Merge branch 'development' into patch-1

README.md

@@ -46,8 +46,11 @@ improvements and bug fixes.
 # Table of Contents
 
 1. [Major Features](#features)
-2. [Changelog](#latest)
+2. [Changelog](#latest-changes)
 3. [Installation](#installation)
+   1. [Linux](#linux)
+   1. [Windows](#windows)
+   1. [MacOS](README-Mac-MPS.md)
 4. [Troubleshooting](#troubleshooting)
 5. [Support](#support)
 

VARIATIONS.md

@@ -48,12 +48,12 @@ variation.
 dream> "prompt" -n6 -S3357757885 -v0.2
 ...
 Outputs:
-./outputs/Xena/000002.784039624.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 784039624,0.2 -S3357757885
+./outputs/Xena/000002.784039624.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 784039624:0.2 -S3357757885
-./outputs/Xena/000002.3647897225.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225,0.2 -S3357757885
+./outputs/Xena/000002.3647897225.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.2 -S3357757885
-./outputs/Xena/000002.917731034.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 917731034,0.2 -S3357757885
+./outputs/Xena/000002.917731034.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 917731034:0.2 -S3357757885
-./outputs/Xena/000002.4116285959.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 4116285959,0.2 -S3357757885
+./outputs/Xena/000002.4116285959.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 4116285959:0.2 -S3357757885
-./outputs/Xena/000002.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1614299449,0.2 -S3357757885
+./outputs/Xena/000002.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1614299449:0.2 -S3357757885
-./outputs/Xena/000002.1335553075.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1335553075,0.2 -S3357757885
+./outputs/Xena/000002.1335553075.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 1335553075:0.2 -S3357757885
 ~~~
 
 Note that the output for each image has a -V option giving the
@@ -78,7 +78,7 @@ this to work.
 ~~~
 dream> "prompt"  -S3357757885 -V3647897225,0.1;1614299449,0.1
 Outputs:
-./outputs/Xena/000003.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225,0.1;1614299449,0.1 -S3357757885
+./outputs/Xena/000003.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1 -S3357757885
 ~~~
 
 Here we are providing equal weights (0.1 and 0.1) for both the
@@ -95,12 +95,12 @@ strength) options. Note that we use -n6 to generate 6 variations:
 ~~~~
 dream> "prompt" -S3357757885 -V3647897225,0.1;1614299449,0.1 -v0.05 -n6
 Outputs:
-./outputs/Xena/000004.3279757577.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225,0.1;1614299449,0.1;3279757577,0.05 -S3357757885
+./outputs/Xena/000004.3279757577.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,3279757577:0.05 -S3357757885
-./outputs/Xena/000004.2853129515.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225,0.1;1614299449,0.1;2853129515,0.05 -S3357757885
+./outputs/Xena/000004.2853129515.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2853129515:0.05 -S3357757885
-./outputs/Xena/000004.3747154981.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225,0.1;1614299449,0.1;3747154981,0.05 -S3357757885
+./outputs/Xena/000004.3747154981.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,3747154981:0.05 -S3357757885
-./outputs/Xena/000004.2664260391.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225,0.1;1614299449,0.1;2664260391,0.05 -S3357757885
+./outputs/Xena/000004.2664260391.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2664260391:0.05 -S3357757885
-./outputs/Xena/000004.1642517170.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225,0.1;1614299449,0.1;1642517170,0.05 -S3357757885
+./outputs/Xena/000004.1642517170.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,1642517170:0.05 -S3357757885
-./outputs/Xena/000004.2183375608.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225,0.1;1614299449,0.1;2183375608,0.05 -S3357757885
+./outputs/Xena/000004.2183375608.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2183375608:0.05 -S3357757885
 ~~~~
 
 This produces six images, all slight variations on the combination of

ldm/dream/pngwriter.py

@@ -70,10 +70,10 @@ class PromptFormatter:
         if opt.upscale:
             switches.append(f'-U {" ".join([str(u) for u in opt.upscale])}')
         if opt.variation_amount > 0:
-            switches.append(f'-v {opt.variation_amount}')
+            switches.append(f'-v{opt.variation_amount}')
         if opt.with_variations:
