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

Small QoL imporvements

Browse Source
This commit is contained in:
Benjamin Warner 2022-08-23 12:49:17 -05:00
parent a21156e3e3
commit de1cea92ce
3 changed files with 254 additions and 116 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

133
.gitignore vendored Normal file
View File

@ -0,0 +1,133 @@
# ignore default image save location and model symbolic link
outputs/
models/ldm/stable-diffusion-v1/model.ckpt
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
pip-wheel-metadata/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
.python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/

229
ldm/simplet2i.py
View File

@ -113,7 +113,8 @@ The vast majority of these arguments default to reasonable values.
precision='autocast', precision='autocast',
full_precision=False, full_precision=False,
strength=0.75, # default in scripts/img2img.py strength=0.75, # default in scripts/img2img.py
latent_diffusion_weights=False # just to keep track of this parameter when regenerating prompt latent_diffusion_weights=False, # just to keep track of this parameter when regenerating prompt
device='cuda'
): ):
self.outdir = outdir self.outdir = outdir
self.batch_size = batch_size self.batch_size = batch_size
@ -136,11 +137,13 @@ The vast majority of these arguments default to reasonable values.
self.model = None # empty for now self.model = None # empty for now
self.sampler = None self.sampler = None
self.latent_diffusion_weights=latent_diffusion_weights self.latent_diffusion_weights=latent_diffusion_weights
self.device = device
if seed is None: if seed is None:
self.seed = self._new_seed() self.seed = self._new_seed()
else: else:
self.seed = seed self.seed = seed
@torch.no_grad()
def txt2img(self,prompt,outdir=None,batch_size=None,iterations=None, def txt2img(self,prompt,outdir=None,batch_size=None,iterations=None,
steps=None,seed=None,grid=None,individual=None,width=None,height=None, steps=None,seed=None,grid=None,individual=None,width=None,height=None,
cfg_scale=None,ddim_eta=None,strength=None,init_img=None,skip_normalize=False): cfg_scale=None,ddim_eta=None,strength=None,init_img=None,skip_normalize=False):
@ -191,69 +194,67 @@ The vast majority of these arguments default to reasonable values.
# Gawd. Too many levels of indent here. Need to refactor into smaller routines! # Gawd. Too many levels of indent here. Need to refactor into smaller routines!
try: try:
with torch.no_grad(): with precision_scope(self.device.type), model.ema_scope():
with precision_scope("cuda"): all_samples = list()
with model.ema_scope(): for n in trange(iterations, desc="Sampling"):
all_samples = list() seed_everything(seed)
for n in trange(iterations, desc="Sampling"): for prompts in tqdm(data, desc="data", dynamic_ncols=True):
seed_everything(seed) uc = None
for prompts in tqdm(data, desc="data", dynamic_ncols=True): if cfg_scale != 1.0:
uc = None uc = model.get_learned_conditioning(batch_size * [""])
if cfg_scale != 1.0: if isinstance(prompts, tuple):
uc = model.get_learned_conditioning(batch_size * [""]) prompts = list(prompts)
if isinstance(prompts, tuple):
prompts = list(prompts)
# weighted sub-prompts # weighted sub-prompts
subprompts,weights = T2I._split_weighted_subprompts(prompts[0]) subprompts,weights = T2I._split_weighted_subprompts(prompts[0])
if len(subprompts) > 1: if len(subprompts) > 1:
# i dont know if this is correct.. but it works # i dont know if this is correct.. but it works
c = torch.zeros_like(uc) c = torch.zeros_like(uc)
# get total weight for normalizing # get total weight for normalizing
totalWeight = sum(weights) totalWeight = sum(weights)
# normalize each "sub prompt" and add it # normalize each "sub prompt" and add it
for i in range(0,len(subprompts)): for i in range(0,len(subprompts)):
weight = weights[i] weight = weights[i]
if not skip_normalize: if not skip_normalize:
weight = weight / totalWeight weight = weight / totalWeight
c = torch.add(c,model.get_learned_conditioning(subprompts[i]), alpha=weight) c = torch.add(c,model.get_learned_conditioning(subprompts[i]), alpha=weight)
else: # just standard 1 prompt else: # just standard 1 prompt
c = model.get_learned_conditioning(prompts) c = model.get_learned_conditioning(prompts)
shape = [self.latent_channels, height // self.downsampling_factor, width // self.downsampling_factor] shape = [self.latent_channels, height // self.downsampling_factor, width // self.downsampling_factor]
samples_ddim, _ = sampler.sample(S=steps, samples_ddim, _ = sampler.sample(S=steps,
conditioning=c, conditioning=c,
batch_size=batch_size, batch_size=batch_size,
shape=shape, shape=shape,
verbose=False, verbose=False,
