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 lstein/xformers-instructions

Browse Source
This commit is contained in:
Lincoln Stein 2023-01-20 17:29:39 -05:00 committed by GitHub
commit 279ffcfe15
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
9 changed files with 90 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/installation/010_INSTALL_AUTOMATED.md
View File

@ -52,7 +52,7 @@ version of InvokeAI with the option to upgrade to experimental versions later.
find python, then open the Python installer again and choose
"Modify" existing installation.
- Installation requires an up to date version of the Microsoft Visual C libraries. Please install the 2015-2022 libraries available here: https://learn.microsoft.com/en-us/cpp/windows/deploying-native-desktop-applications-visual-cpp?view=msvc-170
- Installation requires an up to date version of the Microsoft Visual C libraries. Please install the 2015-2022 libraries available here: https://learn.microsoft.com/en-US/cpp/windows/latest-supported-vc-redist?view=msvc-170
=== "Mac users"

10
ldm/invoke/CLI.py
View File

@ -45,6 +45,7 @@ def main():
Globals.try_patchmatch = args.patchmatch
Globals.always_use_cpu = args.always_use_cpu
Globals.internet_available = args.internet_available and check_internet()
Globals.disable_xformers = not args.xformers
print(f'>> Internet connectivity is {Globals.internet_available}')
if not args.conf:
@ -124,7 +125,7 @@ def main():
# preload the model
try:
gen.load_model()
except KeyError as e:
except KeyError:
pass
except Exception as e:
report_model_error(opt, e)
@ -731,11 +732,6 @@ def del_config(model_name:str, gen, opt, completer):
completer.update_models(gen.model_manager.list_models())
def edit_model(model_name:str, gen, opt, completer):
current_model = gen.model_name
# if model_name == current_model:
# print("** Can't edit the active model. !switch to another model first. **")
# return
manager = gen.model_manager
if not (info := manager.model_info(model_name)):
print(f'** Unknown model {model_name}')
@ -887,7 +883,7 @@ def prepare_image_metadata(
try:
filename = opt.fnformat.format(**wildcards)
except KeyError as e:
print(f'** The filename format contains an unknown key \'{e.args[0]}\'. Will use \'{{prefix}}.{{seed}}.png\' instead')
print(f'** The filename format contains an unknown key \'{e.args[0]}\'. Will use {{prefix}}.{{seed}}.png\' instead')
filename = f'{prefix}.{seed}.png'
except IndexError:
print(f'** The filename format is broken or complete. Will use \'{{prefix}}.{{seed}}.png\' instead')

6
ldm/invoke/args.py
View File

@ -482,6 +482,12 @@ class Args(object):
action='store_true',
help='Force free gpu memory before final decoding',
)
model_group.add_argument(
'--xformers',
action=argparse.BooleanOptionalAction,
default=True,
help='Enable/disable xformers support (default enabled if installed)',
)
model_group.add_argument(
"--always_use_cpu",
dest="always_use_cpu",

3
ldm/invoke/generator/diffusers_pipeline.py
View File

@ -39,6 +39,7 @@ from diffusers.utils.outputs import BaseOutput
from torchvision.transforms.functional import resize as tv_resize
from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
from ldm.invoke.globals import Globals
from ldm.models.diffusion.shared_invokeai_diffusion import InvokeAIDiffuserComponent, ThresholdSettings
from ldm.modules.textual_inversion_manager import TextualInversionManager
@ -306,7 +307,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
textual_inversion_manager=self.textual_inversion_manager
)
if is_xformers_available():
if is_xformers_available() and not Globals.disable_xformers:
self.enable_xformers_memory_efficient_attention()
def image_from_embeddings(self, latents: torch.Tensor, num_inference_steps: int,

4
ldm/invoke/generator/txt2img2img.py
View File

@ -3,6 +3,7 @@ ldm.invoke.generator.txt2img inherits from ldm.invoke.generator
'''
import math
from diffusers.utils.logging import get_verbosity, set_verbosity, set_verbosity_error
from typing import Callable, Optional
import torch
@ -66,6 +67,8 @@ class Txt2Img2Img(Generator):
second_pass_noise = self.get_noise_like(resized_latents)
verbosity = get_verbosity()
set_verbosity_error()
pipeline_output = pipeline.img2img_from_latents_and_embeddings(
resized_latents,
num_inference_steps=steps,
@ -73,6 +76,7 @@ class Txt2Img2Img(Generator):
strength=strength,
noise=second_pass_noise,
callback=step_callback)
set_verbosity(verbosity)
return pipeline.numpy_to_pil(pipeline_output.images)[0]

