mirror of https://github.com/huggingface/diffusers.git synced 2025-12-09 05:54:24 +08:00

Files

Sayak Paul a2bc2e14b9 [feat] allow SDXL pipeline to run with fused QKV projections (#6030 )

* debug

* from step

* print

* turn sigma a list

* make str

* init_noise_sigma

* comment

* remove prints

* feat: introduce fused projections

* change to a better name

* no grad

* device.

* device

* dtype

* okay

* print

* more print

* fix: unbind -> split

* fix: qkv >-> k

* enable disable

* apply attention processor within the method

* attn processors

* _enable_fused_qkv_projections

* remove print

* add fused projection to vae

* add todos.

* add: documentation and cleanups.

* add: test for qkv projection fusion.

* relax assertions.

* relax further

* fix: docs

* fix-copies

* correct error message.

* Empty-Commit

* better conditioning on disable_fused_qkv_projections

* check

* check processor

* bfloat16 computation.

* check latent dtype

* style

* remove copy temporarily

* cast latent to bfloat16

* fix: vae -> self.vae

* remove print.

* add _change_to_group_norm_32

* comment out stuff that didn't work

* Apply suggestions from code review

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* reflect patrick's suggestions.

* fix imports

* fix: disable call.

* fix more

* fix device and dtype

* fix conditions.

* fix more

* Apply suggestions from code review

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

2023-12-06 07:33:26 +05:30

2.0 KiB

Raw Blame History

Attention Processor

An attention processor is a class for applying different types of attention mechanisms.

AttnProcessor

autodoc models.attention_processor.AttnProcessor

AttnProcessor2_0

autodoc models.attention_processor.AttnProcessor2_0

FusedAttnProcessor2_0

autodoc models.attention_processor.FusedAttnProcessor2_0

LoRAAttnProcessor

autodoc models.attention_processor.LoRAAttnProcessor

LoRAAttnProcessor2_0

autodoc models.attention_processor.LoRAAttnProcessor2_0

CustomDiffusionAttnProcessor

autodoc models.attention_processor.CustomDiffusionAttnProcessor

CustomDiffusionAttnProcessor2_0

autodoc models.attention_processor.CustomDiffusionAttnProcessor2_0

AttnAddedKVProcessor

autodoc models.attention_processor.AttnAddedKVProcessor

AttnAddedKVProcessor2_0

autodoc models.attention_processor.AttnAddedKVProcessor2_0

LoRAAttnAddedKVProcessor

autodoc models.attention_processor.LoRAAttnAddedKVProcessor

XFormersAttnProcessor

autodoc models.attention_processor.XFormersAttnProcessor

LoRAXFormersAttnProcessor

autodoc models.attention_processor.LoRAXFormersAttnProcessor

CustomDiffusionXFormersAttnProcessor

autodoc models.attention_processor.CustomDiffusionXFormersAttnProcessor

SlicedAttnProcessor

autodoc models.attention_processor.SlicedAttnProcessor

SlicedAttnAddedKVProcessor

autodoc models.attention_processor.SlicedAttnAddedKVProcessor

2.0 KiB Raw Blame History