Merge branch 'main' into feat/import-with-vae

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:
@@ -902,7 +903,7 @@ 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/ckpt_to_diffuser.py

@@ -21,7 +21,7 @@ import os
 import re
 import torch
 from pathlib import Path
-from ldm.invoke.globals import Globals
+from ldm.invoke.globals import Globals, global_cache_dir
 from safetensors.torch import load_file
 
 try:
@@ -637,7 +637,7 @@ def convert_ldm_bert_checkpoint(checkpoint, config):
 
 
 def convert_ldm_clip_checkpoint(checkpoint):
-    text_model = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14")
+    text_model = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14",cache_dir=global_cache_dir('hub'))
 
     keys = list(checkpoint.keys())
 
@@ -677,7 +677,8 @@ textenc_pattern = re.compile("|".join(protected.keys()))
 
 
 def convert_paint_by_example_checkpoint(checkpoint):
-    config = CLIPVisionConfig.from_pretrained("openai/clip-vit-large-patch14")
+    cache_dir = global_cache_dir('hub')
+    config = CLIPVisionConfig.from_pretrained("openai/clip-vit-large-patch14",cache_dir=cache_dir)
     model = PaintByExampleImageEncoder(config)
 
     keys = list(checkpoint.keys())
@@ -744,7 +745,8 @@ def convert_paint_by_example_checkpoint(checkpoint):
 
 
 def convert_open_clip_checkpoint(checkpoint):
-    text_model = CLIPTextModel.from_pretrained("stabilityai/stable-diffusion-2", subfolder="text_encoder")
+    cache_dir=global_cache_dir('hub')
+    text_model = CLIPTextModel.from_pretrained("stabilityai/stable-diffusion-2", subfolder="text_encoder", cache_dir=cache_dir)
 
     keys = list(checkpoint.keys())
 
@@ -795,6 +797,7 @@ def convert_ckpt_to_diffuser(checkpoint_path:str,
                              ):
 
     checkpoint = load_file(checkpoint_path) if Path(checkpoint_path).suffix == '.safetensors' else torch.load(checkpoint_path)
+    cache_dir = global_cache_dir('hub')
 
     # Sometimes models don't have the global_step item
     if "global_step" in checkpoint:
@@ -904,7 +907,7 @@ def convert_ckpt_to_diffuser(checkpoint_path:str,
 
     if model_type == "FrozenOpenCLIPEmbedder":
         text_model = convert_open_clip_checkpoint(checkpoint)
-        tokenizer = CLIPTokenizer.from_pretrained("stabilityai/stable-diffusion-2", subfolder="tokenizer")
+        tokenizer = CLIPTokenizer.from_pretrained("stabilityai/stable-diffusion-2", subfolder="tokenizer",cache_dir=global_cache_dir('diffusers'))
         pipe = StableDiffusionPipeline(
             vae=vae,
             text_encoder=text_model,
@@ -917,8 +920,8 @@ def convert_ckpt_to_diffuser(checkpoint_path:str,
         )
     elif model_type == "PaintByExample":
         vision_model = convert_paint_by_example_checkpoint(checkpoint)
-        tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")
-        feature_extractor = AutoFeatureExtractor.from_pretrained("CompVis/stable-diffusion-safety-checker")
+        tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14",cache_dir=cache_dir)
+        feature_extractor = AutoFeatureExtractor.from_pretrained("CompVis/stable-diffusion-safety-checker",cache_dir=cache_dir)
         pipe = PaintByExamplePipeline(
             vae=vae,
             image_encoder=vision_model,
@@ -929,9 +932,9 @@ def convert_ckpt_to_diffuser(checkpoint_path:str,
         )
     elif model_type in ['FrozenCLIPEmbedder','WeightedFrozenCLIPEmbedder']:
         text_model = convert_ldm_clip_checkpoint(checkpoint)
-        tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14")
-        safety_checker = StableDiffusionSafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker")
-        feature_extractor = AutoFeatureExtractor.from_pretrained("CompVis/stable-diffusion-safety-checker")
+        tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14",cache_dir=cache_dir)
+        safety_checker = StableDiffusionSafetyChecker.from_pretrained("CompVis/stable-diffusion-safety-checker",cache_dir=cache_dir)
+        feature_extractor = AutoFeatureExtractor.from_pretrained("CompVis/stable-diffusion-safety-checker",cache_dir=cache_dir)
         pipe = StableDiffusionPipeline(
             vae=vae,
             text_encoder=text_model,
@@ -944,7 +947,7 @@ def convert_ckpt_to_diffuser(checkpoint_path:str,
     else:
         text_config = create_ldm_bert_config(original_config)
         text_model = convert_ldm_bert_checkpoint(checkpoint, text_config)
-        tokenizer = BertTokenizerFast.from_pretrained("bert-base-uncased")
+        tokenizer = BertTokenizerFast.from_pretrained("bert-base-uncased",cache_dir=cache_dir)
         pipe = LDMTextToImagePipeline(vqvae=vae, bert=text_model, tokenizer=tokenizer, unet=unet, scheduler=scheduler)
 
     pipe.save_pretrained(

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

@@ -27,6 +27,7 @@ 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
@@ -871,11 +872,11 @@ 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: