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

Merge branch 'main' into release/invokeai-3-0-1

Browse Source
This commit is contained in:
Lincoln Stein 2023-07-27 15:21:08 -04:00
commit 006075483d
9 changed files with 173 additions and 157 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -123,7 +123,7 @@ and go to http://localhost:9090.
### Command-Line Installation (for developers and users familiar with Terminals)
You must have Python 3.9 or 3.10 installed on your machine. Earlier or
You must have Python 3.9 through 3.11 installed on your machine. Earlier or
later versions are not supported.
Node.js also needs to be installed along with yarn (can be installed with
the command `npm install -g yarn` if needed)

6
docs/installation/010_INSTALL_AUTOMATED.md
View File

@ -40,10 +40,8 @@ experimental versions later.
this, open up a command-line window ("Terminal" on Linux and
Macintosh, "Command" or "Powershell" on Windows) and type `python
--version`. If Python is installed, it will print out the version
number. If it is version `3.9.*` or `3.10.*`, you meet
requirements. We do not recommend using Python 3.11 or higher,
as not all the libraries that InvokeAI depends on work properly
with this version.
number. If it is version `3.9.*`, `3.10.*` or `3.11.*` you meet
requirements.
!!! warning "What to do if you have an unsupported version"

4
docs/installation/020_INSTALL_MANUAL.md
View File

@ -32,7 +32,7 @@ gaming):
* **Python**
version 3.9 or 3.10 (3.11 is not recommended).
version 3.9 through 3.11
* **CUDA Tools**
@ -65,7 +65,7 @@ gaming):
To install InvokeAI with virtual environments and the PIP package
manager, please follow these steps:
1. Please make sure you are using Python 3.9 or 3.10. The rest of the install
1. Please make sure you are using Python 3.9 through 3.11. The rest of the install
procedure depends on this and will not work with other versions:
```bash

16
installer/install.sh.in
View File

@ -9,16 +9,20 @@ cd $scriptdir
function version { echo "$@" | awk -F. '{ printf("%d%03d%03d%03d\n", $1,$2,$3,$4); }'; }
MINIMUM_PYTHON_VERSION=3.9.0
MAXIMUM_PYTHON_VERSION=3.11.0
MAXIMUM_PYTHON_VERSION=3.11.100
PYTHON=""
for candidate in python3.10 python3.9 python3 python ; do
for candidate in python3.11 python3.10 python3.9 python3 python ; do
if ppath=`which $candidate`; then
# when using `pyenv`, the executable for an inactive Python version will exist but will not be operational
# we check that this found executable can actually run
if [ $($candidate --version &>/dev/null; echo ${PIPESTATUS}) -gt 0 ]; then continue; fi
python_version=$($ppath -V | awk '{ print $2 }')
if [ $(version $python_version) -ge $(version "$MINIMUM_PYTHON_VERSION") ]; then
if [ $(version $python_version) -lt $(version "$MAXIMUM_PYTHON_VERSION") ]; then
PYTHON=$ppath
break
fi
if [ $(version $python_version) -le $(version "$MAXIMUM_PYTHON_VERSION") ]; then
PYTHON=$ppath
break
fi
fi
fi
done

2
invokeai/app/api/routers/models.py
View File

@ -90,7 +90,7 @@ async def update_model(
new_name=info.model_name,
new_base=info.base_model,
)
logger.info(f"Successfully renamed {base_model}/{model_name}=>{info.base_model}/{info.model_name}")
logger.info(f"Successfully renamed {base_model.value}/{model_name}=>{info.base_model}/{info.model_name}")
# update information to support an update of attributes
model_name = info.model_name
base_model = info.base_model

242
invokeai/app/invocations/latent.py
View File

@ -12,7 +12,7 @@ from pydantic import BaseModel, Field, validator
from invokeai.app.invocations.metadata import CoreMetadata
from invokeai.app.util.step_callback import stable_diffusion_step_callback
from invokeai.backend.model_management.models.base import ModelType
from invokeai.backend.model_management.models import ModelType, SilenceWarnings
from ...backend.model_management.lora import ModelPatcher
from ...backend.stable_diffusion import PipelineIntermediateState
@ -311,70 +311,71 @@ class TextToLatentsInvocation(BaseInvocation):
@torch.no_grad()
def invoke(self, context: InvocationContext) -> LatentsOutput:
noise = context.services.latents.get(self.noise.latents_name)
with SilenceWarnings():
noise = context.services.latents.get(self.noise.latents_name)
# Get the source node id (we are invoking the prepared node)
graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
source_node_id = graph_execution_state.prepared_source_mapping[self.id]
# Get the source node id (we are invoking the prepared node)
graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
source_node_id = graph_execution_state.prepared_source_mapping[self.id]
