Stein	10db192cc4	changes to dogettx optimizations to run on m1 ... * Author @any-winter-4079 * Author @dogettx Thanks to many individuals who contributed time and hardware to benchmarking and debugging these changes.	2022-09-09 09:51:41 -04:00
Lincoln Stein	653144694f	work around unexplained crash when timesteps=1000 (#440) ... * work around unexplained crash when timesteps=1000 * this fix seems to work	2022-09-08 20:41:37 -04:00
Lincoln Stein	4f02b72c9c	prettified all the code using "blue" at the urging of @tildebyte	2022-08-26 03:15:42 -04:00
Sean McLellan	8952196bbf	Add personalization	2022-08-23 18:26:28 -04:00
Robin Rombach	2ff270f4e0	stable diffusion	2022-08-10 16:30:49 +02:00
ablattmann	171cf29fb5	add configs for training unconditional/class-conditional ldms	2021-12-22 15:57:23 +01:00
ablattmann	e66308c7f2	add code	2021-12-21 03:23:41 +01:00