github/InvokeAI
1
1
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI.git synced 2026-04-23 03:00:31 -04:00
Code Issues Packages Projects Releases Wiki Activity

Remove logic for modifying attn processors from DiffusersControlNetFlux.

Browse Source
This commit is contained in:
Ryan Dick
2024-10-04 15:08:54 +00:00
parent 3578010ba4
commit a17ea9bfad
1 changed files with 0 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
invokeai/backend/flux/controlnet/diffusers_controlnet_flux.py
View File

@@ -11,7 +11,6 @@ from typing import Any, Dict, List, Optional, Tuple, Union
import torch
import torch.nn as nn
from diffusers.configuration_utils import ConfigMixin, register_to_config
from diffusers.models.attention_processor import AttentionProcessor
from diffusers.models.controlnet import zero_module
from diffusers.models.modeling_utils import ModelMixin
from diffusers.utils.outputs import BaseOutput
@@ -95,66 +94,6 @@ class DiffusersControlNetFlux(ModelMixin, ConfigMixin, PeftAdapterMixin):
self.gradient_checkpointing = False
@property
# Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.attn_processors
def attn_processors(self):
r"""
Returns:
`dict` of attention processors: A dictionary containing all attention processors used in the model with
indexed by its weight name.
"""
# set recursively
processors = {}
def fn_recursive_add_processors(name: str, module: torch.nn.Module, processors: Dict[str, AttentionProcessor]):
if hasattr(module, "get_processor"):
processors[f"{name}.processor"] = module.get_processor()
for sub_name, child in module.named_children():
fn_recursive_add_processors(f"{name}.{sub_name}", child, processors)
return processors
for name, module in self.named_children():
fn_recursive_add_processors(name, module, processors)
return processors
# Copied from diffusers.models.unets.unet_2d_condition.UNet2DConditionModel.set_attn_processor
def set_attn_processor(self, processor):
r"""
Sets the attention processor to use to compute attention.
Parameters:
processor (`dict` of `AttentionProcessor` or only `AttentionProcessor`):
The instantiated processor class or a dictionary of processor classes that will be set as the processor
for **all** `Attention` layers.
If `processor` is a dict, the key needs to define the path to the corresponding cross attention
processor. This is strongly recommended when setting trainable attention processors.
"""
count = len(self.attn_processors.keys())
if isinstance(processor, dict) and len(processor) != count:
raise ValueError(
f"A dict of processors was passed, but the number of processors {len(processor)} does not match the"
f" number of attention layers: {count}. Please make sure to pass {count} processor classes."
)
def fn_recursive_attn_processor(name: str, module: torch.nn.Module, processor):
if hasattr(module, "set_processor"):
if not isinstance(processor, dict):
module.set_processor(processor)
else:
module.set_processor(processor.pop(f"{name}.processor"))
for sub_name, child in module.named_children():
fn_recursive_attn_processor(f"{name}.{sub_name}", child, processor)
for name, module in self.named_children():
fn_recursive_attn_processor(name, module, processor)
def _set_gradient_checkpointing(self, module, value=False):
if hasattr(module, "gradient_checkpointing"):
module.gradient_checkpointing = value