unconditional_guidance_scale=cfg_scale, unconditional_guidance_scale=cfg_scale,
unconditional_conditioning=uc, unconditional_conditioning=uc,
eta=ddim_eta, eta=ddim_eta,
x_T=start_code) x_T=start_code)
x_samples_ddim = model.decode_first_stage(samples_ddim) x_samples_ddim = model.decode_first_stage(samples_ddim)
x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0) x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
if not grid: if not grid:
for x_sample in x_samples_ddim: for x_sample in x_samples_ddim:
x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c') x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
filename = self._unique_filename(outdir,previousname=filename, filename = self._unique_filename(outdir,previousname=filename,
seed=seed,isbatch=(batch_size>1)) seed=seed,isbatch=(batch_size>1))
assert not os.path.exists(filename) assert not os.path.exists(filename)
Image.fromarray(x_sample.astype(np.uint8)).save(filename) Image.fromarray(x_sample.astype(np.uint8)).save(filename)
images.append([filename,seed]) images.append([filename,seed])
else: else:
all_samples.append(x_samples_ddim) all_samples.append(x_samples_ddim)
seeds.append(seed) seeds.append(seed)
image_count += 1 image_count += 1
seed = self._new_seed() seed = self._new_seed()
if grid: if grid:
images = self._make_grid(samples=all_samples, images = self._make_grid(samples=all_samples,
seeds=seeds, seeds=seeds,
batch_size=batch_size, batch_size=batch_size,
iterations=iterations, iterations=iterations,
outdir=outdir) outdir=outdir)
except KeyboardInterrupt: except KeyboardInterrupt:
print('*interrupted*') print('*interrupted*')
print('Partial results will be returned; if --grid was requested, nothing will be returned.') print('Partial results will be returned; if --grid was requested, nothing will be returned.')
@ -266,6 +267,7 @@ The vast majority of these arguments default to reasonable values.
return images return images
# There is lots of shared code between this and txt2img and should be refactored. # There is lots of shared code between this and txt2img and should be refactored.
@torch.no_grad()
def img2img(self,prompt,outdir=None,init_img=None,batch_size=None,iterations=None, def img2img(self,prompt,outdir=None,init_img=None,batch_size=None,iterations=None,
steps=None,seed=None,grid=None,individual=None,width=None,height=None, steps=None,seed=None,grid=None,individual=None,width=None,height=None,
cfg_scale=None,ddim_eta=None,strength=None,skip_normalize=False): cfg_scale=None,ddim_eta=None,strength=None,skip_normalize=False):
@ -312,7 +314,7 @@ The vast majority of these arguments default to reasonable values.
assert os.path.isfile(init_img) assert os.path.isfile(init_img)
init_image = self._load_img(init_img).to(self.device) init_image = self._load_img(init_img).to(self.device)
init_image = repeat(init_image, '1 ... -> b ...', b=batch_size) init_image = repeat(init_image, '1 ... -> b ...', b=batch_size)
with precision_scope("cuda"): with precision_scope(self.device.type):
init_latent = model.get_first_stage_encoding(model.encode_first_stage(init_image)) # move to latent space init_latent = model.get_first_stage_encoding(model.encode_first_stage(init_image)) # move to latent space
sampler.make_schedule(ddim_num_steps=steps, ddim_eta=ddim_eta, verbose=False) sampler.make_schedule(ddim_num_steps=steps, ddim_eta=ddim_eta, verbose=False)
@ -334,63 +336,61 @@ The vast majority of these arguments default to reasonable values.
# Gawd. Too many levels of indent here. Need to refactor into smaller routines! # Gawd. Too many levels of indent here. Need to refactor into smaller routines!
try: try:
with torch.no_grad(): with precision_scope(self.device.type), model.ema_scope():
with precision_scope("cuda"): all_samples = list()
with model.ema_scope(): for n in trange(iterations, desc="Sampling"):
all_samples = list() seed_everything(seed)
for n in trange(iterations, desc="Sampling"): for prompts in tqdm(data, desc="data", dynamic_ncols=True):
seed_everything(seed) uc = None
for prompts in tqdm(data, desc="data", dynamic_ncols=True): if cfg_scale != 1.0:
uc = None uc = model.get_learned_conditioning(batch_size * [""])
if cfg_scale != 1.0: if isinstance(prompts, tuple):
uc = model.get_learned_conditioning(batch_size * [""]) prompts = list(prompts)
if isinstance(prompts, tuple):
prompts = list(prompts)
# weighted sub-prompts # weighted sub-prompts
subprompts,weights = T2I._split_weighted_subprompts(prompts[0]) subprompts,weights = T2I._split_weighted_subprompts(prompts[0])
if len(subprompts) > 1: if len(subprompts) > 1:
# i dont know if this is correct.. but it works # i dont know if this is correct.. but it works
c = torch.zeros_like(uc) c = torch.zeros_like(uc)
