Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

LoRA patching optimization (#6439)

Browse Source 
* allow model patcher to optimize away the unpatching step when feasible

* remove lazy_offloading functionality

* allow model patcher to optimize away the unpatching step when feasible

* remove lazy_offloading functionality

* do not save original weights if there is a CPU copy of state dict

* Update invokeai/backend/model_manager/load/load_base.py

Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>

* documentation fixes added during penultimate review

---------

Co-authored-by: Lincoln Stein <lstein@gmail.com>
Co-authored-by: Kent Keirsey <31807370+hipsterusername@users.noreply.github.com>
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>
This commit is contained in:
Lincoln Stein
2024-06-06 09:53:35 -04:00
committed by GitHub
parent 1c5c3cdbd6
commit 2871676f79
7 changed files with 146 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
invokeai/app/invocations/compel.py
View File

@ -81,9 +81,13 @@ class CompelInvocation(BaseInvocation):
with (
# apply all patches while the model is on the target device
text_encoder_info as text_encoder,
text_encoder_info.model_on_device() as (model_state_dict, text_encoder),
tokenizer_info as tokenizer,
ModelPatcher.apply_lora_text_encoder(text_encoder, _lora_loader()),
ModelPatcher.apply_lora_text_encoder(
text_encoder,
loras=_lora_loader(),
model_state_dict=model_state_dict,
),
# Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
ModelPatcher.apply_clip_skip(text_encoder, self.clip.skipped_layers),
ModelPatcher.apply_ti(tokenizer, text_encoder, ti_list) as (
@ -172,9 +176,14 @@ class SDXLPromptInvocationBase:
with (
# apply all patches while the model is on the target device
text_encoder_info as text_encoder,
text_encoder_info.model_on_device() as (state_dict, text_encoder),
tokenizer_info as tokenizer,
ModelPatcher.apply_lora(text_encoder, _lora_loader(), lora_prefix),
ModelPatcher.apply_lora(
text_encoder,
loras=_lora_loader(),
prefix=lora_prefix,
model_state_dict=state_dict,
),
# Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
ModelPatcher.apply_clip_skip(text_encoder, clip_field.skipped_layers),
ModelPatcher.apply_ti(tokenizer, text_encoder, ti_list) as (