17
ldm/invoke/globals.py
View File

@ -43,6 +43,9 @@ Globals.always_use_cpu = False
# The CLI will test connectivity at startup time.
Globals.internet_available = True
# Whether to disable xformers
Globals.disable_xformers = False
# whether we are forcing full precision
Globals.full_precision = False
@ -62,11 +65,21 @@ def global_cache_dir(subdir:Union[str,Path]='')->Path:
'''
Returns Path to the model cache directory. If a subdirectory
is provided, it will be appended to the end of the path, allowing
for huggingface-style conventions:
for huggingface-style conventions:
global_cache_dir('diffusers')
global_cache_dir('transformers')
'''
if (home := os.environ.get('HF_HOME')):
home: str = os.getenv('HF_HOME')
if home is None:
home = os.getenv('XDG_CACHE_HOME')
if home is not None:
# Set `home` to $XDG_CACHE_HOME/huggingface, which is the default location mentioned in HuggingFace Hub Client Library.
# See: https://huggingface.co/docs/huggingface_hub/main/en/package_reference/environment_variables#xdgcachehome
home += os.sep + 'huggingface'
if home is not None:
return Path(home,subdir)
else:
return Path(Globals.root,'models',subdir)

47
ldm/invoke/model_manager.py
View File

@ -25,6 +25,7 @@ import torch
import safetensors
import transformers
from diffusers import AutoencoderKL, logging as dlogging
from diffusers.utils.logging import get_verbosity, set_verbosity, set_verbosity_error
from omegaconf import OmegaConf
from omegaconf.dictconfig import DictConfig
from picklescan.scanner import scan_file_path
@ -166,7 +167,7 @@ class ModelManager(object):
# don't include VAEs in listing (legacy style)
if 'config' in stanza and '/VAE/' in stanza['config']:
continue
models[name] = dict()
format = stanza.get('format','ckpt') # Determine Format
@ -183,7 +184,7 @@ class ModelManager(object):
format = format,
status = status,
)
# Checkpoint Config Parse
if format == 'ckpt':
models[name].update(
@ -193,7 +194,7 @@ class ModelManager(object):
width = str(stanza.get('width', 512)),
height = str(stanza.get('height', 512)),
)
# Diffusers Config Parse
if (vae := stanza.get('vae',None)):
if isinstance(vae,DictConfig):
@ -202,14 +203,14 @@ class ModelManager(object):
path = str(vae.get('path',None)),
subfolder = str(vae.get('subfolder',None))
)
if format == 'diffusers':
models[name].update(
vae = vae,
repo_id = str(stanza.get('repo_id', None)),
path = str(stanza.get('path',None)),
)
return models
def print_models(self) -> None:
@ -257,7 +258,7 @@ class ModelManager(object):
assert (clobber or model_name not in omega), f'attempt to overwrite existing model definition "{model_name}"'
omega[model_name] = model_attributes
if 'weights' in omega[model_name]:
omega[model_name]['weights'].replace('\\','/')
@ -554,12 +555,12 @@ class ModelManager(object):
'''
Attempts to install the indicated ckpt file and returns True if successful.
"weights" can be either a path-like object corresponding to a local .ckpt file
"weights" can be either a path-like object corresponding to a local .ckpt file
or a http/https URL pointing to a remote model.
"config" is the model config file to use with this ckpt file. It defaults to
v1-inference.yaml. If a URL is provided, the config will be downloaded.
You can optionally provide a model name and/or description. If not provided,
then these will be derived from the weight file name. If you provide a commit_to_conf
path to the configuration file, then the new entry will be committed to the
@ -572,7 +573,7 @@ class ModelManager(object):
return False
if config_path is None or not config_path.exists():
return False
model_name = model_name or Path(weights).stem
model_description = model_description or f'imported stable diffusion weights file {model_name}'
new_config = dict(
@ -587,7 +588,7 @@ class ModelManager(object):
if commit_to_conf:
self.commit(commit_to_conf)
return True
def autoconvert_weights(
self,
conf_path:Path,
@ -660,7 +661,7 @@ class ModelManager(object):
except Exception as e:
print(f'** Conversion failed: {str(e)}')
traceback.print_exc()
print('done.')
return new_config
@ -756,9 +757,13 @@ class ModelManager(object):
print('** Legacy version <= 2.2.5 model directory layout detected. Reorganizing.')
print('** This is a quick one-time operation.')
from shutil import move, rmtree
# transformer files get moved into the hub directory
hub = models_dir / 'hub'
if cls._is_huggingface_hub_directory_present():
hub = global_cache_dir('hub')
else:
hub = models_dir / 'hub'
os.makedirs(hub, exist_ok=True)
for model in legacy_locations:
source = models_dir / model
@ -771,7 +776,11 @@ class ModelManager(object):
move(source, dest)
# anything else gets moved into the diffusers directory
diffusers = models_dir / 'diffusers'
if cls._is_huggingface_hub_directory_present():
diffusers = global_cache_dir('diffusers')
else:
diffusers = models_dir / 'diffusers'
os.makedirs(diffusers, exist_ok=True)
for root, dirs, _ in os.walk(models_dir, topdown=False):
for dir in dirs:
@ -819,11 +828,11 @@ class ModelManager(object):
return model
# diffusers really really doesn't like us moving a float16 model onto CPU
import logging
logging.getLogger('diffusers.pipeline_utils').setLevel(logging.CRITICAL)
verbosity = get_verbosity()
set_verbosity_error()
model.cond_stage_model.device = 'cpu'
model.to('cpu')
logging.getLogger('pipeline_utils').setLevel(logging.INFO)
set_verbosity(verbosity)
for submodel in ('first_stage_model','cond_stage_model','model'):
try:
@ -962,3 +971,7 @@ class ModelManager(object):
print(f'** Could not load VAE {name_or_path}: {str(deferred_error)}')
return vae
@staticmethod
def _is_huggingface_hub_directory_present() -> bool:
return os.getenv('HF_HOME') is not None or os.getenv('XDG_CACHE_HOME') is not None