-            formatted_variations = ';'.join(f'{seed},{weight}' for seed, weight in opt.with_variations)
+            formatted_variations = ','.join(f'{seed}:{weight}' for seed, weight in opt.with_variations)
-            switches.append(f'-V {formatted_variations}')
+            switches.append(f'-V{formatted_variations}')
         if t2i.full_precision:
             switches.append('-F')
         return ' '.join(switches)

ldm/simplet2i.py

@@ -151,7 +151,7 @@ class T2I:
         self.grid                     = grid
         self.ddim_eta                 = ddim_eta
         self.precision                = precision
-        self.full_precision           = full_precision
+        self.full_precision           = True if choose_torch_device() == 'mps' else full_precision
         self.strength                 = strength
         self.embedding_path           = embedding_path
         self.device_type              = device_type
@@ -286,7 +286,7 @@ class T2I:
                 0.0 <= variation_amount <= 1.0
         ), '-v --variation_amount must be in [0.0, 1.0]'
 
-        if len(with_variations) > 0:
+        if len(with_variations) > 0 or variation_amount > 1.0:
             assert seed is not None,\
                 'seed must be specified when using with_variations'
             if variation_amount == 0.0:
@@ -324,6 +324,7 @@ class T2I:
                         self.model.encode_first_stage(init_image)
                     ) # move to latent space
 
+                print(f' DEBUG: seed at make_image time ={seed}')
                 make_image = self._img2img(
                     prompt,
                     steps=steps,
@@ -346,25 +347,15 @@ class T2I:
                     callback=step_callback,
                 )
 
-            def get_noise():
-                if init_img:
-                    return torch.randn_like(init_latent, device=self.device)
-                else:
-                    return torch.randn([1,
-                        self.latent_channels,
-                        height // self.downsampling_factor,
-                        width  // self.downsampling_factor],
-                        device=self.device)
-
             initial_noise = None
             if variation_amount > 0 or len(with_variations) > 0:
                 # use fixed initial noise plus random noise per iteration
                 seed_everything(seed)
-                initial_noise = get_noise()
+                initial_noise = self._get_noise(init_img,width,height)
                 for v_seed, v_weight in with_variations:
                     seed = v_seed
                     seed_everything(seed)
-                    next_noise = get_noise()
+                    next_noise = self._get_noise(init_img,width,height)
                     initial_noise = self.slerp(v_weight, initial_noise, next_noise)
                 if variation_amount > 0:
                     random.seed() # reset RNG to an actually random state, so we can get a random seed for variations
@@ -376,14 +367,17 @@ class T2I:
                     x_T = None
                     if variation_amount > 0:
                         seed_everything(seed)
-                        target_noise = get_noise()
+                        target_noise = self._get_noise(init_img,width,height)
                         x_T = self.slerp(variation_amount, initial_noise, target_noise)
                     elif initial_noise is not None:
                         # i.e. we specified particular variations
                         x_T = initial_noise
                     else:
                         seed_everything(seed)
+                        if self.device.type == 'mps':
+                            x_T = self._get_noise(init_img,width,height)
                         # make_image will do the equivalent of get_noise itself
+                    print(f' DEBUG: seed at make_image() invocation time ={seed}')
                     image = make_image(x_T)
                     results.append([image, seed])
                     if image_callback is not None:
@@ -611,6 +605,27 @@ class T2I:
 
         return self.model
 
+    # returns a tensor filled with random numbers from a normal distribution
+    def _get_noise(self,init_img,width,height):
+        if init_img:
+            if self.device.type == 'mps':
+                return torch.randn_like(init_latent, device='cpu').to(self.device)
+            else:
+                return torch.randn_like(init_latent, device=self.device)