def step_callback(state: PipelineIntermediateState):
self.dispatch_progress(context, source_node_id, state)
def step_callback(state: PipelineIntermediateState):
self.dispatch_progress(context, source_node_id, state)
def _lora_loader():
for lora in self.unet.loras:
lora_info = context.services.model_manager.get_model(
**lora.dict(exclude={"weight"}),
def _lora_loader():
for lora in self.unet.loras:
lora_info = context.services.model_manager.get_model(
**lora.dict(exclude={"weight"}),
context=context,
)
yield (lora_info.context.model, lora.weight)
del lora_info
return
unet_info = context.services.model_manager.get_model(
**self.unet.unet.dict(),
context=context,
)
with ExitStack() as exit_stack, ModelPatcher.apply_lora_unet(
unet_info.context.model, _lora_loader()
), unet_info as unet:
noise = noise.to(device=unet.device, dtype=unet.dtype)
scheduler = get_scheduler(
context=context,
scheduler_info=self.unet.scheduler,
scheduler_name=self.scheduler,
)
yield (lora_info.context.model, lora.weight)
del lora_info
return
unet_info = context.services.model_manager.get_model(
**self.unet.unet.dict(),
context=context,
)
with ExitStack() as exit_stack, ModelPatcher.apply_lora_unet(
unet_info.context.model, _lora_loader()
), unet_info as unet:
noise = noise.to(device=unet.device, dtype=unet.dtype)
pipeline = self.create_pipeline(unet, scheduler)
conditioning_data = self.get_conditioning_data(context, scheduler, unet)
scheduler = get_scheduler(
context=context,
scheduler_info=self.unet.scheduler,
scheduler_name=self.scheduler,
)
control_data = self.prep_control_data(
model=pipeline,
context=context,
control_input=self.control,
latents_shape=noise.shape,
# do_classifier_free_guidance=(self.cfg_scale >= 1.0))
do_classifier_free_guidance=True,
exit_stack=exit_stack,
)
pipeline = self.create_pipeline(unet, scheduler)
conditioning_data = self.get_conditioning_data(context, scheduler, unet)
# TODO: Verify the noise is the right size
result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
latents=torch.zeros_like(noise, dtype=torch_dtype(unet.device)),
noise=noise,
num_inference_steps=self.steps,
conditioning_data=conditioning_data,
control_data=control_data, # list[ControlNetData]
callback=step_callback,
)
control_data = self.prep_control_data(
model=pipeline,
context=context,
control_input=self.control,
latents_shape=noise.shape,
# do_classifier_free_guidance=(self.cfg_scale >= 1.0))
do_classifier_free_guidance=True,
exit_stack=exit_stack,
)
# https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
result_latents = result_latents.to("cpu")
torch.cuda.empty_cache()
# TODO: Verify the noise is the right size
result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
latents=torch.zeros_like(noise, dtype=torch_dtype(unet.device)),
noise=noise,
num_inference_steps=self.steps,
conditioning_data=conditioning_data,
control_data=control_data, # list[ControlNetData]
callback=step_callback,
)
# https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
result_latents = result_latents.to("cpu")
torch.cuda.empty_cache()
name = f"{context.graph_execution_state_id}__{self.id}"
context.services.latents.save(name, result_latents)
return build_latents_output(latents_name=name, latents=result_latents)
name = f"{context.graph_execution_state_id}__{self.id}"
context.services.latents.save(name, result_latents)
return build_latents_output(latents_name=name, latents=result_latents)
class LatentsToLatentsInvocation(TextToLatentsInvocation):
@ -402,82 +403,83 @@ class LatentsToLatentsInvocation(TextToLatentsInvocation):
@torch.no_grad()
def invoke(self, context: InvocationContext) -> LatentsOutput:
noise = context.services.latents.get(self.noise.latents_name)
latent = context.services.latents.get(self.latents.latents_name)
with SilenceWarnings(): # this quenches NSFW nag from diffusers
noise = context.services.latents.get(self.noise.latents_name)
latent = context.services.latents.get(self.latents.latents_name)
# Get the source node id (we are invoking the prepared node)
graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
source_node_id = graph_execution_state.prepared_source_mapping[self.id]
# Get the source node id (we are invoking the prepared node)
graph_execution_state = context.services.graph_execution_manager.get(context.graph_execution_state_id)
source_node_id = graph_execution_state.prepared_source_mapping[self.id]
def step_callback(state: PipelineIntermediateState):
self.dispatch_progress(context, source_node_id, state)
def step_callback(state: PipelineIntermediateState):
