Mihail Dumitrescu d176fb07cd Replace --full_precision with --precision that works even if not specified ... Allowed values are 'auto', 'float32', 'autocast', 'float16'. If not specified or 'auto' a working precision is automatically selected based on the torch device. Context: #526 Deprecated --full_precision / -F Tested on both cuda and cpu by calling scripts/dream.py without arguments and checked the auto configuration worked. With --precision=auto/float32/autocast/float16 it performs as expected, either working or failing with a reasonable error. Also checked Img2Img.		2022-09-20 17:08:00 -04:00
..
orig_scripts	Refactor generate.py and dream.py (#534)	2022-09-14 07:02:31 -04:00
dream.py	Replace --full_precision with --precision that works even if not specified	2022-09-20 17:08:00 -04:00
images2prompt.py	tidied up scripts directory by moving the original CompViz scripts into a subfolder	2022-08-22 10:11:54 -04:00
merge_embeddings.py	Fix merging embeddings (#226)	2022-08-31 11:24:11 -04:00
preload_models.py	Use model_url instead of model_path for gfpgan and CodeFormer. Fixes lstein/stable-diffusion#678	2022-09-20 07:15:54 -04:00
sd-metadata.py	Squashed commit of the following:	2022-09-16 16:58:16 -04:00