+        else:
+            if self.device.type == 'mps':
+                return torch.randn([1,
+                                    self.latent_channels,
+                                    height // self.downsampling_factor,
+                                    width  // self.downsampling_factor],
+                                   device='cpu').to(self.device)
+            else:
+                return torch.randn([1,
+                                    self.latent_channels,
+                                    height // self.downsampling_factor,
+                                    width  // self.downsampling_factor],
+                                   device=self.device)
+
     def _set_sampler(self):
         msg = f'>> Setting Sampler to {self.sampler_name}'
         if self.sampler_name == 'plms':

scripts/dream.py

@@ -9,7 +9,6 @@ import sys
 import copy
 import warnings
 import time
-from ldm.dream.devices import choose_torch_device
 import ldm.dream.readline
 from ldm.dream.pngwriter import PngWriter, PromptFormatter
 from ldm.dream.server import DreamServer, ThreadingDreamServer
@@ -99,7 +98,7 @@ def main():
 
     cmd_parser = create_cmd_parser()
     if opt.web:
-        dream_server_loop(t2i)
+        dream_server_loop(t2i, opt.host, opt.port)
     else:
         main_loop(t2i, opt.outdir, opt.prompt_as_dir, cmd_parser, infile)
 
@@ -187,8 +186,8 @@ def main_loop(t2i, outdir, prompt_as_dir, parser, infile):
             # shotgun parsing, woo
             parts = []
             broken = False # python doesn't have labeled loops...
-            for part in opt.with_variations.split(';'):
+            for part in opt.with_variations.split(','):
-                seed_and_weight = part.split(',')
+                seed_and_weight = part.split(':')
                 if len(seed_and_weight) != 2:
                     print(f'could not parse with_variation part "{part}"')
                     broken = True
@@ -310,7 +309,7 @@ def get_next_command(infile=None) -> str: #command string
         print(f'#{command}')
     return command
 
-def dream_server_loop(t2i):
+def dream_server_loop(t2i, host, port):
     print('\n* --web was specified, starting web server...')
     # Change working directory to the stable-diffusion directory
     os.chdir(
@@ -319,9 +318,13 @@ def dream_server_loop(t2i):
 
     # Start server
     DreamServer.model = t2i
-    dream_server = ThreadingDreamServer(("0.0.0.0", 9090))
+    dream_server = ThreadingDreamServer((host, port))
-    print("\nStarted Stable Diffusion dream server!")
+    print(">> Started Stable Diffusion dream server!")
-    print("Point your browser at http://localhost:9090 or use the host's DNS name or IP address.")
+    if host == '0.0.0.0':
+        print(f"Point your browser at http://localhost:{port} or use the host's DNS name or IP address.")
+    else:
+        print(">> Default host address now 127.0.0.1 (localhost). Use --host 0.0.0.0 to bind any address.")
+        print(f">> Point your browser at http://{host}:{port}.")
 
     try:
         dream_server.serve_forever()
@@ -387,9 +390,7 @@ def create_argv_parser():
         '--full_precision',
         dest='full_precision',
         action='store_true',
-        help='Use slower full precision math for calculations',
+        help='Use more memory-intensive full precision math for calculations',
-        # MPS only functions with full precision, see https://github.com/lstein/stable-diffusion/issues/237
-        default=choose_torch_device() == 'mps',
     )
     parser.add_argument(
         '-g',
@@ -457,6 +458,18 @@ def create_argv_parser():
         action='store_true',
         help='Start in web server mode.',
     )
+    parser.add_argument(
+        '--host',
+        type=str,
+        default='127.0.0.1',
+        help='Web server: Host or IP to listen on. Set to 0.0.0.0 to accept traffic from other devices on your network.'
+    )
+    parser.add_argument(
+        '--port',
+        type=int,
+        default='9090',
+        help='Web server: Port to listen on'
+    )
     parser.add_argument(
         '--weights',
         default='model',
@@ -598,7 +611,7 @@ def create_cmd_parser():
         '--with_variations',
         default=None,
         type=str,
-        help='list of variations to apply, in the format `seed,weight;seed,weight;...'
+        help='list of variations to apply, in the format `seed:weight,seed:weight,...'
     )
     return parser