Merge branch 'development' into model-switching

backend/invoke_ai_web_server.py

@@ -319,7 +319,7 @@ class InvokeAIWebServer:
                 elif postprocessing_parameters['type'] == 'gfpgan':
                     image = self.gfpgan.process(
                         image=image,
-                        strength=postprocessing_parameters['gfpgan_strength'],
+                        strength=postprocessing_parameters['facetool_strength'],
                         seed=seed,
                     )
                 else:
@@ -625,7 +625,7 @@ class InvokeAIWebServer:
                         seed=seed,
                     )
                     postprocessing = True
-                    all_parameters['gfpgan_strength'] = gfpgan_parameters[
+                    all_parameters['facetool_strength'] = gfpgan_parameters[
                         'strength'
                     ]
 
@@ -723,6 +723,7 @@ class InvokeAIWebServer:
                 'height',
                 'extra',
                 'seamless',
+                'hires_fix',
             ]
 
             rfc_dict = {}
@@ -735,12 +736,12 @@ class InvokeAIWebServer:
             postprocessing = []
 
             # 'postprocessing' is either null or an
-            if 'gfpgan_strength' in parameters:
+            if 'facetool_strength' in parameters:
 
                 postprocessing.append(
                     {
                         'type': 'gfpgan',
-                        'strength': float(parameters['gfpgan_strength']),
+                        'strength': float(parameters['facetool_strength']),
                     }
                 )
 
@@ -837,7 +838,7 @@ class InvokeAIWebServer:
             elif parameters['type'] == 'gfpgan':
                 postprocessing_metadata['type'] = 'gfpgan'
                 postprocessing_metadata['strength'] = parameters[
-                    'gfpgan_strength'
+                    'facetool_strength'
                 ]
             else:
                 raise TypeError(f"Invalid type: {parameters['type']}")

backend/modules/parameters.py

@@ -36,6 +36,8 @@ def parameters_to_command(params):
         switches.append(f'-A {params["sampler_name"]}')
     if "seamless" in params and params["seamless"] == True:
         switches.append(f"--seamless")
+    if "hires_fix" in params and params["hires_fix"] == True:
+        switches.append(f"--hires")
     if "init_img" in params and len(params["init_img"]) > 0:
         switches.append(f'-I {params["init_img"]}')
     if "init_mask" in params and len(params["init_mask"]) > 0:
@@ -46,8 +48,14 @@ def parameters_to_command(params):
         switches.append(f'-f {params["strength"]}')
         if "fit" in params and params["fit"] == True:
             switches.append(f"--fit")
-    if "gfpgan_strength" in params and params["gfpgan_strength"]:
+    if "facetool" in params:
+        switches.append(f'-ft {params["facetool"]}')
+    if "facetool_strength" in params and params["facetool_strength"]:
+        switches.append(f'-G {params["facetool_strength"]}')
+    elif "gfpgan_strength" in params and params["gfpgan_strength"]:
         switches.append(f'-G {params["gfpgan_strength"]}')
+    if "codeformer_fidelity" in params:
+        switches.append(f'-cf {params["codeformer_fidelity"]}')
     if "upscale" in params and params["upscale"]:
         switches.append(f'-U {params["upscale"][0]} {params["upscale"][1]}')
     if "variation_amount" in params and params["variation_amount"] > 0:

backend/server.py

@@ -349,7 +349,7 @@ def handle_run_gfpgan_event(original_image, gfpgan_parameters):
     eventlet.sleep(0)
 
     image = gfpgan.process(
-        image=image, strength=gfpgan_parameters["gfpgan_strength"], seed=seed
+        image=image, strength=gfpgan_parameters["facetool_strength"], seed=seed
     )
 
     progress["currentStatus"] = "Saving image"
@@ -464,7 +464,7 @@ def parameters_to_post_processed_image_metadata(parameters, original_image_path,
         image["strength"] = parameters["upscale"][1]
     elif type == "gfpgan":
         image["type"] = "gfpgan"
-        image["strength"] = parameters["gfpgan_strength"]
+        image["strength"] = parameters["facetool_strength"]
     else:
         raise TypeError(f"Invalid type: {type}")
 
@@ -493,6 +493,7 @@ def parameters_to_generated_image_metadata(parameters):
         "height",
         "extra",
         "seamless",
+        "hires_fix",
     ]
 
     rfc_dict = {}
@@ -505,10 +506,10 @@ def parameters_to_generated_image_metadata(parameters):
     postprocessing = []
 
