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
..
CHANGELOG.md	Mkdocs material (#593)	2022-09-15 14:35:22 -04:00
CLI.md	Replace --full_precision with --precision that works even if not specified	2022-09-20 17:08:00 -04:00
EMBIGGEN.md	Add documentation for Embiggen	2022-09-12 15:46:07 -04:00
IMG2IMG.md	Mkdocs-material (#575)	2022-09-15 10:53:41 -04:00
INPAINTING.md	Updating with evergreen Discord invite (#635)	2022-09-18 21:30:21 -04:00
OTHER.md	Documentation for negative prompts (#668)	2022-09-18 09:50:19 -04:00
PROMPTS.md	Documentation for negative prompts (#668)	2022-09-18 09:50:19 -04:00
TEXTUAL_INVERSION.md	Replace --full_precision with --precision that works even if not specified	2022-09-20 17:08:00 -04:00
UPSCALE.md	Implement CodeFormer Face Restoration (#669)	2022-09-18 15:01:05 -04:00
VARIATIONS.md	VARIATIONS.md - fix typo in formatting (#664)	2022-09-18 09:50:54 -04:00
WEB.md	Mkdocs-material (#575)	2022-09-15 10:53:41 -04:00