Damian Stewart 786b8878d6 Save and display per-token attention maps (#1866) ...

* attention maps saving to /tmp

* tidy up diffusers branch backporting of cross attention refactoring

* base64-encoding the attention maps image for generationResult

* cleanup/refactor conditioning.py

* attention maps and tokens being sent to web UI

* attention maps: restrict count to actual token count and improve robustness

* add argument type hint to image_to_dataURL function

Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>

Co-authored-by: damian <git@damianstewart.com>
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>

2022-12-10 15:57:41 +01:00

..

diffusionmodules

cleanup

2022-10-21 15:07:11 +02:00

distributions

prettified all the code using "blue" at the urging of @tildebyte

2022-08-26 03:15:42 -04:00

encoders

Merge dev into main for 2.2.0 (#1642)

2022-11-30 16:12:23 -05:00

image_degradation

prevent crash that occurs when changing models.yaml on windows systems

2022-11-25 16:59:31 -05:00

losses

prettified all the code using "blue" at the urging of @tildebyte

2022-08-26 03:15:42 -04:00

__init__.py

Merge dev into main for 2.2.0 (#1642)

2022-11-30 16:12:23 -05:00

attention.py

Save and display per-token attention maps (#1866)

2022-12-10 15:57:41 +01:00

ema.py

prettified all the code using "blue" at the urging of @tildebyte

2022-08-26 03:15:42 -04:00

embedding_manager.py

Merge dev into main for 2.2.0 (#1642)

2022-11-30 16:12:23 -05:00

x_transformer.py

prettified all the code using "blue" at the urging of @tildebyte

2022-08-26 03:15:42 -04:00