Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 01:04:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

Cleanup

Browse Source
This commit is contained in:
Disty0
2024-06-21 21:07:15 +03:00
parent 0f459411e4
commit bbaec29720
3 changed files with 23 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/intel/ipex/diffusers.py
+8 -11
View File
@@ -70,8 +70,8 @@ class SlicedAttnProcessor: # pylint: disable=too-few-public-methods
def __init__(self, slice_size):
self.slice_size = slice_size
def __call__(self, attn: Attention, hidden_states: torch.FloatTensor,
encoder_hidden_states=None, attention_mask=None) -> torch.FloatTensor: # pylint: disable=too-many-statements, too-many-locals, too-many-branches
def __call__(self, attn: Attention, hidden_states: torch.Tensor,
encoder_hidden_states=None, attention_mask=None) -> torch.Tensor: # pylint: disable=too-many-statements, too-many-locals, too-many-branches
residual = hidden_states
@@ -188,14 +188,11 @@ class AttnProcessor:
Default processor for performing attention-related computations.
"""
def __call__(self, attn: Attention, hidden_states: torch.FloatTensor,
encoder_hidden_states=None, attention_mask=None,
temb=None, scale: float = 1.0) -> torch.Tensor: # pylint: disable=too-many-statements, too-many-locals, too-many-branches
def __call__(self, attn, hidden_states: torch.Tensor, encoder_hidden_states=None, attention_mask=None,
temb=None, *args, **kwargs) -> torch.Tensor: # pylint: disable=too-many-statements, too-many-locals, too-many-branches
residual = hidden_states
args = () if USE_PEFT_BACKEND else (scale,)
if attn.spatial_norm is not None:
hidden_states = attn.spatial_norm(hidden_states, temb)
@@ -213,15 +210,15 @@ class AttnProcessor:
if attn.group_norm is not None:
hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
query = attn.to_q(hidden_states, *args)
query = attn.to_q(hidden_states)
if encoder_hidden_states is None:
encoder_hidden_states = hidden_states
elif attn.norm_cross:
encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
key = attn.to_k(encoder_hidden_states, *args)
value = attn.to_v(encoder_hidden_states, *args)
key = attn.to_k(encoder_hidden_states)
value = attn.to_v(encoder_hidden_states)
query = attn.head_to_batch_dim(query)
key = attn.head_to_batch_dim(key)
@@ -292,7 +289,7 @@ class AttnProcessor:
hidden_states = attn.batch_to_head_dim(hidden_states)
# linear proj
hidden_states = attn.to_out[0](hidden_states, *args)
hidden_states = attn.to_out[0](hidden_states)
# dropout
hidden_states = attn.to_out[1](hidden_states)
modules/sd_hijack_dynamic_atten.py
+12 -15
View File
@@ -110,8 +110,8 @@ class DynamicAttnProcessorSDP:
if not hasattr(F, "scaled_dot_product_attention"):
raise ImportError("AttnProcessor2_0 requires PyTorch 2.0, to use it, please upgrade PyTorch to 2.0.")
def __call__(
self, attn, hidden_states: torch.FloatTensor, encoder_hidden_states=None, attention_mask=None, temb=None, scale: float = 1.0) -> torch.FloatTensor:
def __call__(self, attn, hidden_states: torch.Tensor, encoder_hidden_states=None, attention_mask=None, temb=None, *args, **kwargs) -> torch.Tensor:
residual = hidden_states
if attn.spatial_norm is not None:
hidden_states = attn.spatial_norm(hidden_states, temb)
@@ -135,16 +135,15 @@ class DynamicAttnProcessorSDP:
if attn.group_norm is not None:
hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
args = () if USE_PEFT_BACKEND else (scale,)
query = attn.to_q(hidden_states, *args)
query = attn.to_q(hidden_states)
if encoder_hidden_states is None:
encoder_hidden_states = hidden_states
elif attn.norm_cross:
encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
key = attn.to_k(encoder_hidden_states, *args)
value = attn.to_v(encoder_hidden_states, *args)
key = attn.to_k(encoder_hidden_states)
value = attn.to_v(encoder_hidden_states)
inner_dim = key.shape[-1]
head_dim = inner_dim // attn.heads
@@ -167,7 +166,7 @@ class DynamicAttnProcessorSDP:
hidden_states = hidden_states.to(query.dtype)
# linear proj
hidden_states = attn.to_out[0](hidden_states, *args)
hidden_states = attn.to_out[0](hidden_states)
# dropout
hidden_states = attn.to_out[1](hidden_states)
@@ -190,13 +189,11 @@ class DynamicAttnProcessorBMM:
based on AttnProcessor V1
"""
def __call__(self, attn, hidden_states: torch.FloatTensor, encoder_hidden_states=None, attention_mask=None,
temb=None, scale: float = 1.0) -> torch.Tensor: # pylint: disable=too-many-statements, too-many-locals, too-many-branches
def __call__(self, attn, hidden_states: torch.Tensor, encoder_hidden_states=None, attention_mask=None,
temb=None, *args, **kwargs) -> torch.Tensor: # pylint: disable=too-many-statements, too-many-locals, too-many-branches
residual = hidden_states
args = () if USE_PEFT_BACKEND else (scale,)
if attn.spatial_norm is not None:
hidden_states = attn.spatial_norm(hidden_states, temb)
@@ -214,15 +211,15 @@ class DynamicAttnProcessorBMM:
if attn.group_norm is not None:
hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
query = attn.to_q(hidden_states, *args)
query = attn.to_q(hidden_states)
if encoder_hidden_states is None:
encoder_hidden_states = hidden_states
elif attn.norm_cross:
encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
key = attn.to_k(encoder_hidden_states, *args)
value = attn.to_v(encoder_hidden_states, *args)
key = attn.to_k(encoder_hidden_states)
value = attn.to_v(encoder_hidden_states)
query = attn.head_to_batch_dim(query)
key = attn.head_to_batch_dim(key)
@@ -294,7 +291,7 @@ class DynamicAttnProcessorBMM:
hidden_states = attn.batch_to_head_dim(hidden_states)
# linear proj
hidden_states = attn.to_out[0](hidden_states, *args)
hidden_states = attn.to_out[0](hidden_states)
# dropout
hidden_states = attn.to_out[1](hidden_states)
modules/sd_models.py
+3 -3
View File
@@ -1299,9 +1299,6 @@ def switch_pipe(cls: diffusers.DiffusionPipeline, pipeline: diffusers.DiffusionP
def set_diffuser_pipe(pipe, new_pipe_type):
if get_diffusers_task(pipe) == new_pipe_type:
return pipe
n = getattr(pipe.__class__, '__name__', '')
if new_pipe_type == DiffusersTaskType.TEXT_2_IMAGE and 'StableDiffusionXL' in n and 'requires_aesthetics_score' in pipe.config and hasattr(pipe, '_internal_dict'):
# diffusers adds requires_aesthetics_score with img2img and complains if requires_aesthetics_score exist in txt2img
@@ -1310,6 +1307,9 @@ def set_diffuser_pipe(pipe, new_pipe_type):
del pipe._internal_dict
pipe.register_to_config(**internal_dict)
if get_diffusers_task(pipe) == new_pipe_type:
return pipe
# skip specific pipelines
if n in ['StableDiffusionReferencePipeline', 'StableDiffusionAdapterPipeline', 'AnimateDiffPipeline', 'AnimateDiffSDXLPipeline']:
return pipe