updated changelog

Fixed typo in the change log (wrong version #)

README.md

@@ -86,7 +86,16 @@ completely). The default is 0.75, and ranges from 0.25-0.75 give interesting res
 
 ## Changes
 
-* v1.01 (21 August 2022)
+* v1.04 (22 August 2022 - after the drop)
+   * Updated README to reflect installation of the released weights.
+   * Suppressed very noisy and inconsequential warning when loading the frozen CLIP
+   tokenizer.
+
+* v1.03 (22 August 2022)
+   * The original txt2img and img2img scripts from the CompViz repository have been moved into
+     a subfolder named "orig_scripts", to reduce confusion.
+   
+* v1.02 (21 August 2022)
     * A copy of the prompt and all of its switches and options is now stored in the corresponding
     image in a tEXt metadata field named "Dream". You can read the prompt using scripts/images2prompt.py,
     or an image editor that allows you to explore the full metadata.
@@ -142,17 +151,21 @@ After these steps, your command prompt will be prefixed by "(ldm)" as shown abov
 
 7. Now you need to install the weights for the stable diffusion model.
 
-For testing prior to the release of the real weights, you can use an older weight file that produces low-quality images. Create a directory within stable-diffusion named "models/ldm/text2img-large", and use the wget URL downloader tool to copy the weight file into it:
-```
-(ldm) ~/stable-diffusion$ mkdir -p models/ldm/text2img-large
-(ldm) ~/stable-diffusion$ wget -O models/ldm/text2img-large/model.ckpt https://ommer-lab.com/files/latent-diffusion/nitro/txt2img-f8-large/model.ckpt
-```
-For testing with the released weighs, you will do something similar, but with a directory named "models/ldm/stable-diffusion-v1"
+For running with the released weights, you will first need to set up an acount with Hugging Face (https://huggingface.co).
+Use your credentials to log in, and then point browser at https://huggingface.co/CompVis/stable-diffusion-v-1-4-original.
+You may be asked to sign a license agreement at this point.
+
+Click on "Files and versions" near the top of the page, and then click on the file named "sd-v1-4.ckpt". You'll be taken
+to a page that prompts you to click the "download" link. Now save the file somewhere safe on your local machine.
+
+Now run the following commands from within the stable-diffusion directory to point it to the weights file.
+   
 ```
 (ldm) ~/stable-diffusion$ mkdir -p models/ldm/stable-diffusion-v1
-(ldm) ~/stable-diffusion$ wget -O models/ldm/stable-diffusion-v1/model.ckpt <ENTER URL HERE>
+(ldm) ~/stable-diffusion$ ln -sf /path/to/sd-v1-4.ckpt models/ldm/stable-diffusion-v1/model.ckpt
 ```
-These weight files are ~5 GB in size, so downloading may take a while.
+
+The weight file is >4 GB in size, so downloading may take a while.
 
 8. Start generating images!
 ```
@@ -209,15 +222,36 @@ This will install all python requirements and activate the "ldm" environment whi
 ```
 python scripts\preload_models.py
 ```
-This installs two machine learning models that stable diffusion requires.
+
+This installs several machine learning models that stable diffusion
+requires. (Note that this step is required. I created it because some people
+are using GPU systems that are behind a firewall and the models can't be
+downloaded just-in-time)
 
 9. Now you need to install the weights for the big stable diffusion model.
 
-For testing prior to the release of the real weights, create a directory within stable-diffusion named "models\ldm\text2img-large".
+For running with the released weights, you will first need to set up
+an acount with Hugging Face (https://huggingface.co).  Use your
+credentials to log in, and then point browser at
+https://huggingface.co/CompVis/stable-diffusion-v-1-4-original.  You
+may be asked to sign a license agreement at this point.
 
-For testing with the released weights, create a directory within stable-diffusion named "models\ldm\stable-diffusion-v1".
+Click on "Files and versions" near the top of the page, and then click
+on the file named "sd-v1-4.ckpt". You'll be taken to a page that
+prompts you to click the "download" link. Now save the file somewhere
+safe on your local machine.  The weight file is >4 GB in size, so
+downloading may take a while.
 
-Then use a web browser to copy model.ckpt into the appropriate directory. For the text2img-large (pre-release) model, the weights are at https://ommer-lab.com/files/latent-diffusion/nitro/txt2img-f8-large/model.ckpt. Check back here later for the release URL.
+Now run the following commands from **within the stable-diffusion
+directory** to point it to the weights file:
+   
+```
+mkdir -p models/ldm/stable-diffusion-v1
+copy C:\path\to\sd-v1-4.ckpt models\ldm\stable-diffusion-v1\model.ckpt
+```
+
+Instead of copying the file, you may instead create a shortcut within the
+models\ldm\stable-diffusion-v1\ directory that points to it.
 
 10. Start generating images!
 ```
@@ -227,7 +261,7 @@ python scripts\dream.py -l
 # for the post-release weights
 python scripts\dream.py
 ```
-11. Subsequently, to relaunch the script, first activate the Anaconda command window (step 4), run "conda activate ldm" (step 7b), and then launch the dream script (step 10).
+11. Subsequently, to relaunch the script, first activate the Anaconda command window (step 4), enter the stable-diffusion directory (step 6, "cd \path\to\stable-diffusion"), run "conda activate ldm" (step 7b), and then launch the dream script (step 10).
 
 ### Updating to newer versions of the script
 

ldm/modules/encoders/modules.py

@@ -146,8 +146,8 @@ class FrozenCLIPEmbedder(AbstractEncoder):
     """Uses the CLIP transformer encoder for text (from Hugging Face)"""
     def __init__(self, version="openai/clip-vit-large-patch14", device="cuda", max_length=77):
         super().__init__()
-        self.tokenizer = CLIPTokenizer.from_pretrained(version)
-        self.transformer = CLIPTextModel.from_pretrained(version)
+        self.tokenizer = CLIPTokenizer.from_pretrained(version,local_files_only=True)
+        self.transformer = CLIPTextModel.from_pretrained(version,local_files_only=True)
         self.device = device
         self.max_length = max_length
         self.freeze()

scripts/dream.py

@@ -40,7 +40,11 @@ def main():
     sys.path.append('.')
     from pytorch_lightning import logging
     from ldm.simplet2i import T2I
-
+    # these two lines prevent a horrible warning message from appearing
+    # when the frozen CLIP tokenizer is imported
+    import transformers
+    transformers.logging.set_verbosity_error()
+    
     # creating a simple text2image object with a handful of
     # defaults passed on the command line.
     # additional parameters will be added (or overriden) during
@@ -87,6 +91,9 @@ def main_loop(t2i,parser,log):
             break
 
         elements = shlex.split(command)
+        if len(elements)==0:
+            continue
+        
         if elements[0]=='q':  # 
             done = True
             break

scripts/images2prompt.py

@@ -6,6 +6,7 @@ from PIL import Image,PngImagePlugin
 
 if len(sys.argv) < 2:
     print("Usage: file2prompt.py <file1.png> <file2.png> <file3.png>...")
+    print("This script opens up the indicated dream.py-generated PNG file(s) and prints out the prompt used to generate them.")
     exit(-1)
 
 filenames = sys.argv[1:]

scripts/preload_models.py

@@ -2,6 +2,10 @@
 # Before running stable-diffusion on an internet-isolated machine,
 # run this script from one with internet connectivity. The
 # two machines must share a common .cache directory.
+import sys
+import transformers
+
+transformers.logging.set_verbosity_error()
 
 # this will preload the Bert tokenizer fles
 print("preloading bert tokenizer...")
@@ -10,7 +14,19 @@ tokenizer = BertTokenizerFast.from_pretrained("bert-base-uncased")
 print("...success")
 
 # this will download requirements for Kornia
-print("preloading Kornia requirements...")
+print("preloading Kornia requirements (ignore the warnings)...")
 import kornia
 print("...success")
 
+# doesn't work - probably wrong logger
+# logging.getLogger('transformers.tokenization_utils').setLevel(logging.ERROR)
+version='openai/clip-vit-large-patch14'
+
+print('preloading CLIP model (Ignore the warnings)...')
+sys.stdout.flush()
+import clip
+from transformers import CLIPTokenizer, CLIPTextModel
+tokenizer  =CLIPTokenizer.from_pretrained(version)
+transformer=CLIPTextModel.from_pretrained(version)
+print('\n\n...success')
+