     # 'postprocessing' is either null or an
-    if "gfpgan_strength" in parameters:
+    if "facetool_strength" in parameters:
 
         postprocessing.append(
-            {"type": "gfpgan", "strength": float(parameters["gfpgan_strength"])}
+            {"type": "gfpgan", "strength": float(parameters["facetool_strength"])}
         )
 
     if "upscale" in parameters:
@@ -751,7 +752,7 @@ def generate_images(generation_parameters, esrgan_parameters, gfpgan_parameters)
                 image=image, strength=gfpgan_parameters["strength"], seed=seed
             )
             postprocessing = True
-            all_parameters["gfpgan_strength"] = gfpgan_parameters["strength"]
+            all_parameters["facetool_strength"] = gfpgan_parameters["strength"]
 
         progress["currentStatus"] = "Saving image"
         socketio.emit("progressUpdate", progress)

docs/features/CLI.md

@@ -154,7 +154,9 @@ Here are the invoke> command that apply to txt2img:
 | --log_tokenization | -t        | False               | Display a color-coded list of the parsed tokens derived from the prompt |
 | --skip_normalization| -x       | False               | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts) |
 | --upscale <int> <float> | -U <int> <float> | -U 1 0.75| Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75. |
-| --gfpgan_strength <float>  | -G <float> | -G0        | Fix faces using the GFPGAN algorithm; argument indicates how hard the algorithm should try (0.0-1.0) |
+| --facetool_strength <float>  | -G <float> | -G0        | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0) |
+| --facetool <name> | -ft <name> | -ft gfpgan | Select face restoration algorithm to use: gfpgan, codeformer |
+| --codeformer_fidelity | -cf <float> | 0.75 | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality |
 | --save_original    | -save_orig| False               | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced. |
 | --variation <float>  |-v<float>| 0.0                 | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with -S<seed> and -n<int> to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
 | --with_variations <pattern> |    | None              | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this. |

docs/features/POSTPROCESS.md

@@ -69,7 +69,7 @@ If you do not explicitly specify an upscaling_strength, it will default to 0.75.
 
 ### Face Restoration
 
-`-G : <gfpgan_strength>`
+`-G : <facetool_strength>`
 
 This prompt argument controls the strength of the face restoration that is being
 applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.

frontend/dist/index.html

@@ -6,7 +6,7 @@
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
   <title>InvokeAI - A Stable Diffusion Toolkit</title>
   <link rel="shortcut icon" type="icon" href="/assets/favicon.0d253ced.ico" />
-  <script type="module" crossorigin src="/assets/index.989a0ca2.js"></script>
+  <script type="module" crossorigin src="/assets/index.ea68b5f5.js"></script>
   <link rel="stylesheet" href="/assets/index.58175ea1.css">
 </head>
 

frontend/src/app/constants.ts

@@ -50,6 +50,7 @@ export const PARAMETERS: { [key: string]: string } = {
   maskPath: 'Initial Image Mask',
   shouldFitToWidthHeight: 'Fit Initial Image',
   seamless: 'Seamless Tiling',
+  hiresFix: 'High Resolution Optimizations',
 };
 
 export const NUMPY_RAND_MIN = 0;

frontend/src/app/features.ts

@@ -14,10 +14,13 @@ export enum Feature {
   FACE_CORRECTION,
   IMAGE_TO_IMAGE,
 }
-
+/** For each tooltip in the UI, the below feature definitions & props will pull relevant information into the tooltip.
+ * 
+ * To-do: href & GuideImages are placeholders, and are not currently utilized, but will be updated (along with the tooltip UI) as feature and UI development and we get a better idea on where things "forever homes" will be . 
+ */
 export const FEATURES: Record<Feature, FeatureHelpInfo> = {
   [Feature.PROMPT]: {
-    text: 'This field will take all prompt text, including both content and stylistic terms. CLI Commands will not work in the prompt.',
+    text: 'This field will take all prompt text, including both content and stylistic terms. While weights can be included in the prompt, standard CLI Commands/parameters will not work.',
     href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
@@ -27,17 +30,16 @@ export const FEATURES: Record<Feature, FeatureHelpInfo> = {
     guideImage: 'asset/path.gif',
   },
   [Feature.OTHER]: {
-    text: 'Additional Options',
+    text: 'These options will enable alternative processing modes for Invoke. Seamless tiling will work to generate repeating patterns in the output. High Resolution Optimization performs a two-step generation cycle, and should be used at higher resolutions when you desire a more coherent image/composition. ',    href: 'link/to/docs/feature3.html',
-    href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
   [Feature.SEED]: {
-    text: 'Seed values provide an initial set of noise which guide the denoising process.',
+    text: 'Seed values provide an initial set of noise which guide the denoising process, and can be randomized or populated with a seed from a previous invocation. The Threshold feature can be used to mitigate undesirable outcomes at higher CFG values (try between 0-10), and Perlin can be used to add Perlin noise into the denoising process - Both serve to add variation to your outputs. ',
     href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
   [Feature.VARIATIONS]: {
-    text: 'Try a variation with an amount of between 0 and 1 to change the output image for the set seed.',
+    text: 'Try a variation with an amount of between 0 and 1 to change the output image for the set seed - Interesting variations on the seed are found between 0.1 and 0.3.',
     href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
@@ -47,8 +49,8 @@ export const FEATURES: Record<Feature, FeatureHelpInfo> = {
     guideImage: 'asset/path.gif',
   },
   [Feature.FACE_CORRECTION]: {
-    text: 'Using GFPGAN or CodeFormer, Face Correction will attempt to identify faces in outputs, and correct any defects/abnormalities. Higher values will apply a stronger corrective pressure on outputs.',
+    text: 'Using GFPGAN, Face Correction will attempt to identify faces in outputs, and correct any defects/abnormalities. Higher values will apply a stronger corrective pressure on outputs, resulting in more appealing faces (with less respect for accuracy of the original subject).',
-    href: 'link/to/docs/feature2.html',
+    href: 'link/to/docs/feature3.html',
     guideImage: 'asset/path.gif',
   },
   [Feature.IMAGE_TO_IMAGE]: {

