From 47033afa5c08e72b622348b0bcfd71fd1a66e2cb Mon Sep 17 00:00:00 2001 From: AngelBottomless Date: Tue, 5 Sep 2023 22:38:02 +0900 Subject: Fix preview for textual inversion training --- modules/textual_inversion/textual_inversion.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'modules/textual_inversion') diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index aa79dc09..401a0a2a 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -386,7 +386,7 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat assert log_directory, "Log directory is empty" -def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height): +def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_name, preview_cfg_scale, preview_seed, preview_width, preview_height): from modules import processing save_embedding_every = save_embedding_every or 0 @@ -590,7 +590,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st p.prompt = preview_prompt p.negative_prompt = preview_negative_prompt p.steps = preview_steps - p.sampler_name = sd_samplers.samplers[preview_sampler_index].name + p.sampler_name = sd_samplers.samplers_map[preview_sampler_name.lower()] p.cfg_scale = preview_cfg_scale p.seed = preview_seed p.width = preview_width -- cgit v1.2.3 From a8cbe50c9fa324ed887089e4333452ecc4355c92 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 14 Oct 2023 12:14:56 +0300 Subject: remove duplicated code --- extensions-builtin/Lora/networks.py | 31 +---------- modules/textual_inversion/textual_inversion.py | 74 ++++++++++++++------------ 2 files changed, 42 insertions(+), 63 deletions(-) (limited to 'modules/textual_inversion') diff --git a/extensions-builtin/Lora/networks.py b/extensions-builtin/Lora/networks.py index 12f70576..d5f0f9f1 100644 --- a/extensions-builtin/Lora/networks.py +++ b/extensions-builtin/Lora/networks.py @@ -15,7 +15,7 @@ import torch from typing import Union from modules import shared, devices, sd_models, errors, scripts, sd_hijack -from modules.textual_inversion.textual_inversion import Embedding +import modules.textual_inversion.textual_inversion as textual_inversion from lora_logger import logger @@ -210,34 +210,7 @@ def load_network(name, network_on_disk): embeddings = {} for emb_name, data in bundle_embeddings.items(): - # textual inversion embeddings - if 'string_to_param' in data: - param_dict = data['string_to_param'] - param_dict = getattr(param_dict, '_parameters', param_dict) # fix for torch 1.12.1 loading saved file from torch 1.11 - assert len(param_dict) == 1, 'embedding file has multiple terms in it' - emb = next(iter(param_dict.items()))[1] - vec = emb.detach().to(devices.device, dtype=torch.float32) - shape = vec.shape[-1] - vectors = vec.shape[0] - elif type(data) == dict and 'clip_g' in data and 'clip_l' in data: # SDXL embedding - vec = {k: v.detach().to(devices.device, dtype=torch.float32) for k, v in data.items()} - shape = data['clip_g'].shape[-1] + data['clip_l'].shape[-1] - vectors = data['clip_g'].shape[0] - elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor: # diffuser concepts - assert len(data.keys()) == 1, 'embedding file has multiple terms in it' - - emb = next(iter(data.values())) - if len(emb.shape) == 1: - emb = emb.unsqueeze(0) - vec = emb.detach().to(devices.device, dtype=torch.float32) - shape = vec.shape[-1] - vectors = vec.shape[0] - else: - raise Exception(f"Couldn't identify {emb_name} in lora: {name} as neither textual inversion embedding nor diffuser concept.") - - embedding = Embedding(vec, emb_name) - embedding.vectors = vectors - embedding.shape = shape + embedding = textual_inversion.create_embedding_from_data(data, emb_name, filename=network_on_disk.filename + "/" + emb_name) embedding.loaded = None embeddings[emb_name] = embedding diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 401a0a2a..04dda585 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -181,40 +181,7 @@ class EmbeddingDatabase: else: return - - # textual inversion embeddings - if 'string_to_param' in data: - param_dict = data['string_to_param'] - param_dict = getattr(param_dict, '_parameters', param_dict) # fix for torch 1.12.1 loading saved file from torch 1.11 - assert len(param_dict) == 1, 'embedding file has multiple terms in it' - emb = next(iter(param_dict.items()))[1] - vec = emb.detach().to(devices.device, dtype=torch.float32) - shape = vec.shape[-1] - vectors = vec.shape[0] - elif type(data) == dict and 'clip_g' in data and 'clip_l' in data: # SDXL embedding - vec = {k: v.detach().to(devices.device, dtype=torch.float32) for k, v in data.items()} - shape = data['clip_g'].shape[-1] + data['clip_l'].shape[-1] - vectors = data['clip_g'].shape[0] - elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor: # diffuser concepts - assert len(data.keys()) == 1, 'embedding file has multiple terms in it' - - emb = next(iter(data.values())) - if len(emb.shape) == 1: - emb = emb.unsqueeze(0) - vec = emb.detach().to(devices.device, dtype=torch.float32) - shape = vec.shape[-1] - vectors = vec.shape[0] - else: - raise Exception(f"Couldn't identify {filename} as neither textual inversion embedding nor diffuser concept.") - - embedding = Embedding(vec, name) - embedding.step = data.get('step', None) - embedding.sd_checkpoint = data.get('sd_checkpoint', None) - embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None) - embedding.vectors = vectors - embedding.shape = shape - embedding.filename = path - embedding.set_hash(hashes.sha256(embedding.filename, "textual_inversion/" + name) or '') + embedding = create_embedding_from_data(data, name, filename=filename, filepath=path) if self.expected_shape == -1 or self.expected_shape == embedding.shape: self.register_embedding(embedding, shared.sd_model) @@ -313,6 +280,45 @@ def create_embedding(name, num_vectors_per_token, overwrite_old, init_text='*'): return fn +def create_embedding_from_data(data, name, filename='unknown embedding file', filepath=None): + if 'string_to_param' in data: # textual inversion embeddings + param_dict = data['string_to_param'] + param_dict = getattr(param_dict, '_parameters', param_dict) # fix for torch 1.12.1 loading saved file from torch 1.11 + assert len(param_dict) == 1, 'embedding file has multiple terms in it' + emb = next(iter(param_dict.items()))[1] + vec = emb.detach().to(devices.device, dtype=torch.float32) + shape = vec.shape[-1] + vectors = vec.shape[0] + elif type(data) == dict and 'clip_g' in data and 'clip_l' in data: # SDXL embedding + vec = {k: v.detach().to(devices.device, dtype=torch.float32) for k, v in data.items()} + shape = data['clip_g'].shape[-1] + data['clip_l'].shape[-1] + vectors = data['clip_g'].shape[0] + elif type(data) == dict and type(next(iter(data.values()))) == torch.Tensor: # diffuser concepts + assert len(data.keys()) == 1, 'embedding file has multiple terms in it' + + emb = next(iter(data.values())) + if len(emb.shape) == 1: + emb = emb.unsqueeze(0) + vec = emb.detach().to(devices.device, dtype=torch.float32) + shape = vec.shape[-1] + vectors = vec.shape[0] + else: + raise Exception(f"Couldn't identify {filename} as neither textual inversion embedding nor diffuser concept.") + + embedding = Embedding(vec, name) + embedding.step = data.get('step', None) + embedding.sd_checkpoint = data.get('sd_checkpoint', None) + embedding.sd_checkpoint_name = data.get('sd_checkpoint_name', None) + embedding.vectors = vectors + embedding.shape = shape + + if filepath: + embedding.filename = filepath + embedding.set_hash(hashes.sha256(filepath, "textual_inversion/" + name) or '') + + return embedding + + def write_loss(log_directory, filename, step, epoch_len, values): if shared.opts.training_write_csv_every == 0: return -- cgit v1.2.3 From 03ee297aa22296ea12b965fc1cb11aa46375d372 Mon Sep 17 00:00:00 2001 From: w-e-w <40751091+w-e-w@users.noreply.github.com> Date: Mon, 27 Nov 2023 17:26:16 +0900 Subject: fix Auto focal point crop for opencv >= 4.8.x autocrop.download_and_cache_models in opencv >= 4.8 the face detection model was updated download the base on opencv version returns the model path or raise exception --- modules/textual_inversion/autocrop.py | 29 ++++++++++++++++------------- modules/textual_inversion/preprocess.py | 4 ++-- 2 files changed, 18 insertions(+), 15 deletions(-) (limited to 'modules/textual_inversion') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 1675e39a..051be118 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -3,6 +3,8 @@ import requests import os import numpy as np from PIL import ImageDraw +from modules import paths_internal +from pkg_resources import parse_version GREEN = "#0F0" BLUE = "#00F" @@ -294,22 +296,23 @@ def is_square(w, h): return w == h -def download_and_cache_models(dirname): - download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true' - model_file_name = 'face_detection_yunet.onnx' +model_dir_opencv = os.path.join(paths_internal.models_path, 'opencv') +if parse_version(cv2.