Merge branch 'development' of github.com:invoke-ai/InvokeAI into development

Author: lstein

docs/features/CLI.md

@@ -85,6 +85,7 @@ overridden on a per-prompt basis (see [List of prompt arguments](#list-of-prompt
 | `--from_file <path>`                      |                                           | `None`                                         | Read list of prompts from a file. Use `-` to read from standard input                                |
 | `--model <modelname>`                     |                                           | `stable-diffusion-1.4`                         | Loads model specified in configs/models.yaml. Currently one of "stable-diffusion-1.4" or "laion400m" |
 | `--full_precision`                        | `-F`                                      | `False`                                        | Run in slower full-precision mode. Needed for Macintosh M1/M2 hardware and some older video cards.   |
+| `--png_compression <0-9>`                 | `-z<0-9>`                                 |  6                                             | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
 | `--web`                                   |                                           | `False`                                        | Start in web server mode                                                                             |
 | `--host <ip addr>`                        |                                           | `localhost`                                    | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any.                |
 | `--port <port>`                           |                                           | `9090`                                         | Which port web server should listen for requests on.                                                 |
@@ -153,6 +154,7 @@ Here are the invoke> command that apply to txt2img:
 | --seed <int>       | -S<int>   | None                | Set the random seed for the next series of images. This can be used to recreate an image generated previously.|
 | --sampler <sampler>| -A<sampler>| k_lms              | Sampler to use. Use -h to get list of available samplers. |
 | --hires_fix        |           |                     | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution |
+| `--png_compression <0-9>` | `-z<0-9>` |  6           | Select level of compression for output files, from 0 (no compression) to 9 (max compression)         |
 | --grid             | -g        | False               | Turn on grid mode to return a single image combining all the images generated by this prompt |
 | --individual       | -i        | True                | Turn off grid mode (deprecated; leave off --grid instead) |
 | --outdir <path>    |  -o<path> | outputs/img_samples  | Temporarily change the location of these images |

ldm/invoke/args.py

@@ -378,6 +378,14 @@ def _create_arg_parser(self):
             default='stable-diffusion-1.4',
             help='Indicates which diffusion model to load. (currently "stable-diffusion-1.4" (default) or "laion400m")',
         )
+        model_group.add_argument(
+            '--png_compression','-z',
+            type=int,
+            default=6,
+            choices=range(0,9),
+            dest='png_compression',
+            help='level of PNG compression, from 0 (none) to 9 (maximum). Default is 6.'
+        )
         model_group.add_argument(
             '--sampler',
             '-A',
@@ -649,6 +657,14 @@ def _create_dream_cmd_parser(self):
             dest='save_intermediates',
             help='Save every nth intermediate image into an "intermediates" directory within the output directory'
         )
+        render_group.add_argument(
+            '--png_compression','-z',
+            type=int,
+            default=6,
+            choices=range(0,10),
+            dest='png_compression',
+            help='level of PNG compression, from 0 (none) to 9 (maximum). Default is 6.'
+        )
         img2img_group.add_argument(
             '-I',
             '--init_img',

ldm/invoke/pngwriter.py

@@ -33,13 +33,13 @@ def unique_prefix(self):
 
     # saves image named _image_ to outdir/name, writing metadata from prompt
     # returns full path of output
-    def save_image_and_prompt_to_png(self, image, dream_prompt, name, metadata=None):
+    def save_image_and_prompt_to_png(self, image, dream_prompt, name, metadata=None, compress_level=6):
         path = os.path.join(self.outdir, name)
         info = PngImagePlugin.PngInfo()
         info.add_text('Dream', dream_prompt)
         if metadata:
           info.add_text('sd-metadata', json.dumps(metadata))
-        image.save(path, 'PNG', pnginfo=info)
+        image.save(path, 'PNG', pnginfo=info, compress_level=compress_level)
         return path
 
     def retrieve_metadata(self,img_basename):

ldm/invoke/readline.py

@@ -53,6 +53,7 @@
     '--log_tokenization','-t',
     '--hires_fix',
     '--inpaint_replace','-r',
+    '--png_compression','-z',
     '!fix','!fetch','!history','!search','!clear',
     '!models','!switch','!import_model','!edit_model'
     )

ldm/modules/diffusionmodules/util.py

@@ -64,7 +64,8 @@ def make_ddim_timesteps(
 ):
     if ddim_discr_method == 'uniform':
         c = num_ddpm_timesteps // num_ddim_timesteps
-        ddim_timesteps = np.asarray(list(range(0, num_ddpm_timesteps, c)))
+        # ddim_timesteps = np.asarray(list(range(0, num_ddpm_timesteps, c)))
+        ddim_timesteps = (np.arange(0, num_ddim_timesteps) * c).astype(int)
     elif ddim_discr_method == 'quad':
         ddim_timesteps = (
             (
@@ -81,8 +82,8 @@ def make_ddim_timesteps(
 
     # assert ddim_timesteps.shape[0] == num_ddim_timesteps
     # add one to get the final alpha values right (the ones from first scale to data during sampling)
-#    steps_out = ddim_timesteps + 1
-    steps_out = ddim_timesteps
+    steps_out = ddim_timesteps + 1
+    # steps_out = ddim_timesteps
 
     if verbose:
         print(f'Selected timesteps for ddim sampler: {steps_out}')

scripts/invoke.py

@@ -273,6 +273,7 @@ def image_writer(image, seed, upscaled=False, first_seed=None, use_prefix=None):
                             model_hash = gen.model_hash,
                         ),
                         name      = filename,
+                        compress_level = opt.png_compression,
                     )
 
                     # update rfc metadata