frontend/src/app/invokeai.d.ts

@@ -55,6 +55,7 @@ export declare type CommonGeneratedImageMetadata = {
   width: number;
   height: number;
   seamless: boolean;
+  hires_fix: boolean;
   extra: null | Record<string, never>; // Pending development of RFC #266
 };
 

frontend/src/app/socketio/emitters.ts

@@ -76,7 +76,7 @@ const makeSocketIOEmitters = (
       const { gfpganStrength } = getState().options;
 
       const gfpganParameters = {
-        gfpgan_strength: gfpganStrength,
+        facetool_strength: gfpganStrength,
       };
       socketio.emit('runPostprocessing', imageToProcess, {
         type: 'gfpgan',

frontend/src/common/util/parameterTranslation.ts

@@ -29,6 +29,7 @@ export const frontendToBackendParameters = (
     sampler,
     seed,
     seamless,
+    hiresFix,
     shouldUseInitImage,
     img2imgStrength,
     initialImagePath,
@@ -59,6 +60,7 @@ export const frontendToBackendParameters = (
     sampler_name: sampler,
     seed,
     seamless,
+    hires_fix: hiresFix,
     progress_images: shouldDisplayInProgress,
   };
 
@@ -123,10 +125,11 @@ export const backendToFrontendParameters = (parameters: {
     sampler_name,
     seed,
     seamless,
+    hires_fix,
     progress_images,
     variation_amount,
     with_variations,
-    gfpgan_strength,
+    facetool_strength,
     upscale,
     init_img,
     init_mask,
@@ -151,9 +154,9 @@ export const backendToFrontendParameters = (parameters: {
     }
   }
 
-  if (gfpgan_strength > 0) {
+  if (facetool_strength > 0) {
     options.shouldRunGFPGAN = true;
-    options.gfpganStrength = gfpgan_strength;
+    options.gfpganStrength = facetool_strength;
   }
 
   if (upscale) {
@@ -185,6 +188,7 @@ export const backendToFrontendParameters = (parameters: {
     options.sampler = sampler_name;
     options.seed = seed;
     options.seamless = seamless;
+    options.hiresFix = hires_fix;
   }
 
   return options;

frontend/src/features/gallery/ImageMetaDataViewer/ImageMetadataViewer.tsx

@@ -16,11 +16,13 @@ import {
   setCfgScale,
   setGfpganStrength,
   setHeight,
+  setHiresFix,
   setImg2imgStrength,
   setInitialImagePath,
   setMaskPath,
   setPrompt,
   setSampler,
+  setSeamless,
   setSeed,
   setSeedWeights,
   setShouldFitToWidthHeight,
@@ -116,6 +118,7 @@ const ImageMetadataViewer = memo(
       steps,
       cfg_scale,
       seamless,
+      hires_fix,
       width,
       height,
       strength,
@@ -214,7 +217,14 @@ const ImageMetadataViewer = memo(
                 <MetadataItem
                   label="Seamless"
                   value={seamless}
-                  onClick={() => dispatch(setWidth(seamless))}
+                  onClick={() => dispatch(setSeamless(seamless))}
+                />
+              )}
+              {hires_fix && (
+                <MetadataItem
+                  label="High Resolution Optimization"
+                  value={hires_fix}
+                  onClick={() => dispatch(setHiresFix(hires_fix))}
                 />
               )}
               {width && (

frontend/src/features/options/HiresOptions.tsx

@@ -0,0 +1,32 @@
+import { Flex } from '@chakra-ui/react';
+import { RootState } from '../../app/store';
+import { useAppDispatch, useAppSelector } from '../../app/store';
+import { setHiresFix } from './optionsSlice';
+import { ChangeEvent } from 'react';
+import IAISwitch from '../../common/components/IAISwitch';
+
+/**
+ * Image output options. Includes width, height, seamless tiling.
+ */
+const HiresOptions = () => {
+  const dispatch = useAppDispatch();
+
+  const hiresFix = useAppSelector((state: RootState) => state.options.hiresFix);
+
+  const handleChangeHiresFix = (e: ChangeEvent<HTMLInputElement>) =>
+    dispatch(setHiresFix(e.target.checked));
+
+
+  return (
+    <Flex gap={2} direction={'column'}>
+      <IAISwitch
+        label="High Res Optimization"
+        fontSize={'md'}
+        isChecked={hiresFix}
+        onChange={handleChangeHiresFix}
+      />
+    </Flex>
+  );
+};
+
+export default HiresOptions;

frontend/src/features/options/OutputOptions.tsx

@@ -1,29 +1,14 @@
 import { Flex } from '@chakra-ui/react';
-import { RootState } from '../../app/store';
-import { useAppDispatch, useAppSelector } from '../../app/store';
-import { setSeamless } from './optionsSlice';
-import { ChangeEvent } from 'react';
-import IAISwitch from '../../common/components/IAISwitch';
 