self.dispatch_progress(context, source_node_id, state)
def _lora_loader():
for lora in self.unet.loras:
lora_info = context.services.model_manager.get_model(
**lora.dict(exclude={"weight"}),
def _lora_loader():
for lora in self.unet.loras:
lora_info = context.services.model_manager.get_model(
**lora.dict(exclude={"weight"}),
context=context,
)
yield (lora_info.context.model, lora.weight)
del lora_info
return
unet_info = context.services.model_manager.get_model(
**self.unet.unet.dict(),
context=context,
)
with ExitStack() as exit_stack, ModelPatcher.apply_lora_unet(
unet_info.context.model, _lora_loader()
), unet_info as unet:
noise = noise.to(device=unet.device, dtype=unet.dtype)
latent = latent.to(device=unet.device, dtype=unet.dtype)
scheduler = get_scheduler(
context=context,
scheduler_info=self.unet.scheduler,
scheduler_name=self.scheduler,
)
yield (lora_info.context.model, lora.weight)
del lora_info
return
unet_info = context.services.model_manager.get_model(
**self.unet.unet.dict(),
context=context,
)
with ExitStack() as exit_stack, ModelPatcher.apply_lora_unet(
unet_info.context.model, _lora_loader()
), unet_info as unet:
noise = noise.to(device=unet.device, dtype=unet.dtype)
latent = latent.to(device=unet.device, dtype=unet.dtype)
pipeline = self.create_pipeline(unet, scheduler)
conditioning_data = self.get_conditioning_data(context, scheduler, unet)
scheduler = get_scheduler(
context=context,
scheduler_info=self.unet.scheduler,
scheduler_name=self.scheduler,
)
control_data = self.prep_control_data(
model=pipeline,
context=context,
control_input=self.control,
latents_shape=noise.shape,
# do_classifier_free_guidance=(self.cfg_scale >= 1.0))
do_classifier_free_guidance=True,
exit_stack=exit_stack,
)
pipeline = self.create_pipeline(unet, scheduler)
conditioning_data = self.get_conditioning_data(context, scheduler, unet)
# TODO: Verify the noise is the right size
initial_latents = (
latent if self.strength < 1.0 else torch.zeros_like(latent, device=unet.device, dtype=latent.dtype)
)
control_data = self.prep_control_data(
model=pipeline,
context=context,
control_input=self.control,
latents_shape=noise.shape,
# do_classifier_free_guidance=(self.cfg_scale >= 1.0))
do_classifier_free_guidance=True,
exit_stack=exit_stack,
)
timesteps, _ = pipeline.get_img2img_timesteps(
self.steps,
self.strength,
device=unet.device,
)
# TODO: Verify the noise is the right size
initial_latents = (
latent if self.strength < 1.0 else torch.zeros_like(latent, device=unet.device, dtype=latent.dtype)
)
result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
latents=initial_latents,
timesteps=timesteps,
noise=noise,
num_inference_steps=self.steps,
conditioning_data=conditioning_data,
control_data=control_data, # list[ControlNetData]
callback=step_callback,
)
timesteps, _ = pipeline.get_img2img_timesteps(
self.steps,
self.strength,
device=unet.device,
)
# https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
result_latents = result_latents.to("cpu")
torch.cuda.empty_cache()
result_latents, result_attention_map_saver = pipeline.latents_from_embeddings(
latents=initial_latents,
timesteps=timesteps,
noise=noise,
num_inference_steps=self.steps,
conditioning_data=conditioning_data,
control_data=control_data, # list[ControlNetData]
callback=step_callback,
)
# https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
result_latents = result_latents.to("cpu")
torch.cuda.empty_cache()
name = f"{context.graph_execution_state_id}__{self.id}"
context.services.latents.save(name, result_latents)
name = f"{context.graph_execution_state_id}__{self.id}"
context.services.latents.save(name, result_latents)
return build_latents_output(latents_name=name, latents=result_latents)
@ -490,7 +492,7 @@ class LatentsToImageInvocation(BaseInvocation):
# Inputs
latents: Optional[LatentsField] = Field(description="The latents to generate an image from")
vae: VaeField = Field(default=None, description="Vae submodel")
tiled: bool = Field(default=False, description="Decode latents by overlapping tiles(less memory consumption)")
tiled: bool = Field(default=False, description="Decode latents by overlaping tiles (less memory consumption)")
fp32: bool = Field(DEFAULT_PRECISION == "float32", description="Decode in full precision")
metadata: Optional[CoreMetadata] = Field(
default=None, description="Optional core metadata to be written to the image"

6
invokeai/backend/model_management/model_manager.py
View File

@ -401,7 +401,11 @@ class ModelManager(object):
base_model: BaseModelType,
model_type: ModelType,
) -> str:
return f"{base_model}/{model_type}/{model_name}"
