remove unwanted formatting/functionality from the PR

launch.py

@@ -1,5 +1,4 @@
 # this scripts installs necessary requirements and launches main program in webui.py
-import shutil
 import subprocess
 import os
 import sys
@@ -119,11 +118,7 @@ def git_clone(url, dir, name, commithash=None):
 git_clone("https://github.com/crowsonkb/k-diffusion.git", repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
 git_clone("https://github.com/sczhou/CodeFormer.git", repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
 git_clone("https://github.com/salesforce/BLIP.git", repo_dir('BLIP'), "BLIP", blip_commit_hash)
-if os.path.isdir(repo_dir('latent-diffusion')):
-    try:
-        shutil.rmtree(repo_dir('latent-diffusion'))
-    except:
-        pass
+
 if not is_installed("lpips"):
     run_pip(f"install -r {os.path.join(repo_dir('CodeFormer'), 'requirements.txt')}", "requirements for CodeFormer")
 

modules/esrgan_model.py

@@ -13,6 +13,63 @@
 from modules.shared import opts
 
 
+def fix_model_layers(crt_model, pretrained_net):
+    # this code is adapted from https://github.com/xinntao/ESRGAN
+    if 'conv_first.weight' in pretrained_net:
+        return pretrained_net
+
+    if 'model.0.weight' not in pretrained_net:
+        is_realesrgan = "params_ema" in pretrained_net and 'body.0.rdb1.conv1.weight' in pretrained_net["params_ema"]
+        if is_realesrgan:
+            raise Exception("The file is a RealESRGAN model, it can't be used as a ESRGAN model.")
+        else:
+            raise Exception("The file is not a ESRGAN model.")
+
+    crt_net = crt_model.state_dict()
+    load_net_clean = {}
+    for k, v in pretrained_net.items():
+        if k.startswith('module.'):
+            load_net_clean[k[7:]] = v
+        else:
+            load_net_clean[k] = v
+    pretrained_net = load_net_clean
+
+    tbd = []
+    for k, v in crt_net.items():
+        tbd.append(k)
+
+    # directly copy
+    for k, v in crt_net.items():
+        if k in pretrained_net and pretrained_net[k].size() == v.size():
+            crt_net[k] = pretrained_net[k]
+            tbd.remove(k)
+
+    crt_net['conv_first.weight'] = pretrained_net['model.0.weight']
+    crt_net['conv_first.bias'] = pretrained_net['model.0.bias']
+
+    for k in tbd.copy():
+        if 'RDB' in k:
+            ori_k = k.replace('RRDB_trunk.', 'model.1.sub.')
+            if '.weight' in k:
+                ori_k = ori_k.replace('.weight', '.0.weight')
+            elif '.bias' in k:
+                ori_k = ori_k.replace('.bias', '.0.bias')
+            crt_net[k] = pretrained_net[ori_k]
+            tbd.remove(k)
+
+    crt_net['trunk_conv.weight'] = pretrained_net['model.1.sub.23.weight']
+    crt_net['trunk_conv.bias'] = pretrained_net['model.1.sub.23.bias']
+    crt_net['upconv1.weight'] = pretrained_net['model.3.weight']
+    crt_net['upconv1.bias'] = pretrained_net['model.3.bias']
+    crt_net['upconv2.weight'] = pretrained_net['model.6.weight']
+    crt_net['upconv2.bias'] = pretrained_net['model.6.bias']
+    crt_net['HRconv.weight'] = pretrained_net['model.8.weight']
+    crt_net['HRconv.bias'] = pretrained_net['model.8.bias']
+    crt_net['conv_last.weight'] = pretrained_net['model.10.weight']
+    crt_net['conv_last.bias'] = pretrained_net['model.10.bias']
+
+    return crt_net
+
 class UpscalerESRGAN(Upscaler):
     def __init__(self, dirname):
         self.name = "ESRGAN"
@@ -28,14 +85,12 @@ def __init__(self, dirname):
             scaler_data = UpscalerData(self.model_name, self.model_url, self, 4)
             scalers.append(scaler_data)
         for file in model_paths:
-            print(f"File: {file}")
             if "http" in file:
                 name = self.model_name
             else:
                 name = modelloader.friendly_name(file)
 
             scaler_data = UpscalerData(name, file, self, 4)
-            print(f"ESRGAN: Adding scaler {name}")
             self.scalers.append(scaler_data)
 
     def do_upscale(self, img, selected_model):
@@ -56,67 +111,14 @@ def load_model(self, path: str):
         if not os.path.exists(filename) or filename is None:
             print("Unable to load %s from %s" % (self.model_path, filename))
             return None
-        # this code is adapted from https://github.com/xinntao/ESRGAN
+
         pretrained_net = torch.load(filename, map_location='cpu' if has_mps else None)
         crt_model = arch.RRDBNet(3, 3, 64, 23, gc=32)
 
-        if 'conv_first.weight' in pretrained_net:
-            crt_model.load_state_dict(pretrained_net)
-            return crt_model
-
-        if 'model.0.weight' not in pretrained_net:
-            is_realesrgan = "params_ema" in pretrained_net and 'body.0.rdb1.conv1.weight' in pretrained_net[
-                "params_ema"]
-            if is_realesrgan:
-                raise Exception("The file is a RealESRGAN model, it can't be used as a ESRGAN model.")
-            else:
-                raise Exception("The file is not a ESRGAN model.")
-
-        crt_net = crt_model.state_dict()
-        load_net_clean = {}
-        for k, v in pretrained_net.items():
-            if k.startswith('module.'):
-                load_net_clean[k[7:]] = v
-            else:
-                load_net_clean[k] = v
-        pretrained_net = load_net_clean
-
-        tbd = []
-        for k, v in crt_net.items():
-            tbd.append(k)
-
-        # directly copy
-        for k, v in crt_net.items():
-            if k in pretrained_net and pretrained_net[k].size() == v.size():
-                crt_net[k] = pretrained_net[k]
-                tbd.remove(k)
-
-        crt_net['conv_first.weight'] = pretrained_net['model.0.weight']
-        crt_net['conv_first.bias'] = pretrained_net['model.0.bias']
-
-        for k in tbd.copy():
-            if 'RDB' in k:
-                ori_k = k.replace('RRDB_trunk.', 'model.1.sub.')
-                if '.weight' in k:
-                    ori_k = ori_k.replace('.weight', '.0.weight')
-                elif '.bias' in k:
-                    ori_k = ori_k.replace('.bias', '.0.bias')
-                crt_net[k] = pretrained_net[ori_k]
-                tbd.remove(k)
-
-        crt_net['trunk_conv.weight'] = pretrained_net['model.1.sub.23.weight']
-        crt_net['trunk_conv.bias'] = pretrained_net['model.1.sub.23.bias']
-        crt_net['upconv1.weight'] = pretrained_net['model.3.weight']
-        crt_net['upconv1.bias'] = pretrained_net['model.3.bias']
-        crt_net['upconv2.weight'] = pretrained_net['model.6.weight']
-        crt_net['upconv2.bias'] = pretrained_net['model.6.bias']
-        crt_net['HRconv.weight'] = pretrained_net['model.8.weight']
-        crt_net['HRconv.bias'] = pretrained_net['model.8.bias']
-        crt_net['conv_last.weight'] = pretrained_net['model.10.weight']
-        crt_net['conv_last.bias'] = pretrained_net['model.10.bias']
-
-        crt_model.load_state_dict(crt_net)
+        pretrained_net = fix_model_layers(crt_model, pretrained_net)
+        crt_model.load_state_dict(pretrained_net)
         crt_model.eval()
+
         return crt_model
 
 
@@ -154,7 +156,6 @@ def esrgan_upscale(model, img):
             newrow.append([x * scale_factor, w * scale_factor, output])
         newtiles.append([y * scale_factor, h * scale_factor, newrow])
 
-    newgrid = images.Grid(newtiles, grid.tile_w * scale_factor, grid.tile_h * scale_factor,
-                                  grid.image_w * scale_factor, grid.image_h * scale_factor, grid.overlap * scale_factor)
+    newgrid = images.Grid(newtiles, grid.tile_w * scale_factor, grid.tile_h * scale_factor, grid.image_w * scale_factor, grid.image_h * scale_factor, grid.overlap * scale_factor)
     output = images.combine_grid(newgrid)
     return output

modules/extras.py

@@ -67,28 +67,29 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v
             info += f"CodeFormer w: {round(codeformer_weight, 2)}, CodeFormer visibility:{round(codeformer_visibility, 2)}\n"
             image = res
 
