Skip to content

Update Compel to 2.1.1 and apply Sentences Split logic #8026

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Update Compel to 2.1.1 and apply Sentences Split logic #8026

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion invokeai/app/invocations/compel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
from typing import Iterator, List, Optional, Tuple, Union, cast

import torch
from compel import Compel, ReturnedEmbeddingsType
from compel import Compel, ReturnedEmbeddingsType, SplitLongTextMode
from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer

Expand Down Expand Up @@ -104,6 +104,7 @@ def _lora_loader() -> Iterator[Tuple[ModelPatchRaw, float]]:
dtype_for_device_getter=TorchDevice.choose_torch_dtype,
truncate_long_prompts=False,
device=TorchDevice.choose_torch_device(),
split_long_text_mode=SplitLongTextMode.SENTENCES,
)

conjunction = Compel.parse_prompt_string(self.prompt)
Expand Down Expand Up @@ -205,6 +206,7 @@ def _lora_loader() -> Iterator[Tuple[ModelPatchRaw, float]]:
returned_embeddings_type=ReturnedEmbeddingsType.PENULTIMATE_HIDDEN_STATES_NON_NORMALIZED, # TODO: clip skip
requires_pooled=get_pooled,
device=TorchDevice.choose_torch_device(),
split_long_text_mode=SplitLongTextMode.SENTENCES,
)

conjunction = Compel.parse_prompt_string(prompt)
Expand Down
10 changes: 5 additions & 5 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,20 +10,20 @@ readme = { content-type = "text/markdown", file = "README.md" }
keywords = ["stable-diffusion", "AI"]
dynamic = ["version"]
license = { file = "LICENSE" }
authors = [{ name = "The InvokeAI Project", email = "[email protected]" }]
authors = [{ name = "Invoke", email = "[email protected]" }]
classifiers = [
'Development Status :: 4 - Beta',
'Development Status :: 5 - Production/Stable',
'Environment :: GPU',
'Environment :: GPU :: NVIDIA CUDA',
'Environment :: MacOS X',
'Intended Audience :: End Users/Desktop',
'Intended Audience :: Developers',
'License :: OSI Approved :: MIT License',
'License :: OSI Approved :: Apache-2.0',
'Operating System :: POSIX :: Linux',
'Operating System :: MacOS',
'Operating System :: Microsoft :: Windows',
'Programming Language :: Python :: 3 :: Only',
'Programming Language :: Python :: 3.10',
'Programming Language :: Python :: 3.12',
'Topic :: Artistic Software',
'Topic :: Internet :: WWW/HTTP :: WSGI :: Application',
'Topic :: Internet :: WWW/HTTP :: WSGI :: Server',
Expand All @@ -35,7 +35,7 @@ dependencies = [
# Core generation dependencies, pinned for reproducible builds.
"accelerate",
"bitsandbytes; sys_platform!='darwin'",
"compel==2.0.2",
"compel==2.1.1",
"diffusers[torch]==0.33.0",
"gguf",
"invisible-watermark==0.2.0", # needed to install SDXL base and refiner using their repo_ids
Expand Down
Loading