# get total weight for normalizing # get total weight for normalizing
totalWeight = sum(weights) totalWeight = sum(weights)
# normalize each "sub prompt" and add it # normalize each "sub prompt" and add it
for i in range(0,len(subprompts)): for i in range(0,len(subprompts)):
weight = weights[i] weight = weights[i]
if not skip_normalize: if not skip_normalize:
weight = weight / totalWeight weight = weight / totalWeight
c = torch.add(c,model.get_learned_conditioning(subprompts[i]), alpha=weight) c = torch.add(c,model.get_learned_conditioning(subprompts[i]), alpha=weight)
else: # just standard 1 prompt else: # just standard 1 prompt
c = model.get_learned_conditioning(prompts) c = model.get_learned_conditioning(prompts)
# encode (scaled latent) # encode (scaled latent)
z_enc = sampler.stochastic_encode(init_latent, torch.tensor([t_enc]*batch_size).to(self.device)) z_enc = sampler.stochastic_encode(init_latent, torch.tensor([t_enc]*batch_size).to(self.device))
# decode it # decode it
samples = sampler.decode(z_enc, c, t_enc, unconditional_guidance_scale=cfg_scale, samples = sampler.decode(z_enc, c, t_enc, unconditional_guidance_scale=cfg_scale,
unconditional_conditioning=uc,) unconditional_conditioning=uc,)
x_samples = model.decode_first_stage(samples) x_samples = model.decode_first_stage(samples)
x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0) x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0)
if not grid: if not grid:
for x_sample in x_samples: for x_sample in x_samples:
x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c') x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
filename = self._unique_filename(outdir,previousname=filename, filename = self._unique_filename(outdir,previousname=filename,
seed=seed,isbatch=(batch_size>1)) seed=seed,isbatch=(batch_size>1))
assert not os.path.exists(filename) assert not os.path.exists(filename)
Image.fromarray(x_sample.astype(np.uint8)).save(filename) Image.fromarray(x_sample.astype(np.uint8)).save(filename)
images.append([filename,seed]) images.append([filename,seed])
else: else:
all_samples.append(x_samples) all_samples.append(x_samples)
seeds.append(seed) seeds.append(seed)
image_count +=1 image_count +=1
seed = self._new_seed() seed = self._new_seed()
if grid: if grid:
images = self._make_grid(samples=all_samples, images = self._make_grid(samples=all_samples,
seeds=seeds, seeds=seeds,
batch_size=batch_size, batch_size=batch_size,
iterations=iterations, iterations=iterations,
outdir=outdir) outdir=outdir)
except KeyboardInterrupt: except KeyboardInterrupt:
print('*interrupted*') print('*interrupted*')
@ -429,7 +429,7 @@ The vast majority of these arguments default to reasonable values.
seed_everything(self.seed) seed_everything(self.seed)
try: try:
config = OmegaConf.load(self.config) config = OmegaConf.load(self.config)
self.device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu") self.device = torch.device(self.device) if torch.cuda.is_available() else torch.device("cpu")
model = self._load_model_from_config(config,self.weights) model = self._load_model_from_config(config,self.weights)
self.model = model.to(self.device) self.model = model.to(self.device)
except AttributeError: except AttributeError:
@ -458,7 +458,6 @@ The vast majority of these arguments default to reasonable values.
sd = pl_sd["state_dict"] sd = pl_sd["state_dict"]
model = instantiate_from_config(config.model) model = instantiate_from_config(config.model)
m, u = model.load_state_dict(sd, strict=False) m, u = model.load_state_dict(sd, strict=False)
model.cuda()
model.eval() model.eval()
if self.full_precision: if self.full_precision:
print('Using slower but more accurate full-precision math (--full_precision)') print('Using slower but more accurate full-precision math (--full_precision)')

8
scripts/dream.py
View File

@ -57,7 +57,8 @@ def main():
weights=weights, weights=weights,
full_precision=opt.full_precision, full_precision=opt.full_precision,
config=config, config=config,
latent_diffusion_weights=opt.laion400m # this is solely for recreating the prompt latent_diffusion_weights=opt.laion400m, # this is solely for recreating the prompt
device=opt.device
) )
# make sure the output directory exists # make sure the output directory exists
@ -268,6 +269,11 @@ def create_argv_parser():
type=str, type=str,
default="outputs/img-samples", default="outputs/img-samples",
help="directory in which to place generated images and a log of prompts and seeds") help="directory in which to place generated images and a log of prompts and seeds")
parser.add_argument('--device',
'-d',
type=str,
default="cuda",
help="device to run stable diffusion on. defaults to cuda `torch.cuda.current_device()` if avalible")
return parser return parser