-        def upscale(image, scaler_index, resize):
-            small = image.crop((image.width // 2, image.height // 2, image.width // 2 + 10, image.height // 2 + 10))
-            pixels = tuple(np.array(small).flatten().tolist())
-            key = (resize, scaler_index, image.width, image.height, gfpgan_visibility, codeformer_visibility, codeformer_weight) + pixels
+        if upscaling_resize != 1.0:
+            def upscale(image, scaler_index, resize):
+                small = image.crop((image.width // 2, image.height // 2, image.width // 2 + 10, image.height // 2 + 10))
+                pixels = tuple(np.array(small).flatten().tolist())
+                key = (resize, scaler_index, image.width, image.height, gfpgan_visibility, codeformer_visibility, codeformer_weight) + pixels
 
-            c = cached_images.get(key)
-            if c is None:
-                upscaler = shared.sd_upscalers[scaler_index]
-                c = upscaler.scaler.upscale(image, resize, upscaler.data_path)
-                cached_images[key] = c
+                c = cached_images.get(key)
+                if c is None:
+                    upscaler = shared.sd_upscalers[scaler_index]
+                    c = upscaler.scaler.upscale(image, resize, upscaler.data_path)
+                    cached_images[key] = c
 
-            return c
+                return c
 
-        info += f"Upscale: {round(upscaling_resize, 3)}, model:{shared.sd_upscalers[extras_upscaler_1].name}\n"
-        res = upscale(image, extras_upscaler_1, upscaling_resize)
+            info += f"Upscale: {round(upscaling_resize, 3)}, model:{shared.sd_upscalers[extras_upscaler_1].name}\n"
+            res = upscale(image, extras_upscaler_1, upscaling_resize)
 
-        if extras_upscaler_2 != 0 and extras_upscaler_2_visibility > 0:
-            res2 = upscale(image, extras_upscaler_2, upscaling_resize)
-            info += f"Upscale: {round(upscaling_resize, 3)}, visibility: {round(extras_upscaler_2_visibility, 3)}, model:{shared.sd_upscalers[extras_upscaler_2].name}\n"
-            res = Image.blend(res, res2, extras_upscaler_2_visibility)
+            if extras_upscaler_2 != 0 and extras_upscaler_2_visibility > 0:
+                res2 = upscale(image, extras_upscaler_2, upscaling_resize)
+                info += f"Upscale: {round(upscaling_resize, 3)}, visibility: {round(extras_upscaler_2_visibility, 3)}, model:{shared.sd_upscalers[extras_upscaler_2].name}\n"
+                res = Image.blend(res, res2, extras_upscaler_2_visibility)
 
-        image = res
+            image = res
 
         while len(cached_images) > 2:
             del cached_images[next(iter(cached_images.keys()))]

modules/gfpgan_model.py

@@ -36,8 +36,7 @@ def gfpgann():
     else:
         print("Unable to load gfpgan model!")
         return None
-    model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2,
-                               bg_upsampler=None)
+    model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None)
     model.gfpgan.to(shared.device)
     loaded_gfpgan_model = model
 
@@ -49,8 +48,7 @@ def gfpgan_fix_faces(np_image):
     if model is None:
         return np_image
     np_image_bgr = np_image[:, :, ::-1]
-    cropped_faces, restored_faces, gfpgan_output_bgr = model.enhance(np_image_bgr, has_aligned=False,
-                                                                     only_center_face=False, paste_back=True)
+    cropped_faces, restored_faces, gfpgan_output_bgr = model.enhance(np_image_bgr, has_aligned=False, only_center_face=False, paste_back=True)
     np_image = gfpgan_output_bgr[:, :, ::-1]
 
     if shared.opts.face_restoration_unload:
@@ -79,7 +77,6 @@ def setup_model(dirname):
         facex_load_file_from_url_orig2 = facexlib.parsing.load_file_from_url
 