-/**
+import HiresOptions from './HiresOptions';
- * Image output options. Includes width, height, seamless tiling.
+import SeamlessOptions from './SeamlessOptions';
- */
+
 const OutputOptions = () => {
-  const dispatch = useAppDispatch();
-
-  const seamless = useAppSelector((state: RootState) => state.options.seamless);
-
-  const handleChangeSeamless = (e: ChangeEvent<HTMLInputElement>) =>
-    dispatch(setSeamless(e.target.checked));
 
   return (
     <Flex gap={2} direction={'column'}>
-      <IAISwitch
+      <SeamlessOptions />
-        label="Seamless tiling"
+      <HiresOptions />
-        fontSize={'md'}
-        isChecked={seamless}
-        onChange={handleChangeSeamless}
-      />
     </Flex>
   );
 };

frontend/src/features/options/SeamlessOptions.tsx

@@ -0,0 +1,28 @@
+import { Flex } from '@chakra-ui/react';
+import { RootState } from '../../app/store';
+import { useAppDispatch, useAppSelector } from '../../app/store';
+import { setSeamless } from './optionsSlice';
+import { ChangeEvent } from 'react';
+import IAISwitch from '../../common/components/IAISwitch';
+
+const SeamlessOptions = () => {
+  const dispatch = useAppDispatch();
+
+  const seamless = useAppSelector((state: RootState) => state.options.seamless);
+
+  const handleChangeSeamless = (e: ChangeEvent<HTMLInputElement>) =>
+    dispatch(setSeamless(e.target.checked));
+
+  return (
+    <Flex gap={2} direction={'column'}>
+      <IAISwitch
+        label="Seamless tiling"
+        fontSize={'md'}
+        isChecked={seamless}
+        onChange={handleChangeSeamless}
+      />
+    </Flex>
+  );
+};
+
+export default SeamlessOptions;

frontend/src/features/options/optionsSlice.ts

@@ -25,6 +25,7 @@ export interface OptionsState {
   initialImagePath: string | null;
   maskPath: string;
   seamless: boolean;
+  hiresFix: boolean;
   shouldFitToWidthHeight: boolean;
   shouldGenerateVariations: boolean;
   variationAmount: number;
@@ -50,6 +51,7 @@ const initialOptionsState: OptionsState = {
   perlin: 0,
   seed: 0,
   seamless: false,
+  hiresFix: false,
   shouldUseInitImage: false,
   img2imgStrength: 0.75,
   initialImagePath: null,
@@ -138,6 +140,9 @@ export const optionsSlice = createSlice({
     setSeamless: (state, action: PayloadAction<boolean>) => {
       state.seamless = action.payload;
     },
+    setHiresFix: (state, action: PayloadAction<boolean>) => {
+      state.hiresFix = action.payload;
+    },
     setShouldFitToWidthHeight: (state, action: PayloadAction<boolean>) => {
       state.shouldFitToWidthHeight = action.payload;
     },
@@ -180,6 +185,7 @@ export const optionsSlice = createSlice({
         threshold,
         perlin,
         seamless,
+        hires_fix,
         width,
         height,
         strength,
@@ -256,6 +262,7 @@ export const optionsSlice = createSlice({
       if (perlin) state.perlin = perlin;
       if (typeof perlin === 'undefined') state.perlin = 0;      
       if (typeof seamless === 'boolean') state.seamless = seamless;
+      if (typeof hires_fix === 'boolean') state.hiresFix = hires_fix;
       if (width) state.width = width;
       if (height) state.height = height;
     },
@@ -301,6 +308,7 @@ export const {
   setSampler,
   setSeed,
   setSeamless,
+  setHiresFix,
   setImg2imgStrength,
   setGfpganStrength,
   setUpscalingLevel,

ldm/generate.py

@@ -35,6 +35,24 @@ from ldm.invoke.devices import choose_torch_device, choose_precision
 from ldm.invoke.conditioning import get_uc_and_c
 from ldm.invoke.model_cache import ModelCache
 
+def fix_func(orig):
+    if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available():
+        def new_func(*args, **kw):
+            device = kw.get("device", "mps")
+            kw["device"]="cpu"
+            return orig(*args, **kw).to(device)
+        return new_func
+    return orig
+
+torch.rand = fix_func(torch.rand)
+torch.rand_like = fix_func(torch.rand_like)
+torch.randn = fix_func(torch.randn)
+torch.randn_like = fix_func(torch.randn_like)
+torch.randint = fix_func(torch.randint)
+torch.randint_like = fix_func(torch.randint_like)
+torch.bernoulli = fix_func(torch.bernoulli)
+torch.multinomial = fix_func(torch.multinomial)
+
 """Simplified text to image API for stable diffusion/latent diffusion
 
