Small QoL imporvements

.gitignore

@@ -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/

ldm/simplet2i.py

@@ -113,7 +113,8 @@ The vast majority of these arguments default to reasonable values.
                  precision='autocast',
                  full_precision=False,
                  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.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.sampler    = None
         self.latent_diffusion_weights=latent_diffusion_weights
+        self.device = device
         if seed is None:
             self.seed = self._new_seed()
         else:
             self.seed = seed
 
+    @torch.no_grad()
     def txt2img(self,prompt,outdir=None,batch_size=None,iterations=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):
@@ -191,9 +194,7 @@ The vast majority of these arguments default to reasonable values.
 
         # Gawd. Too many levels of indent here. Need to refactor into smaller routines!
         try:
-            with torch.no_grad():
+            with precision_scope(self.device.type), model.ema_scope():
-                with precision_scope("cuda"):
-                    with model.ema_scope():
                 all_samples = list()
                 for n in trange(iterations, desc="Sampling"):
                     seed_everything(seed)
@@ -266,6 +267,7 @@ The vast majority of these arguments default to reasonable values.
         return images
         
     # 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,
                 steps=None,seed=None,grid=None,individual=None,width=None,height=None,
                 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)
         init_image = self._load_img(init_img).to(self.device)
         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
 
         sampler.make_schedule(ddim_num_steps=steps, ddim_eta=ddim_eta, verbose=False)
@@ -334,9 +336,7 @@ The vast majority of these arguments default to reasonable values.
 
         # Gawd. Too many levels of indent here. Need to refactor into smaller routines!
         try:
-            with torch.no_grad():
+            with precision_scope(self.device.type), model.ema_scope():
-                with precision_scope("cuda"):
-                    with model.ema_scope():
                 all_samples = list()
                 for n in trange(iterations, desc="Sampling"):
                     seed_everything(seed)
@@ -429,7 +429,7 @@ The vast majority of these arguments default to reasonable values.
             seed_everything(self.seed)
             try:
                 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)
                 self.model = model.to(self.device)
             except AttributeError:
@@ -458,7 +458,6 @@ The vast majority of these arguments default to reasonable values.
         sd = pl_sd["state_dict"]
         model = instantiate_from_config(config.model)
         m, u = model.load_state_dict(sd, strict=False)
-        model.cuda()
         model.eval()
         if self.full_precision:
             print('Using slower but more accurate full-precision math (--full_precision)')

scripts/dream.py

@@ -57,7 +57,8 @@ def main():
               weights=weights,
               full_precision=opt.full_precision,
               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
@@ -268,6 +269,11 @@ def create_argv_parser():
                         type=str,
                         default="outputs/img-samples",
                         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