Raphael Walker 61b50720d0 Add support for attention masking in Flux (#5942) ... * fix attention OOM in xformers * allow passing attention mask in flux attention * allow an attn_mask in flux * attn masks can be done using replace patches instead of a separate dict * fix return types * fix return order * enumerate * patch the right keys * arg names * fix a silly bug * fix xformers masks * replace match with if, elif, else * mask with image_ref_size * remove unused import * remove unused import 2 * fix pytorch/xformers attention This corrects a weird inconsistency with skip_reshape. It also allows masks of various shapes to be passed, which will be automtically expanded (in a memory-efficient way) to a size that is compatible with xformers or pytorch sdpa respectively. * fix mask shapes		2024-12-16 18:21:17 -05:00
..
diffusionmodules	Support conv3d in PatchEmbed.	2024-12-14 05:46:04 -05:00
distributions	Initial commit.	2023-01-16 22:37:14 -05:00
encoders	Make unclip more deterministic.	2024-01-14 17:28:31 -05:00
attention.py	Add support for attention masking in Flux (#5942)	2024-12-16 18:21:17 -05:00
ema.py	Initial commit.	2023-01-16 22:37:14 -05:00
sub_quadratic_attention.py	Enforce all pyflake lint rules (#6033)	2024-12-12 19:29:37 -05:00
temporal_ae.py	Lint unused import (#5973)	2024-12-09 15:24:39 -05:00