 Example Usage:
@@ -137,6 +155,7 @@ class Generate:
         self.precision      = precision
         self.strength       = 0.75
         self.seamless       = False
+        self.hires_fix      = False
         self.embedding_path = embedding_path
         self.model          = None     # empty for now
         self.model_hash     = None
@@ -156,6 +175,7 @@ class Generate:
         # device to Generate(). However the device was then ignored, so
         # it wasn't actually doing anything. This logic could be reinstated.
         device_type = choose_torch_device()
+        print(f'>> Using device_type {device_type}')
         self.device = torch.device(device_type)
         if full_precision:
             if self.precision != 'auto':
@@ -236,7 +256,7 @@ class Generate:
             embiggen_tiles =    None,
             # these are specific to GFPGAN/ESRGAN
             facetool         = None,
-            gfpgan_strength  = 0,
+            facetool_strength  = 0,
             codeformer_fidelity = None,
             save_original    = False,
             upscale          = None,
@@ -256,9 +276,10 @@ class Generate:
            height                          // height of image, in multiples of 64 (512)
            cfg_scale                       // how strongly the prompt influences the image (7.5) (must be >1)
            seamless                        // whether the generated image should tile
+           hires_fix                        // whether the Hires Fix should be applied during generation
            init_img                        // path to an initial image
            strength                        // strength for noising/unnoising init_img. 0.0 preserves image exactly, 1.0 replaces it completely
-           gfpgan_strength                 // strength for GFPGAN. 0.0 preserves image exactly, 1.0 replaces it completely
+           facetool_strength               // strength for GFPGAN/CodeFormer. 0.0 preserves image exactly, 1.0 replaces it completely
            ddim_eta                        // image randomness (eta=0.0 means the same seed always produces the same image)
            step_callback                   // a function or method that will be called each step
            image_callback                  // a function or method that will be called each time an image is generated
@@ -289,6 +310,7 @@ class Generate:
         width = width or self.width
         height = height or self.height
         seamless = seamless or self.seamless
+        hires_fix = hires_fix or self.hires_fix
         cfg_scale = cfg_scale or self.cfg_scale
         ddim_eta = ddim_eta or self.ddim_eta
         iterations = iterations or self.iterations
@@ -405,11 +427,11 @@ class Generate:
                                     reference_image_path = init_color,
                                     image_callback       = image_callback)
 
-            if upscale is not None or gfpgan_strength > 0:
+            if upscale is not None or facetool_strength > 0:
                 self.upscale_and_reconstruct(results,
                                              upscale        = upscale,
                                              facetool       = facetool,
-                                             strength       = gfpgan_strength,
+                                             strength       = facetool_strength,
                                              codeformer_fidelity = codeformer_fidelity,
                                              save_original  = save_original,
                                              image_callback = image_callback)
@@ -452,7 +474,7 @@ class Generate:
             self,
             image_path,
             tool                = 'gfpgan',  # one of 'upscale', 'gfpgan', 'codeformer', 'outpaint', or 'embiggen'
-            gfpgan_strength     = 0.0,
+            facetool_strength   = 0.0,
             codeformer_fidelity = 0.75,
             upscale             = None,
             out_direction       = None,
@@ -499,11 +521,11 @@ class Generate:
                 facetool = 'codeformer'
             elif tool == 'upscale':
                 facetool = 'gfpgan'   # but won't be run
-                gfpgan_strength = 0
+                facetool_strength = 0
             return self.upscale_and_reconstruct(
                 [[image,seed]],
                 facetool = facetool,
-                strength = gfpgan_strength,
+                strength = facetool_strength,
                 codeformer_fidelity = codeformer_fidelity,
                 save_original = save_original,
                 upscale = upscale,

ldm/invoke/args.py

@@ -242,9 +242,13 @@ class Args(object):
         else:
             switches.append(f'-A {a["sampler_name"]}')
 
-        # gfpgan-specific parameters
+        # facetool-specific parameters
-        if a['gfpgan_strength']:
+        if a['facetool']:
-            switches.append(f'-G {a["gfpgan_strength"]}')
+            switches.append(f'-ft {a["facetool"]}')
+        if a['facetool_strength']:
+            switches.append(f'-G {a["facetool_strength"]}')
+        if a['codeformer_fidelity']:
+            switches.append(f'-cf {a["codeformer_fidelity"]}')
 
         if a['outcrop']:
             switches.append(f'-c {" ".join([str(u) for u in a["outcrop"]])}')
@@ -636,6 +640,13 @@ class Args(object):
             dest='hires_fix',
             help='Create hires image using img2img to prevent duplicated objects'
         )
+        render_group.add_argument(
+            '--save_intermediates',
+            type=int,
+            default=0,
+            dest='save_intermediates',
+            help='Save every nth intermediate image into an "intermediates" directory within the output directory'
+        )
         img2img_group.add_argument(
             '-I',
             '--init_img',
@@ -692,6 +703,7 @@ class Args(object):
         )
         postprocessing_group.add_argument(
             '-G',
+            '--facetool_strength',
             '--gfpgan_strength',
             type=float,
             help='The strength at which to apply the face restoration to the result.',

ldm/invoke/readline.py

@@ -33,6 +33,7 @@ COMMANDS = (
     '--perlin',
     '--grid','-g',
     '--individual','-i',
+    '--save_intermediates',
     '--init_img','-I',
     '--init_mask','-M',
     '--init_color',
@@ -43,7 +44,9 @@ COMMANDS = (
     '--embedding_path',
     '--device',
     '--grid','-g',
-    '--gfpgan_strength','-G',
+    '--facetool','-ft',
+    '--facetool_strength','-G',
+    '--codeformer_fidelity','-cf',
     '--upscale','-U',
     '-save_orig','--save_original',
     '--skip_normalize','-x',

ldm/invoke/server.py

@@ -31,12 +31,13 @@ def build_opt(post_data, seed, gfpgan_model_exists):
     setattr(opt, 'embiggen', None)
     setattr(opt, 'embiggen_tiles', None)
 
-    setattr(opt, 'gfpgan_strength', float(post_data['gfpgan_strength']) if gfpgan_model_exists else 0)
+    setattr(opt, 'facetool_strength', float(post_data['facetool_strength']) if gfpgan_model_exists else 0)
     setattr(opt, 'upscale', [int(post_data['upscale_level']), float(post_data['upscale_strength'])] if post_data['upscale_level'] != '' else None)
     setattr(opt, 'progress_images', 'progress_images' in post_data)
     setattr(opt, 'seed', None if int(post_data['seed']) == -1 else int(post_data['seed']))
     setattr(opt, 'threshold', float(post_data['threshold']))
     setattr(opt, 'perlin', float(post_data['perlin']))
+    setattr(opt, 'hires_fix', 'hires_fix' in post_data)
     setattr(opt, 'variation_amount', float(post_data['variation_amount']) if int(post_data['seed']) != -1 else 0)
     setattr(opt, 'with_variations', [])
     setattr(opt, 'embiggen', None)
@@ -196,7 +197,7 @@ class DreamServer(BaseHTTPRequestHandler):
                 ) + '\n',"utf-8"))
 
             # control state of the "postprocessing..." message
-            upscaling_requested = opt.upscale or opt.gfpgan_strength > 0
+            upscaling_requested = opt.upscale or opt.facetool_strength > 0
             nonlocal images_generated # NB: Is this bad python style? It is typical usage in a perl closure.
             nonlocal images_upscaled  # NB: Is this bad python style? It is typical usage in a perl closure.
             if upscaled:

ldm/models/diffusion/ksampler.py

@@ -98,7 +98,8 @@ class KSampler(Sampler):
             rho=7.,
             device=self.device,
         )
-        self.sigmas = self.karras_sigmas
+        self.sigmas = self.model_sigmas
+        #self.sigmas = self.karras_sigmas
         
     # ALERT: We are completely overriding the sample() method in the base class, which
     # means that inpainting will not work. To get this to work we need to be able to

ldm/models/diffusion/sampler.py

@@ -140,7 +140,7 @@ class Sampler(object):
         conditioning=None,
         callback=None,
         normals_sequence=None,
-        img_callback=None,
+        img_callback=None,   # TODO: this is very confusing because it is called "step_callback" elsewhere. Change.
         quantize_x0=False,
         eta=0.0,
         mask=None,

ldm/modules/diffusionmodules/model.py

@@ -49,9 +49,15 @@ class Upsample(nn.Module):
                                         padding=1)
 
     def forward(self, x):
+        cpu_m1_cond = True if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available() and \
+                              x.size()[0] * x.size()[1] * x.size()[2] * x.size()[3] % 2**27 == 0 else False
+        if cpu_m1_cond:
+            x = x.to('cpu')  # send to cpu
         x = torch.nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
         if self.with_conv:
             x = self.conv(x)
+        if cpu_m1_cond:
+            x = x.to('mps')  # return to mps
         return x
 
 
@@ -117,6 +123,14 @@ class ResnetBlock(nn.Module):
                                                     padding=0)
 
     def forward(self, x, temb):
+        if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available():
+            x_size = x.size()
+            if (x_size[0] * x_size[1] * x_size[2] * x_size[3]) % 2**29 == 0:
+                self.to('cpu')
+                x = x.to('cpu')
+            else:
+                self.to('mps')
+                x = x.to('mps')
         h = self.norm1(x)
         h = silu(h)
         h = self.conv1(h)

notebooks/Stable_Diffusion_AI_Notebook.ipynb

@@ -6,7 +6,7 @@
         "id": "ycYWcsEKc6w7"
       },
       "source": [
-        "# Stable Diffusion AI Notebook (Release 1.14)\n",
+        "# Stable Diffusion AI Notebook (Release 2.0.0)\n",
         "\n",
         "<img src=\"https://user-images.githubusercontent.com/60411196/186547976-d9de378a-9de8-4201-9c25-c057a9c59bad.jpeg\" alt=\"stable-diffusion-ai\" width=\"170px\"/> <br>\n",
         "#### Instructions:\n",
@@ -58,8 +58,8 @@
         "from os.path import exists\n",
         "\n",
         "!git clone --quiet https://github.com/invoke-ai/InvokeAI.git # Original repo\n",
-        "%cd /content/stable-diffusion/\n",
+        "%cd /content/InvokeAI/\n",
-        "!git checkout --quiet tags/release-1.14.1"
+        "!git checkout --quiet tags/v2.0.0"
       ]
     },
     {
@@ -79,6 +79,7 @@
         "!pip install colab-xterm\n",
         "!pip install -r requirements-lin-win-colab-CUDA.txt\n",
         "!pip install clean-fid torchtext\n",
+        "!pip install transformers\n",
         "gc.collect()"
       ]
     },
@@ -106,7 +107,7 @@
       "source": [
         "#@title 5. Load small ML models required\n",
         "import gc\n",
-        "%cd /content/stable-diffusion/\n",
+        "%cd /content/InvokeAI/\n",
         "!python scripts/preload_models.py\n",
         "gc.collect()"
       ]
@@ -171,18 +172,18 @@
         "import os \n",
         "\n",
         "# Folder creation if it doesn't exist\n",
-        "if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1\"):\n",
+        "if exists(\"/content/InvokeAI/models/ldm/stable-diffusion-v1\"):\n",
         "     print(\"❗ Dir stable-diffusion-v1 already exists\")\n",
         "else:\n",
-        "    %mkdir /content/stable-diffusion/models/ldm/stable-diffusion-v1\n",
+        "    %mkdir /content/InvokeAI/models/ldm/stable-diffusion-v1\n",
         "    print(\"✅ Dir stable-diffusion-v1 created\")\n",
         "\n",
         "# Symbolic link if it doesn't exist\n",
-        "if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt\"):\n",
+        "if exists(\"/content/InvokeAI/models/ldm/stable-diffusion-v1/model.ckpt\"):\n",
         "    print(\"❗ Symlink already created\")\n",
         "else: \n",
         "    src = model_path\n",
-        "    dst = '/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt'\n",
+        "    dst = '/content/InvokeAI/models/ldm/stable-diffusion-v1/model.ckpt'\n",
         "    os.symlink(src, dst) \n",
         "    print(\"✅ Symbolic link created successfully\")"
       ]
@@ -207,7 +208,7 @@
       "source": [
         "#@title 9. Run Terminal and Execute Dream bot\n",
         "#@markdown <font color=\"blue\">Steps:</font> <br>\n",
-        "#@markdown 1. Execute command `python scripts/dream.py` to run dream bot.<br>\n",
+        "#@markdown 1. Execute command `python scripts/invoke.py` to run InvokeAI.<br>\n",
         "#@markdown 2. After initialized you'll see `Dream>` line.<br>\n",
         "#@markdown 3. Example text: `Astronaut floating in a distant galaxy` <br>\n",
         "#@markdown 4. To quit Dream bot use: `q` command.<br>\n",
@@ -233,7 +234,7 @@
         "%matplotlib inline\n",
         "\n",
         "images = []\n",
-        "for img_path in sorted(glob.glob('/content/stable-diffusion/outputs/img-samples/*.png'), reverse=True):\n",
+        "for img_path in sorted(glob.glob('/content/InvokeAI/outputs/img-samples/*.png'), reverse=True):\n",
         "    images.append(mpimg.imread(img_path))\n",
         "\n",
         "images = images[:15] \n",

scripts/dream.py

@@ -1,12 +1,11 @@
 #!/usr/bin/env python3
 # Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
 
-import sys
+import warnings
-import os.path
+import invoke
-
-script_path = sys.argv[0]
-script_args = sys.argv[1:]
-script_dir,script_name = os.path.split(script_path)
-script_dest = os.path.join(script_dir,'invoke.py')
-os.execlp('python3','python3',script_dest,*script_args)
 
+if __name__ == '__main__':
+    warnings.warn("dream.py is being deprecated, please run invoke.py for the "
+                  "new UI/API or legacy_api.py for the old API",
+                  DeprecationWarning)
+    invoke.main()

scripts/invoke.py

@@ -236,6 +236,7 @@ def main_loop(gen, opt, infile):
             grid_images      = dict()  # seed -> Image, only used if `opt.grid`
             prior_variations = opt.with_variations or []
             prefix = file_writer.unique_prefix()
+            step_callback = make_step_callback(gen, opt, prefix) if opt.save_intermediates > 0 else None
 
             def image_writer(image, seed, upscaled=False, first_seed=None, use_prefix=None):
                 # note the seed is the seed of the current image
@@ -297,6 +298,7 @@ def main_loop(gen, opt, infile):
                 opt.last_operation='generate'
                 gen.prompt2image(
                     image_callback=image_writer,
+                    step_callback=step_callback,
                     catch_interrupts=catch_ctrl_c,
                     **vars(opt)
                 )
@@ -494,7 +496,7 @@ def do_postprocess (gen, opt, callback):
         file_path = os.path.join(opt.outdir,file_path)
 
     tool=None
-    if opt.gfpgan_strength > 0:
+    if opt.facetool_strength > 0:
         tool = opt.facetool
     elif opt.embiggen:
         tool = 'embiggen'
@@ -510,7 +512,7 @@ def do_postprocess (gen, opt, callback):
         gen.apply_postprocessor(
             image_path      = file_path,
             tool            = tool,
-            gfpgan_strength = opt.gfpgan_strength,
+            facetool_strength = opt.facetool_strength,
             codeformer_fidelity = opt.codeformer_fidelity,
             save_original       = opt.save_original,
             upscale             = opt.upscale,
@@ -666,6 +668,17 @@ def load_face_restoration(opt):
     return gfpgan,codeformer,esrgan
     