         def my_load_file_from_url(**kwargs):
-            print("Setting model_dir to " + model_path)
             return load_file_from_url_orig(**dict(kwargs, model_dir=model_path))
 
         def facex_load_file_from_url(**kwargs):
@@ -92,7 +89,6 @@ def facex_load_file_from_url2(**kwargs):
         facexlib.detection.load_file_from_url = facex_load_file_from_url
         facexlib.parsing.load_file_from_url = facex_load_file_from_url2
         user_path = dirname
-        print("Have gfpgan should be true?")
         have_gfpgan = True
         gfpgan_constructor = GFPGANer
 
@@ -102,9 +98,7 @@ def name(self):
 
             def restore(self, np_image):
                 np_image_bgr = np_image[:, :, ::-1]
-                cropped_faces, restored_faces, gfpgan_output_bgr = gfpgann().enhance(np_image_bgr, has_aligned=False,
-                                                                                     only_center_face=False,
-                                                                                     paste_back=True)
+                cropped_faces, restored_faces, gfpgan_output_bgr = gfpgann().enhance(np_image_bgr, has_aligned=False, only_center_face=False, paste_back=True)
                 np_image = gfpgan_output_bgr[:, :, ::-1]
 
                 return np_image

modules/images.py

@@ -84,10 +84,8 @@ def make_mask_image(r):
         r = r.astype(np.uint8)
         return Image.fromarray(r, 'L')
 
-    mask_w = make_mask_image(
-        np.arange(grid.overlap, dtype=np.float32).reshape((1, grid.overlap)).repeat(grid.tile_h, axis=0))
-    mask_h = make_mask_image(
-        np.arange(grid.overlap, dtype=np.float32).reshape((grid.overlap, 1)).repeat(grid.image_w, axis=1))
+    mask_w = make_mask_image(np.arange(grid.overlap, dtype=np.float32).reshape((1, grid.overlap)).repeat(grid.tile_h, axis=0))
+    mask_h = make_mask_image(np.arange(grid.overlap, dtype=np.float32).reshape((grid.overlap, 1)).repeat(grid.image_w, axis=1))
 
     combined_image = Image.new("RGB", (grid.image_w, grid.image_h))
     for y, h, row in grid.tiles:
@@ -130,12 +128,10 @@ def wrap(drawing, text, font, line_length):
 
     def draw_texts(drawing, draw_x, draw_y, lines):
         for i, line in enumerate(lines):
-            drawing.multiline_text((draw_x, draw_y + line.size[1] / 2), line.text, font=fnt,
-                                   fill=color_active if line.is_active else color_inactive, anchor="mm", align="center")
+            drawing.multiline_text((draw_x, draw_y + line.size[1] / 2), line.text, font=fnt, fill=color_active if line.is_active else color_inactive, anchor="mm", align="center")
 
             if not line.is_active:
-                drawing.line((draw_x - line.size[0] // 2, draw_y + line.size[1] // 2, draw_x + line.size[0] // 2,
-                              draw_y + line.size[1] // 2), fill=color_inactive, width=4)
+                drawing.line((draw_x - line.size[0] // 2, draw_y + line.size[1] // 2, draw_x + line.size[0] // 2, draw_y + line.size[1] // 2), fill=color_inactive, width=4)
 
             draw_y += line.size[1] + line_spacing
 
@@ -206,10 +202,8 @@ def draw_prompt_matrix(im, width, height, all_prompts):
     prompts_horiz = prompts[:boundary]
     prompts_vert = prompts[boundary:]
 
-    hor_texts = [[GridAnnotation(x, is_active=pos & (1 << i) != 0) for i, x in enumerate(prompts_horiz)] for pos in
-                 range(1 << len(prompts_horiz))]
-    ver_texts = [[GridAnnotation(x, is_active=pos & (1 << i) != 0) for i, x in enumerate(prompts_vert)] for pos in
-                 range(1 << len(prompts_vert))]
+    hor_texts = [[GridAnnotation(x, is_active=pos & (1 << i) != 0) for i, x in enumerate(prompts_horiz)] for pos in range(1 << len(prompts_horiz))]
+    ver_texts = [[GridAnnotation(x, is_active=pos & (1 << i) != 0) for i, x in enumerate(prompts_vert)] for pos in range(1 << len(prompts_vert))]
 
     return draw_grid_annotations(im, width, height, hor_texts, ver_texts)
 
