diff options
Diffstat (limited to 'modules/extras.py')
| -rw-r--r-- | modules/extras.py | 116 |
1 files changed, 82 insertions, 34 deletions
diff --git a/modules/extras.py b/modules/extras.py index 39dd3806..22c5a1c1 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -1,3 +1,4 @@ +import math
import os
import numpy as np
@@ -19,26 +20,43 @@ import gradio as gr cached_images = {}
-def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility):
+def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_dir, show_extras_results, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility):
devices.torch_gc()
imageArr = []
# Also keep track of original file names
imageNameArr = []
-
+ outputs = []
+
if extras_mode == 1:
#convert file to pillow image
for img in image_folder:
- image = Image.fromarray(np.array(Image.open(img)))
+ image = Image.open(img)
imageArr.append(image)
imageNameArr.append(os.path.splitext(img.orig_name)[0])
+ elif extras_mode == 2:
+ assert not shared.cmd_opts.hide_ui_dir_config, '--hide-ui-dir-config option must be disabled'
+
+ if input_dir == '':
+ return outputs, "Please select an input directory.", ''
+ image_list = [file for file in [os.path.join(input_dir, x) for x in sorted(os.listdir(input_dir))] if os.path.isfile(file)]
+ for img in image_list:
+ try:
+ image = Image.open(img)
+ except Exception:
+ continue
+ imageArr.append(image)
+ imageNameArr.append(img)
else:
imageArr.append(image)
imageNameArr.append(None)
- outpath = opts.outdir_samples or opts.outdir_extras_samples
+ if extras_mode == 2 and output_dir != '':
+ outpath = output_dir
+ else:
+ outpath = opts.outdir_samples or opts.outdir_extras_samples
- outputs = []
+
for image, image_name in zip(imageArr, imageNameArr):
if image is None:
return outputs, "Please select an input image.", ''
@@ -67,25 +85,35 @@ 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
+ if resize_mode == 1:
+ upscaling_resize = max(upscaling_resize_w/image.width, upscaling_resize_h/image.height)
+ crop_info = " (crop)" if upscaling_crop else ""
+ info += f"Resize to: {upscaling_resize_w:g}x{upscaling_resize_h:g}{crop_info}\n"
+
if upscaling_resize != 1.0:
- def upscale(image, scaler_index, resize):
+ def upscale(image, scaler_index, resize, mode, resize_w, resize_h, crop):
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
+ key = (resize, scaler_index, image.width, image.height, gfpgan_visibility, codeformer_visibility, codeformer_weight,
+ resize_mode, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop) + 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)
+ if mode == 1 and crop:
+ cropped = Image.new("RGB", (resize_w, resize_h))
+ cropped.paste(c, box=(resize_w // 2 - c.width // 2, resize_h // 2 - c.height // 2))
+ c = cropped
cached_images[key] = 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)
+ res = upscale(image, extras_upscaler_1, upscaling_resize, resize_mode, upscaling_resize_w, upscaling_resize_h, upscaling_crop)
if extras_upscaler_2 != 0 and extras_upscaler_2_visibility > 0:
- res2 = upscale(image, extras_upscaler_2, upscaling_resize)
+ res2 = upscale(image, extras_upscaler_2, upscaling_resize, resize_mode, upscaling_resize_w, upscaling_resize_h, upscaling_crop)
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)
@@ -93,16 +121,21 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v while len(cached_images) > 2:
del cached_images[next(iter(cached_images.keys()))]
+
+ if opts.use_original_name_batch and image_name != None:
+ basename = os.path.splitext(os.path.basename(image_name))[0]
+ else:
+ basename = ''
- images.save_image(image, path=outpath, basename="", seed=None, prompt=None, extension=opts.samples_format, info=info, short_filename=True,
- no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo,
- forced_filename=image_name if opts.use_original_name_batch else None)
+ images.save_image(image, path=outpath, basename=basename, seed=None, prompt=None, extension=opts.samples_format, info=info, short_filename=True,
+ no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=None)
if opts.enable_pnginfo:
image.info = existing_pnginfo
image.info["extras"] = info
- outputs.append(image)
+ if extras_mode != 2 or show_extras_results :
+ outputs.append(image)
devices.torch_gc()
@@ -149,48 +182,63 @@ def run_pnginfo(image): return '', geninfo, info
-def run_modelmerger(primary_model_name, secondary_model_name, interp_method, interp_amount, save_as_half, custom_name):
- # Linear interpolation (https://en.wikipedia.org/wiki/Linear_interpolation)
+def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_name, interp_method, multiplier, save_as_half, custom_name):
def weighted_sum(theta0, theta1, alpha):
return ((1 - alpha) * theta0) + (alpha * theta1)
- # Smoothstep (https://en.wikipedia.org/wiki/Smoothstep)
- def sigmoid(theta0, theta1, alpha):
- alpha = alpha * alpha * (3 - (2 * alpha))
- return theta0 + ((theta1 - theta0) * alpha)
+ def get_difference(theta1, theta2):
+ return theta1 - theta2
- # Inverse Smoothstep (https://en.wikipedia.org/wiki/Smoothstep)
- def inv_sigmoid(theta0, theta1, alpha):
- import math
- alpha = 0.5 - math.sin(math.asin(1.0 - 2.0 * alpha) / 3.0)
- return theta0 + ((theta1 - theta0) * alpha)
+ def add_difference(theta0, theta1_2_diff, alpha):
+ return theta0 + (alpha * theta1_2_diff)
primary_model_info = sd_models.checkpoints_list[primary_model_name]
secondary_model_info = sd_models.checkpoints_list[secondary_model_name]
+ teritary_model_info = sd_models.checkpoints_list.get(teritary_model_name, None)
print(f"Loading {primary_model_info.filename}...")