 
+def make_step_callback(gen, opt, prefix):
+    destination = os.path.join(opt.outdir,'intermediates',prefix)
+    os.makedirs(destination,exist_ok=True)
+    print(f'>> Intermediate images will be written into {destination}')
+    def callback(img, step):
+        if step % opt.save_intermediates == 0 or step == opt.steps-1:
+            filename = os.path.join(destination,f'{step:04}.png')
+            image = gen.sample_to_image(img)
+            image.save(filename,'PNG')
+    return callback
+    
 def retrieve_dream_command(opt,file_path,completer):
     '''
     Given a full or partial path to a previously-generated image file,

server/models.py

@@ -35,13 +35,14 @@ class DreamBase():
   perlin: float = 0.0
   sampler_name: string = 'klms'
   seamless: bool = False
+  hires_fix: bool = False
   model: str = None # The model to use (currently unused)
   embeddings = None # The embeddings to use (currently unused)
   progress_images: bool = False
 
   # GFPGAN
   enable_gfpgan: bool
-  gfpgan_strength: float = 0
+  facetool_strength: float = 0
 
   # Upscale
   enable_upscale: bool
@@ -91,12 +92,13 @@ class DreamBase():
       # model: str = None # The model to use (currently unused)
       # embeddings = None # The embeddings to use (currently unused)
       self.seamless = 'seamless' in j
+      self.hires_fix = 'hires_fix' in j
       self.progress_images = 'progress_images' in j
 
     # GFPGAN
     self.enable_gfpgan = 'enable_gfpgan' in j and bool(j.get('enable_gfpgan'))
     if self.enable_gfpgan:
-      self.gfpgan_strength = float(j.get('gfpgan_strength'))
+      self.facetool_strength = float(j.get('facetool_strength'))
 
     # Upscale
     self.enable_upscale = 'enable_upscale' in j and bool(j.get('enable_upscale'))

server/services.py

@@ -334,11 +334,11 @@ class GeneratorService:
       # TODO: Support no generation (just upscaling/gfpgan)
 
       upscale = None if not jobRequest.enable_upscale else jobRequest.upscale
-      gfpgan_strength = 0 if not jobRequest.enable_gfpgan else jobRequest.gfpgan_strength
+      facetool_strength = 0 if not jobRequest.enable_gfpgan else jobRequest.facetool_strength
 
       if not jobRequest.enable_generate:
         # If not generating, check if we're upscaling or running gfpgan
-        if not upscale and not gfpgan_strength:
+        if not upscale and not facetool_strength:
           # Invalid settings (TODO: Add message to help user)
           raise CanceledException()
 
@@ -347,7 +347,7 @@ class GeneratorService:
         self.__model.upscale_and_reconstruct(
           image_list = [[image,0]],
           upscale = upscale,
-          strength = gfpgan_strength,
+          strength = facetool_strength,
           save_original = False,
           image_callback = lambda image, seed, upscaled=False: self.__on_image_result(jobRequest, image, seed, upscaled))
 
@@ -371,10 +371,11 @@ class GeneratorService:
           steps            = jobRequest.steps,
           variation_amount = jobRequest.variation_amount,
           with_variations  = jobRequest.with_variations,
-          gfpgan_strength  = gfpgan_strength,
+          facetool_strength = facetool_strength,
           upscale          = upscale,
           sampler_name     = jobRequest.sampler_name,
           seamless         = jobRequest.seamless,
+          hires_fix        = jobRequest.hires_fix,
           embiggen         = jobRequest.embiggen,
           embiggen_tiles   = jobRequest.embiggen_tiles,
           step_callback    = lambda sample, step: self.__on_progress(jobRequest, sample, step),

static/dream_web/index.html

@@ -144,8 +144,8 @@
             <input type="checkbox" name="enable_gfpgan" id="enable_gfpgan">
             <label for="enable_gfpgan">Enable gfpgan</label>
           </legend>
-          <label title="Strength of the gfpgan (face fixing) algorithm." for="gfpgan_strength">GPFGAN Strength:</label>
+          <label title="Strength of the gfpgan (face fixing) algorithm." for="facetool_strength">GPFGAN Strength:</label>
-          <input value="0.8" min="0" max="1" type="number" id="gfpgan_strength" name="gfpgan_strength" step="0.05">
+          <input value="0.8" min="0" max="1" type="number" id="facetool_strength" name="facetool_strength" step="0.05">
         </fieldset>
         <fieldset id="upscale">
           <legend>

static/legacy_web/index.html

@@ -100,8 +100,8 @@
 	</fieldset>
         <fieldset id="gfpgan">
 	  <div class="section-header">Post-processing options</div>
-          <label title="Strength of the gfpgan (face fixing) algorithm." for="gfpgan_strength">GPFGAN Strength (0 to disable):</label>
+          <label title="Strength of the gfpgan (face fixing) algorithm." for="facetool_strength">GPFGAN Strength (0 to disable):</label>
-          <input value="0.0" min="0" max="1" type="number" id="gfpgan_strength" name="gfpgan_strength" step="0.1">
+          <input value="0.0" min="0" max="1" type="number" id="facetool_strength" name="facetool_strength" step="0.1">
           <label title="Upscaling to perform using ESRGAN." for="upscale_level">Upscaling Level</label>
           <select id="upscale_level" name="upscale_level" value="">
             <option value="" selected>None</option>