InvokeAI/ldm/models/diffusion
Lincoln Stein d25bf7a55a cut over from karras to model noise schedule for higher steps
The k_samplers come with a "karras" noise schedule which performs
very well at low step counts but becomes noisy at higher ones.

This commit introduces a threshold (currently 30 steps) at which the
k samplers will switch over from using karras to the older model
noise schedule.
2022-10-27 17:06:49 -04:00
..
__init__.py add code 2021-12-21 03:23:41 +01:00
classifier.py prettified all the code using "blue" at the urging of @tildebyte 2022-08-26 03:15:42 -04:00
cross_attention_control.py keep the effect of _start and _end arguments consistent across k* and other samplers 2022-10-24 01:43:35 +02:00
ddim.py resolve conflicts between PR #1108 and #1243 2022-10-26 15:37:24 -04:00
ddpm.py working with 1.4, 1.5, not with inpainting 1.5 2022-10-26 18:25:48 -04:00
ksampler.py cut over from karras to model noise schedule for higher steps 2022-10-27 17:06:49 -04:00
plms.py resolve conflicts between PR #1108 and #1243 2022-10-26 15:37:24 -04:00
sampler.py acceptable integration of new prompting system and inpainting 2022-10-27 01:51:35 -04:00
shared_invokeai_diffusion.py refactor hybrid and cross attention control codepaths for readability 2022-10-27 19:40:37 +02:00