Merge branch 'main' into lstein-improve-ti-frontend

ldm/invoke/CLI.py

@@ -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')

ldm/invoke/args.py

@@ -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",

ldm/invoke/generator/diffusers_pipeline.py

@@ -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,

ldm/invoke/generator/txt2img2img.py

@@ -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]
 

ldm/invoke/globals.py

@@ -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
 

ldm/invoke/model_manager.py

@@ -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
@@ -827,11 +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:

scripts/configure_invokeai.py

@@ -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)

scripts/textual_inversion_fe.py

@@ -121,6 +121,14 @@ 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:',
@@ -137,6 +145,22 @@ 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:",
@@ -160,22 +184,6 @@ 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
@@ -242,7 +250,7 @@ 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)
@@ -332,6 +340,7 @@ 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: