Millun Atluri 74e644c4ba Allow bfloat16 to be configurable in invoke.yaml (#5469) ... * feat: allow bfloat16 to be configurable in invoke.yaml * fix: `torch_dtype()` util - Use `choose_precision` to get the precision string - Do not reference deprecated `config.full_precision` flat (why does this still exist?), if a user had this enabled it would override their actual precision setting and potentially cause a lot of confusion. --------- Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>		2024-01-12 18:40:37 +00:00
..
api	feat(api): add max_prompts constraints	2023-12-29 08:26:14 -05:00
assets/images	tweaks in response to psychedelicious review of PR	2023-07-26 15:27:04 +10:00
invocations	feat(nodes): add title for cfg rescale mult on denoise_latents	2024-01-03 13:18:50 +11:00
services	Allow bfloat16 to be configurable in invoke.yaml (#5469)	2024-01-12 18:40:37 +00:00
shared	Add CFG Rescale option for supporting zero-terminal SNR models (#4335)	2023-11-30 20:55:20 +11:00
util	Ti trigger from prompt util (#5294)	2023-12-22 03:04:44 +00:00
api_app.py	feat(ui): update assets	2024-01-12 08:02:59 +11:00