# In 3.11, the behavior of (str,enum) when interpolated into a
# string has changed. The next two lines are defensive.
base_model = BaseModelType(base_model)
model_type = ModelType(model_type)
return f"{base_model.value}/{model_type.value}/{model_name}"
@classmethod
def parse_key(cls, model_key: str) -> Tuple[str, BaseModelType, ModelType]:

42
pyproject.toml
View File

@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
[project]
name = "InvokeAI"
description = "An implementation of Stable Diffusion which provides various new features and options to aid the image generation process"
requires-python = ">=3.9, <3.11"
requires-python = ">=3.9, <3.12"
readme = { content-type = "text/markdown", file = "README.md" }
keywords = ["stable-diffusion", "AI"]
dynamic = ["version"]
@ -32,16 +32,16 @@ classifiers = [
'Topic :: Scientific/Engineering :: Image Processing',
]
dependencies = [
"accelerate~=0.16",
"accelerate~=0.21.0",
"albumentations",
"click",
"clip_anytorch", # replacing "clip @ https://github.com/openai/CLIP/archive/eaa22acb90a5876642d0507623e859909230a52d.zip",
"compel==2.0.0",
"clip_anytorch", # replacing "clip @ https://github.com/openai/CLIP/archive/eaa22acb90a5876642d0507623e859909230a52d.zip",
"compel~=2.0.0",
"controlnet-aux>=0.0.6",
"timm==0.6.13", # needed to override timm latest in controlnet_aux, see https://github.com/isl-org/ZoeDepth/issues/26
"timm==0.6.13", # needed to override timm latest in controlnet_aux, see https://github.com/isl-org/ZoeDepth/issues/26
"datasets",
"diffusers[torch]~=0.18.1",
"dnspython==2.2.1",
"diffusers[torch]~=0.18.2",
"dnspython~=2.4.0",
"dynamicprompts",
"easing-functions",
"einops",
@ -54,37 +54,37 @@ dependencies = [
"flask_cors==3.0.10",
"flask_socketio==5.3.0",
"flaskwebgui==1.0.3",
"gfpgan==1.3.8",
"huggingface-hub>=0.11.1",
"invisible-watermark>=0.2.0", # needed to install SDXL base and refiner using their repo_ids
"invisible-watermark~=0.2.0", # needed to install SDXL base and refiner using their repo_ids
"matplotlib", # needed for plotting of Penner easing functions
"mediapipe", # needed for "mediapipeface" controlnet model
"npyscreen",
"numpy<1.24",
"numpy==1.24.4",
"omegaconf",
"opencv-python",
"picklescan",
"pillow",
"prompt-toolkit",
"pympler==1.0.1",
"pydantic==1.10.10",
"pympler~=1.0.1",
"pypatchmatch",
'pyperclip',
"pyreadline3",
"python-multipart==0.0.6",
"pytorch-lightning==1.7.7",
"python-multipart",
"pytorch-lightning",
"realesrgan",
"requests==2.28.2",
"requests~=2.28.2",
"rich~=13.3",
"safetensors~=0.3.0",
"scikit-image>=0.19",
"scikit-image~=0.21.0",
"send2trash",
"test-tube>=0.7.5",
"torch~=2.0.0",
"torchvision>=0.14.1",
"torchmetrics==0.11.4",
"torchsde==0.2.5",
"test-tube~=0.7.5",
"torch~=2.0.1",
"torchvision~=0.15.2",
"torchmetrics~=1.0.1",
"torchsde~=0.2.5",
"transformers~=4.31.0",
"uvicorn[standard]==0.21.1",
"uvicorn[standard]~=0.21.1",
"windows-curses; sys_platform=='win32'",
]

10
scripts/probe-model.py
View File

@ -1,8 +1,16 @@
#!/bin/env python
import argparse
import sys
from pathlib import Path
from invokeai.backend.model_management.model_probe import ModelProbe
info = ModelProbe().probe(Path(sys.argv[1]))
parser = argparse.ArgumentParser(description="Probe model type")
parser.add_argument(
"model_path",
type=Path,
)
args = parser.parse_args()
info = ModelProbe().probe(args.model_path)
print(info)