Mathis Koroglu 3e0d128da7 Motion Model / Adapter versatility (#8301) ...

* Motion Model / Adapter versatility

- allow to use a different number of layers per block
- allow to use a different number of transformer per layers per block
- allow a different number of motion attention head per block
- use dropout argument in get_down/up_block in 3d blocks

* Motion Model added arguments renamed & refactoring

* Add test for asymmetric UNetMotionModel

2024-06-27 11:11:29 +05:30

..

autoencoders

Adding VQGAN Training script (#5483)

2024-05-15 08:47:12 +05:30

transformers

Add Stable Diffusion 3 (#8483)

2024-06-12 20:44:00 +01:00

unets

Motion Model / Adapter versatility (#8301)

2024-06-27 11:11:29 +05:30

__init__.py

[Tests] Improve unet / vae tests (#1018)

2022-10-28 13:43:26 +02:00

test_activations.py

move activation dispatches into helper function (#3656)

2023-06-05 12:30:48 -07:00

test_attention_processor.py

adding back test_conversion_when_using_device_map (#7704)

2024-04-18 19:21:32 -10:00

test_layers_utils.py

[LoRA] use the PyTorch classes wherever needed and start depcrecation cycles (#7204)

2024-03-13 07:56:19 +05:30

test_modeling_common_flax.py

[Tests] parallelize (#3078)

2023-04-13 13:32:57 +01:00

test_modeling_common.py

Update xformers SD3 test (#8712)

2024-06-26 10:24:27 -10:00