@@ -259,13 +253,11 @@ def resize(im, w, h):
         if ratio < src_ratio:
             fill_height = height // 2 - src_h // 2
             res.paste(resized.resize((width, fill_height), box=(0, 0, width, 0)), box=(0, 0))
-            res.paste(resized.resize((width, fill_height), box=(0, resized.height, width, resized.height)),
-                      box=(0, fill_height + src_h))
+            res.paste(resized.resize((width, fill_height), box=(0, resized.height, width, resized.height)), box=(0, fill_height + src_h))
         elif ratio > src_ratio:
             fill_width = width // 2 - src_w // 2
             res.paste(resized.resize((fill_width, height), box=(0, 0, 0, height)), box=(0, 0))
-            res.paste(resized.resize((fill_width, height), box=(resized.width, 0, resized.width, height)),
-                      box=(fill_width + src_w, 0))
+            res.paste(resized.resize((fill_width, height), box=(resized.width, 0, resized.width, height)), box=(fill_width + src_w, 0))
 
     return res
 
@@ -300,17 +292,15 @@ def apply_filename_pattern(x, p, seed, prompt):
             words = [x for x in re_nonletters.split(prompt or "") if len(x) > 0]
             if len(words) == 0:
                 words = ["empty"]
-            x = x.replace("[prompt_words]",
-                          sanitize_filename_part(" ".join(words[0:max_prompt_words]), replace_spaces=False))
+            x = x.replace("[prompt_words]", sanitize_filename_part(" ".join(words[0:max_prompt_words]), replace_spaces=False))
 
     if p is not None:
         x = x.replace("[steps]", str(p.steps))
         x = x.replace("[cfg]", str(p.cfg_scale))
         x = x.replace("[width]", str(p.width))
         x = x.replace("[height]", str(p.height))
         x = x.replace("[styles]", sanitize_filename_part(", ".join(p.styles), replace_spaces=False))
-        x = x.replace("[sampler]",
-                      sanitize_filename_part(sd_samplers.samplers[p.sampler_index].name, replace_spaces=False))
+        x = x.replace("[sampler]", sanitize_filename_part(sd_samplers.samplers[p.sampler_index].name, replace_spaces=False))
 
     x = x.replace("[model_hash]", shared.sd_model.sd_model_hash)
     x = x.replace("[date]", datetime.date.today().isoformat())
@@ -336,8 +326,7 @@ def get_next_sequence_number(path, basename):
     prefix_length = len(basename)
     for p in os.listdir(path):
         if p.startswith(basename):
-            l = os.path.splitext(p[prefix_length:])[0].split(
-                '-')  # splits the filename (removing the basename first if one is defined, so the sequence number is always the first element)
+            l = os.path.splitext(p[prefix_length:])[0].split('-')  # splits the filename (removing the basename first if one is defined, so the sequence number is always the first element)
             try:
                 result = max(int(l[0]), result)
             except ValueError:
@@ -346,9 +335,7 @@ def get_next_sequence_number(path, basename):
     return result + 1
 
 
-def save_image(image, path, basename, seed=None, prompt=None, extension='png', info=None, short_filename=False,
-               no_prompt=False, grid=False, pnginfo_section_name='parameters', p=None, existing_info=None,
-               forced_filename=None, suffix=""):
+def save_image(image, path, basename, seed=None, prompt=None, extension='png', info=None, short_filename=False, no_prompt=False, grid=False, pnginfo_section_name='parameters', p=None, existing_info=None, forced_filename=None, suffix=""):
     if short_filename or prompt is None or seed is None:
         file_decoration = ""
     elif opts.save_to_dirs:

modules/ldsr_model_arch.py

@@ -125,7 +125,6 @@ def super_resolution(self, image, steps=100, target_scale=2, half_attention=Fals
         del model
         gc.collect()
         torch.cuda.empty_cache()
-        print(f'Processing finished!')
         return a