Jonathan 093174942b Add thresholding for all diffusers types (#2479) ... `generator` now asks `InvokeAIDiffuserComponent` to do postprocessing work on latents after every step. Thresholding - now implemented as replacing latents outside of the threshold with random noise - is called at this point. This postprocessing step is also where we can hook up symmetry and other image latent manipulations in the future. Note: code at this layer doesn't need to worry about MPS as relevant torch functions are wrapped and made MPS-safe by `generator.py`.		2023-02-14 18:00:34 -06:00
..
__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	rename override/restore methods to better reflect what they actually do	2023-01-30 16:23:44 +01:00
cross_attention_map_saving.py	Save and display per-token attention maps (#1866)	2022-12-10 15:57:41 +01:00
ddim.py	rename override/restore methods to better reflect what they actually do	2023-01-30 16:23:44 +01:00
ddpm.py	use 🧨diffusers model (#1583)	2023-01-15 09:22:46 -05:00
ksampler.py	rename override/restore methods to better reflect what they actually do	2023-01-30 16:23:44 +01:00
plms.py	rename override/restore methods to better reflect what they actually do	2023-01-30 16:23:44 +01:00
sampler.py	Global replace [ \t]+$, add "GB" (#1751)	2022-12-19 16:36:39 +00:00
shared_invokeai_diffusion.py	Add thresholding for all diffusers types (#2479)	2023-02-14 18:00:34 -06:00