primary_model = torch.load(primary_model_info.filename, map_location='cpu')
+ theta_0 = sd_models.get_state_dict_from_checkpoint(primary_model)
print(f"Loading {secondary_model_info.filename}...")
secondary_model = torch.load(secondary_model_info.filename, map_location='cpu')
-
- theta_0 = sd_models.get_state_dict_from_checkpoint(primary_model)
theta_1 = sd_models.get_state_dict_from_checkpoint(secondary_model)
+ if teritary_model_info is not None:
+ print(f"Loading {teritary_model_info.filename}...")
+ teritary_model = torch.load(teritary_model_info.filename, map_location='cpu')
+ theta_2 = sd_models.get_state_dict_from_checkpoint(teritary_model)
+ else:
+ teritary_model = None
+ theta_2 = None
+
theta_funcs = {
- "Weighted Sum": weighted_sum,
- "Sigmoid": sigmoid,
- "Inverse Sigmoid": inv_sigmoid,
+ "Weighted sum": (None, weighted_sum),
+ "Add difference": (get_difference, add_difference),
}
- theta_func = theta_funcs[interp_method]
+ theta_func1, theta_func2 = theta_funcs[interp_method]
print(f"Merging...")
+
+ if theta_func1:
+ for key in tqdm.tqdm(theta_1.keys()):
+ if 'model' in key:
+ if key in theta_2:
+ t2 = theta_2.get(key, torch.zeros_like(theta_1[key]))
+ theta_1[key] = theta_func1(theta_1[key], t2)
+ else:
+ theta_1[key] = torch.zeros_like(theta_1[key])
+ del theta_2, teritary_model
+
for key in tqdm.tqdm(theta_0.keys()):
if 'model' in key and key in theta_1:
- theta_0[key] = theta_func(theta_0[key], theta_1[key], (float(1.0) - interp_amount)) # Need to reverse the interp_amount to match the desired mix ration in the merged checkpoint
+
+ theta_0[key] = theta_func2(theta_0[key], theta_1[key], multiplier)
+
if save_as_half:
theta_0[key] = theta_0[key].half()
-
+
+ # I believe this part should be discarded, but I'll leave it for now until I am sure
for key in theta_1.keys():
if 'model' in key and key not in theta_0:
theta_0[key] = theta_1[key]
@@ -199,7 +247,7 @@ def run_modelmerger(primary_model_name, secondary_model_name, interp_method, int ckpt_dir = shared.cmd_opts.ckpt_dir or sd_models.model_path
- filename = primary_model_info.model_name + '_' + str(round(interp_amount, 2)) + '-' + secondary_model_info.model_name + '_' + str(round((float(1.0) - interp_amount), 2)) + '-' + interp_method.replace(" ", "_") + '-merged.ckpt'
+ filename = primary_model_info.model_name + '_' + str(round(1-multiplier, 2)) + '-' + secondary_model_info.model_name + '_' + str(round(multiplier, 2)) + '-' + interp_method.replace(" ", "_") + '-merged.ckpt'
filename = filename if custom_name == '' else (custom_name + '.ckpt')
output_modelname = os.path.join(ckpt_dir, filename)
@@ -209,4 +257,4 @@ def run_modelmerger(primary_model_name, secondary_model_name, interp_method, int sd_models.list_models()
print(f"Checkpoint saved.")
- return ["Checkpoint saved to " + output_modelname] + [gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(3)]
+ return ["Checkpoint saved to " + output_modelname] + [gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)]
|