5
scripts/configure_invokeai.py
View File

@ -291,7 +291,7 @@ for more information.
Visit https://huggingface.co/settings/tokens to generate a token. (Sign up for an account if needed).
Paste the token below using Ctrl-V on macOS/Linux, or Ctrl-Shift-V or right-click on Windows.
Paste the token below using Ctrl-V on macOS/Linux, or Ctrl-Shift-V or right-click on Windows.
Alternatively press 'Enter' to skip this step and continue.
You may re-run the configuration script again in the future if you do not wish to set the token right now.
''')
@ -676,7 +676,8 @@ def download_weights(opt:dict) -> Union[str, None]:
return
access_token = authenticate()
HfFolder.save_token(access_token)
if access_token is not None:
HfFolder.save_token(access_token)
print('\n** DOWNLOADING WEIGHTS **')
successfully_downloaded = download_weight_datasets(models, access_token, precision=precision)

43
scripts/textual_inversion_fe.py
View File

@ -115,6 +115,14 @@ class textualInversionForm(npyscreen.FormMultiPageAction):
value=self.precisions.index(saved_args.get('mixed_precision','fp16')),
max_height=4,
)
self.num_train_epochs = self.add_widget_intelligent(
npyscreen.TitleSlider,
name='Number of training epochs:',
out_of=1000,
step=50,
lowest=1,
value=saved_args.get('num_train_epochs',100)
)
self.max_train_steps = self.add_widget_intelligent(
npyscreen.TitleSlider,
name='Max Training Steps:',
@ -131,6 +139,22 @@ class textualInversionForm(npyscreen.FormMultiPageAction):
lowest=1,
value=saved_args.get('train_batch_size',8),
)
self.gradient_accumulation_steps = self.add_widget_intelligent(
npyscreen.TitleSlider,
name='Gradient Accumulation Steps (may need to decrease this to resume from a checkpoint):',
out_of=10,
step=1,
lowest=1,
value=saved_args.get('gradient_accumulation_steps',4)
)
self.lr_warmup_steps = self.add_widget_intelligent(
npyscreen.TitleSlider,
name='Warmup Steps:',
out_of=100,
step=1,
lowest=0,
value=saved_args.get('lr_warmup_steps',0),
)
self.learning_rate = self.add_widget_intelligent(
npyscreen.TitleText,
name="Learning Rate:",
@ -154,22 +178,6 @@ class textualInversionForm(npyscreen.FormMultiPageAction):
scroll_exit = True,
value=self.lr_schedulers.index(saved_args.get('lr_scheduler','constant')),
)
self.gradient_accumulation_steps = self.add_widget_intelligent(
npyscreen.TitleSlider,
name='Gradient Accumulation Steps:',
out_of=10,
step=1,
lowest=1,
value=saved_args.get('gradient_accumulation_steps',4)
)
self.lr_warmup_steps = self.add_widget_intelligent(
npyscreen.TitleSlider,
name='Warmup Steps:',
out_of=100,
step=1,
lowest=0,
value=saved_args.get('lr_warmup_steps',0),
)
def initializer_changed(self):
placeholder = self.placeholder_token.value
@ -236,7 +244,7 @@ class textualInversionForm(npyscreen.FormMultiPageAction):
# all the integers
for attr in ('train_batch_size','gradient_accumulation_steps',
'max_train_steps','lr_warmup_steps'):
'num_train_epochs','max_train_steps','lr_warmup_steps'):
args[attr] = int(getattr(self,attr).value)
# the floats (just one)
@ -324,6 +332,7 @@ if __name__ == '__main__':
save_args(args)
try:
print(f'DEBUG: args = {args}')
do_textual_inversion_training(**args)
copy_to_embeddings_folder(args)
except Exception as e: