fixed filenames

README.md

@@ -86,6 +86,26 @@ completely). The default is 0.75, and ranges from 0.25-0.75 give interesting res
 
 ## Changes
 
+* v1.05 (22 August 2022 - after the drop)
+   * Filenames now use the following formats:
+       000010.95183149.png      -- Two files produced by the same command (e.g. -n2),
+       000010.26742632.png      -- distinguished by a different seed.
+
+       000011.455191342.01.png  -- Two files produced by the same command using
+       000011.455191342.02.png  -- a batch size>1 (e.g. -b2). They have the same seed.
+
+       000011.4160627868.grid#1-4.png  -- a grid of four images (-g); the whole grid can
+                                          be regenerated with the indicated key
+
+    * It should no longer be possible for one image to overwrite another
+    * You can use the "cd" and "pwd" commands at the dream> prompt to set and retrieve
+      the path of the output directory.
+     
+* 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.
@@ -105,6 +125,8 @@ completely). The default is 0.75, and ranges from 0.25-0.75 give interesting res
 
 ## Installation
 
+There are separate installation walkthroughs for [Linux/Mac](#linuxmac) and [Windows](#windows).
+
 ### Linux/Mac
 
 1. You will need to install the following prerequisites if they are not already available. Use your
@@ -144,19 +166,26 @@ After these steps, your command prompt will be prefixed by "(ldm)" as shown abov
 (ldm) ~/stable-diffusion$ python3 scripts/preload_models.py
 ```
 
+Note that this step is necessary because I modified the original
+just-in-time model loading scheme to allow the script to work on GPU
+machines that are not internet connected. See [Workaround for machines with limited internet connectivity](#workaround-for-machines-with-limited-internet-connectivity)
+
 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 your 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. Save the file somewhere safe on your local machine.
+
+Now run the following commands from within the stable-diffusion directory. This will create a symbolic
+link from the stable-diffusion model.ckpt file, to the true location of the sd-v1-4.ckpt 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.
 
 8. Start generating images!
 ```
@@ -172,7 +201,7 @@ These weight files are ~5 GB in size, so downloading may take a while.
 9. Subsequently, to relaunch the script, be sure to run "conda activate ldm" (step 5, second command), enter the "stable-diffusion" 
 directory, and then launch the dream script (step 8). If you forget to activate the ldm environment, the script will fail with multiple ModuleNotFound errors.
 
-### Updating to newer versions of the script
+#### Updating to newer versions of the script
 
 This distribution is changing rapidly. If you used the "git clone" method (step 5) to download the stable-diffusion directory, then to update to the latest and greatest version, launch the Anaconda window, enter "stable-diffusion", and type:
 ```
@@ -213,15 +242,37 @@ 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 your 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 copy the weights file to the right place:
+   
+```
+mkdir -p models/ldm/stable-diffusion-v1
+copy C:\path\to\sd-v1-4.ckpt models\ldm\stable-diffusion-v1\model.ckpt
+```
+Please replace "C:\path\to\sd-v1.4.ckpt" with the correct path to wherever
+you stashed this file. If you prefer not to copy or move the .ckpt file, 
+you may instead create a shortcut to it from within
+"models\ldm\stable-diffusion-v1\".
 
 10. Start generating images!
 ```
@@ -233,7 +284,7 @@ python scripts\dream.py
 ```
 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
+#### Updating to newer versions of the script
 
 This distribution is changing rapidly. If you used the "git clone" method (step 5) to download the stable-diffusion directory, then to update to the latest and greatest version, launch the Anaconda window, enter "stable-diffusion", and type:
 ```

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()

ldm/simplet2i.py

@@ -60,6 +60,7 @@ from torch import autocast
 from contextlib import contextmanager, nullcontext
 import time
 import math
+import re
 
 from ldm.util import instantiate_from_config
 from ldm.models.diffusion.ddim     import DDIMSampler
@@ -171,7 +172,6 @@ The vast majority of these arguments default to reasonable values.
 
         # make directories and establish names for the output files
         os.makedirs(outdir, exist_ok=True)
-        base_count = len(os.listdir(outdir))-1
 
         start_code = None
         if self.fixed_code:
@@ -185,7 +185,7 @@ The vast majority of these arguments default to reasonable values.
         sampler         = self.sampler
         images = list()
         seeds  = list()
-
+        filename = None
         tic    = time.time()
         
         with torch.no_grad():
@@ -218,10 +218,11 @@ The vast majority of these arguments default to reasonable values.
                             if not grid:
                                 for x_sample in x_samples_ddim:
                                     x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
-                                    filename = os.path.join(outdir, f"{base_count:05}.png")
+                                    filename = self._unique_filename(outdir,previousname=filename,
+                                                                     seed=seed,isbatch=(batch_size>1))
+                                    assert not os.path.exists(filename)
                                     Image.fromarray(x_sample.astype(np.uint8)).save(filename)
                                     images.append([filename,seed])
-                                    base_count += 1
                             else:
                                 all_samples.append(x_samples_ddim)
                                 seeds.append(seed)
@@ -283,7 +284,6 @@ The vast majority of these arguments default to reasonable values.
 
         # make directories and establish names for the output files
         os.makedirs(outdir, exist_ok=True)
-        base_count = len(os.listdir(outdir))-1
 
         assert os.path.isfile(init_img)
         init_image = self._load_img(init_img).to(self.device)
@@ -304,7 +304,8 @@ The vast majority of these arguments default to reasonable values.
 
         images = list()
         seeds  = list()
-
+        filename = None
+        
         tic    = time.time()
         
         with torch.no_grad():
@@ -333,10 +334,10 @@ The vast majority of these arguments default to reasonable values.
                             if not grid:
                                 for x_sample in x_samples:
                                     x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
-                                    filename = os.path.join(outdir, f"{base_count:05}.png")
+                                    filename = self._unique_filename(outdir,filename,seed=seed,isbatch=(batch_size>1))
+                                    assert not os.path.exists(filename)
                                     Image.fromarray(x_sample.astype(np.uint8)).save(filename)
                                     images.append([filename,seed])
-                                    base_count += 1
                             else:
                                 all_samples.append(x_samples)
                                 seeds.append(seed)
@@ -357,7 +358,6 @@ The vast majority of these arguments default to reasonable values.
 
     def _make_grid(self,samples,seeds,batch_size,iterations,outdir):
         images = list()
-        base_count = len(os.listdir(outdir))-1
         n_rows = batch_size if batch_size>1 else int(math.sqrt(batch_size * iterations))
         # save as grid
         grid = torch.stack(samples, 0)
@@ -366,7 +366,7 @@ The vast majority of these arguments default to reasonable values.
 
         # to image
         grid = 255. * rearrange(grid, 'c h w -> h w c').cpu().numpy()
-        filename = os.path.join(outdir, f"{base_count:05}.png")
+        filename = self._unique_filename(outdir,seed=seeds[0],grid_count=batch_size*iterations)
         Image.fromarray(grid.astype(np.uint8)).save(filename)
         for s in seeds:
             images.append([filename,s])
@@ -430,3 +430,40 @@ The vast majority of these arguments default to reasonable values.
         image = image[None].transpose(0, 3, 1, 2)
         image = torch.from_numpy(image)
         return 2.*image - 1.
+
+    def _unique_filename(self,outdir,previousname=None,seed=0,isbatch=False,grid_count=None):
+        revision = 1
+
+        if previousname is None:
+            # count up until we find an unfilled slot
+            dir_list  = [a.split('.',1)[0] for a in os.listdir(outdir)]
+            uniques   = dict.fromkeys(dir_list,True)
+            basecount = 1
+            while f'{basecount:06}' in uniques:
+                basecount += 1
+            if grid_count is not None:
+                grid_label = f'grid#1-{grid_count}'
+                filename = f'{basecount:06}.{seed}.{grid_label}.png'
+            elif isbatch:
+                filename = f'{basecount:06}.{seed}.01.png'
+            else:
+                filename = f'{basecount:06}.{seed}.png'
+            
+            return os.path.join(outdir,filename)
+
+        else:
+            previousname = os.path.basename(previousname)
+            x = re.match('^(\d+)\..*\.png',previousname)
+            if not x:
+                return self._unique_filename(outdir,previousname,seed)
+
+            basecount = int(x.groups()[0])
+            series = 0 
+            finished = False
+            while not finished:
+                series += 1
+                filename = f'{basecount:06}.{seed}.png'
+                if isbatch or os.path.exists(os.path.join(outdir,filename)):
+                    filename = f'{basecount:06}.{seed}.{series:02}.png'
+                finished = not os.path.exists(os.path.join(outdir,filename))
+            return os.path.join(outdir,filename)

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
@@ -66,9 +70,9 @@ def main():
     # preload the model
     if not debugging:
         t2i.load_model()
-    print("\n* Initialization done! Awaiting your command (-h for help, q to quit)...")
+    print("\n* Initialization done! Awaiting your command (-h for help, 'q' to quit, 'cd' to change output dir, 'pwd' to print output dir)...")
 
-    log_path   = os.path.join(opt.outdir,"dream_log.txt")
+    log_path   = os.path.join(opt.outdir,'..','dream_log.txt')
     with open(log_path,'a') as log:
         cmd_parser = create_cmd_parser()
         main_loop(t2i,cmd_parser,log)
@@ -86,10 +90,31 @@ def main_loop(t2i,parser,log):
             done = True
             break
 
-        elements = shlex.split(command)
-        if elements[0]=='q':  # 
+        try:
+            elements = shlex.split(command)
+        except ValueError as e:
+            print(str(e))
+            continue
+        
+        if len(elements)==0:
+            continue
+        
+        if elements[0]=='q':
             done = True
             break
+
+        if elements[0]=='cd' and len(elements)>1:
+            if os.path.exists(elements[1]):
+                print(f"setting image output directory to {elements[1]}")
+                t2i.outdir=elements[1]
+            else:
+                print(f"directory {elements[1]} does not exist")
+            continue
+
+        if elements[0]=='pwd':
+            print(f"current output directory is {t2i.outdir}")
+            continue
+        
         if elements[0].startswith('!dream'): # in case a stored prompt still contains the !dream command
             elements.pop(0)
             
@@ -126,6 +151,10 @@ def main_loop(t2i,parser,log):
         except KeyboardInterrupt:
             print('*interrupted*')
             continue
+        except RuntimeError as e:
+            print(str(e))
+            continue
+            
 
     print("goodbye!")
 
@@ -140,7 +169,13 @@ def write_log_message(t2i,opt,results,logfile):
     img_num    = 1
     batch_size = opt.batch_size or t2i.batch_size
     seenit     = {}
-    
+
+    seeds = [a[1] for a in results]
+    if batch_size > 1:
+        seeds = f"(seeds for each batch row: {seeds})"
+    else:
+        seeds = f"(seeds for individual images: {seeds})"
+
     for r in results:
         seed = r[1]
         log_message = (f'{r[0]}: {prompt_str} -S{seed}')
@@ -159,7 +194,10 @@ def write_log_message(t2i,opt,results,logfile):
         if r[0] not in seenit:
             seenit[r[0]] = True
             try:
-                _write_prompt_to_png(r[0],f'{prompt_str} -S{seed}')
+                if opt.grid:
+                    _write_prompt_to_png(r[0],f'{prompt_str} -g -S{seed} {seeds}')
+                else:
+                    _write_prompt_to_png(r[0],f'{prompt_str} -S{seed}')
             except FileNotFoundError:
                 print(f"Could not open file '{r[0]}' for reading")
 
@@ -237,7 +275,8 @@ def create_cmd_parser():
 
 if readline_available:
     def setup_readline():
-        readline.set_completer(Completer(['--steps','-s','--seed','-S','--iterations','-n','--batch_size','-b',
+        readline.set_completer(Completer(['cd','pwd',
+                                          '--steps','-s','--seed','-S','--iterations','-n','--batch_size','-b',
                                           '--width','-W','--height','-H','--cfg_scale','-C','--grid','-g',
                                           '--individual','-i','--init_img','-I','--strength','-f']).complete)
         readline.set_completer_delims(" ")
@@ -259,8 +298,13 @@ if readline_available:
             return
 
         def complete(self,text,state):
-            if text.startswith('-I') or text.startswith('--init_img'):
-                return self._image_completions(text,state)
+            buffer = readline.get_line_buffer()
+            
+            if text.startswith(('-I','--init_img')):
+                return self._path_completions(text,state,('.png'))
+
+            if buffer.strip().endswith('cd') or text.startswith(('.','/')):
+                return self._path_completions(text,state,())
 
             response = None
             if state == 0:
@@ -280,12 +324,14 @@ if readline_available:
                 response = None
             return response
 
-        def _image_completions(self,text,state):
+        def _path_completions(self,text,state,extensions):
             # get the path so far
             if text.startswith('-I'):
                 path = text.replace('-I','',1).lstrip()
             elif text.startswith('--init_img='):
                 path = text.replace('--init_img=','',1).lstrip()
+            else:
+                path = text
 
             matches  = list()
 
@@ -302,7 +348,7 @@ if readline_available:
                     if full_path.startswith(path):
                         if os.path.isdir(full_path):
                             matches.append(os.path.join(os.path.dirname(text),n)+'/')
-                        elif n.endswith('.png'):
+                        elif n.endswith(extensions):
                             matches.append(os.path.join(os.path.dirname(text),n))
 
             try:
@@ -310,7 +356,6 @@ if readline_available:
             except IndexError:
                 response = None
             return response
-        
 
 if __name__ == "__main__":
     main()

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')
+