__version__) >= parse_version('4.8'): + model_file_path = os.path.join(model_dir_opencv, 'face_detection_yunet_2023mar.onnx') + model_url = 'https://github.com/opencv/opencv_zoo/blob/b6e370b10f641879a87890d44e42173077154a05/models/face_detection_yunet/face_detection_yunet_2023mar.onnx?raw=true' +else: + model_file_path = os.path.join(model_dir_opencv, 'face_detection_yunet.onnx') + model_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true' - os.makedirs(dirname, exist_ok=True) - cache_file = os.path.join(dirname, model_file_name) - if not os.path.exists(cache_file): - print(f"downloading face detection model from '{download_url}' to '{cache_file}'") - response = requests.get(download_url) - with open(cache_file, "wb") as f: +def download_and_cache_models(): + if not os.path.exists(model_file_path): + os.makedirs(model_dir_opencv, exist_ok=True) + print(f"downloading face detection model from '{model_url}' to '{model_file_path}'") + response = requests.get(model_url) + with open(model_file_path, "wb") as f: f.write(response.content) - - if os.path.exists(cache_file): - return cache_file - return None + return model_file_path class PointOfInterest: diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index dbd856bd..789fa083 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -3,7 +3,7 @@ from PIL import Image, ImageOps import math import tqdm -from modules import paths, shared, images, deepbooru +from modules import shared, images, deepbooru from modules.textual_inversion import autocrop @@ -196,7 +196,7 @@ def preprocess_work(process_src, process_dst, process_width, process_height, pre dnn_model_path = None try: - dnn_model_path = autocrop.download_and_cache_models(os.path.join(paths.models_path, "opencv")) + dnn_model_path = autocrop.download_and_cache_models() except Exception as e: print("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", e) -- cgit v1.2.3 From d608926f817b279d16b39a7875beec80d010a988 Mon Sep 17 00:00:00 2001 From: w-e-w <40751091+w-e-w@users.noreply.github.com> Date: Tue, 28 Nov 2023 12:12:27 +0900 Subject: reformat file with uniform indentation --- modules/textual_inversion/autocrop.py | 210 +++++++++++++++++----------------- 1 file changed, 106 insertions(+), 104 deletions(-) (limited to 'modules/textual_inversion') diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 051be118..e223a2e0 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -27,7 +27,6 @@ def crop_image(im, settings): elif is_portrait(settings.crop_width, settings.crop_height): scale_by = settings.crop_height / im.height - im = im.resize((int(im.width * scale_by), int(im.height * scale_by))) im_debug = im.copy() @@ -71,6 +70,7 @@ def crop_image(im, settings): return results + def focal_point(im, settings): corner_points = image_corner_points(im, settings) if settings.corner_points_weight > 0 else [] entropy_points = image_entropy_points(im, settings) if settings.entropy_points_weight > 0 else [] @@ -80,118 +80,120 @@ def focal_point(im, settings): weight_pref_total = 0 if corner_points: - weight_pref_total += settings.corner_points_weight + weight_pref_total += settings.corner_points_weight if entropy_points: - weight_pref_total += settings.entropy_points_weight + weight_pref_total += settings.entropy_points_weight if face_points: - weight_pref_total += settings.face_points_weight + weight_pref_total += settings.face_points_weight corner_centroid = None if corner_points: - corner_centroid = centroid(corner_points) - corner_centroid.weight = settings.corner_points_weight / weight_pref_total - pois.append(corner_centroid) + corner_centroid = centroid(corner_points) + corner_centroid.weight = settings.corner_points_weight / weight_pref_total + pois.append(corner_centroid) entropy_centroid = None if entropy_points: - entropy_centroid = centroid(entropy_points) - entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total - pois.append(entropy_centroid) + entropy_centroid = centroid(entropy_points) + entropy_centroid.weight = settings.entropy_points_weight / weight_pref_total + pois.append(entropy_centroid) face_centroid = None if face_points: - face_centroid = centroid(face_points) - face_centroid.weight = settings.face_points_weight / weight_pref_total - pois.append(face_centroid) + face_centroid = centroid(face_points) + face_centroid.weight = settings.face_points_weight / weight_pref_total + pois.append(face_centroid) average_point = poi_average(pois, settings) if settings.annotate_image: - d = ImageDraw.Draw(im) - max_size = min(im.width, im.height) * 0.07 - if corner_centroid is not None: - color = BLUE - box = corner_centroid.bounding(max_size * corner_centroid.weight) - d.text((box[0], box[1]-15), f"Edge: {corner_centroid.weight:.02f}", fill=color) - d.ellipse(box, outline=color) - if len(corner_points) > 1: - for f in corner_points: - d.rectangle(f.bounding(4), outline=color) - if entropy_centroid is not None: - color = "#ff0" - box = entropy_centroid.bounding(max_size * entropy_centroid.weight) - d.text((box[0], box[1]-15), f"Entropy: {entropy_centroid.weight:.02f}", fill=color) - d.ellipse(box, outline=color) - if len(entropy_points) > 1: - for f in entropy_points: - d.rectangle(f.bounding(4), outline=color) - if face_centroid is not None: - color = RED - box = face_centroid.bounding(max_size * face_centroid.weight) - d.text((box[0], box[1]-15), f"Face: {face_centroid.weight:.02f}", fill=color) - d.ellipse(box, outline=color) - if len(face_points) > 1: - for f in face_points: - d.rectangle(f.bounding(4), outline=color) - - d.ellipse(average_point.bounding(max_size), outline=GREEN) + d = ImageDraw.Draw(im) + max_size = min(im.width, im.height) * 0.07 + if corner_centroid is not None: + color = BLUE + box = corner_centroid.bounding(max_size * corner_centroid.weight) + d.text((box[0], box[1] - 15), f"Edge: {corner_centroid.weight:.02f}", fill=color) + d.ellipse(box, outline=color) + if len(corner_points) > 1: + for f in corner_points: + d.rectangle(f.bounding(4), outline=color) + if entropy_centroid is not None: + color = "#ff0" + box = entropy_centroid.bounding(max_size * entropy_centroid.weight) + d.text((box[0], box[1] - 15), f"Entropy: {entropy_centroid.weight:.02f}", fill=color) + d.ellipse(box, outline=color) + if len(entropy_points) > 1: + for f in entropy_points: + d.rectangle(f.bounding(4), outline=color) + if face_centroid is not None: + color = RED + box = face_centroid.bounding(max_size * face_centroid.weight) + d.text((box[0], box[1] - 15), f"Face: {face_centroid.weight:.02f}", fill=color) + d.ellipse(box, outline=color) + if len(face_points) > 1: + for f in face_points: + d.rectangle(f.bounding(4), outline=color) + + d.ellipse(average_point.bounding(max_size), outline=GREEN) return average_point def image_face_points(im, settings): if settings.dnn_model_path is not None: - detector = cv2.FaceDetectorYN.create( - settings.dnn_model_path, - "", - (im.width, im.height), - 0.9, # score threshold - 0.3, # nms threshold - 5000 # keep top k before nms - ) - faces = detector.detect(np.array(im)) - results = [] - if faces[1] is not None: - for face in faces[1]: - x = face[0] - y = face[1] - w = face[2] - h = face[3] - results.append( - PointOfInterest( - int(x + (w * 0.5)), # face focus left/right is center - int(y + (h * 0.33)), # face focus up/down is close to the top of the head - size = w, - weight = 1/len(faces[1]) - ) - ) - return results + detector = cv2.FaceDetectorYN.create( + settings.dnn_model_path, + "", + (im.width, im.height), + 0.9, # score threshold + 0.3, # nms threshold + 5000 # keep top k before nms + ) + faces = detector.detect(np.array(im)) + results = [] + if faces[1] is not None: + for face in faces[1]: + x = face[0] + y = face[1] + w = face[2] + h = face[3] + results.append( + PointOfInterest( + int(x + (w * 0.5)), # face focus left/right is center + int(y + (h * 0.33)), # face focus up/down is close to the top of the head + size=w, + weight=1 / len(faces[1]) + ) + ) + return results else: - np_im = np.array(im) - gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY) - - tries = [ - [ f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05 ], - [ f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05 ] - ] - for t in tries: - classifier = cv2.CascadeClassifier(t[0]) - minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side - try: - faces = classifier.detectMultiScale(gray, scaleFactor=1.1, - minNeighbors=7, minSize=(minsize, minsize), flags=cv2.CASCADE_SCALE_IMAGE) - except Exception: - continue - - if faces: - rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces] - return [PointOfInterest((r[0] +r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0]-r[2]), weight=1/len(rects)) for r in rects] + np_im = np.array(im) + gray = cv2.cvtColor(np_im, cv2.COLOR_BGR2GRAY) + + tries = [ + [f'{cv2.data.haarcascades}haarcascade_eye.xml', 0.01], + [f'{cv2.data.haarcascades}haarcascade_frontalface_default.xml', 0.05], + [f'{cv2.data.haarcascades}haarcascade_profileface.xml', 0.05], + [f'{cv2.data.haarcascades}haarcascade_frontalface_alt.xml', 0.05], + [f'{cv2.data.haarcascades}haarcascade_frontalface_alt2.xml', 0.05], + [f'{cv2.data.haarcascades}haarcascade_frontalface_alt_tree.xml', 0.05], + [f'{cv2.data.haarcascades}haarcascade_eye_tree_eyeglasses.xml', 0.05], + [f'{cv2.data.haarcascades}haarcascade_upperbody.xml', 0.05] + ] + for t in tries: + classifier = cv2.CascadeClassifier(t[0]) + minsize = int(min(im.width, im.height) * t[1]) # at least N percent of the smallest side + try: + faces = classifier.detectMultiScale(gray, scaleFactor=1.1, + minNeighbors=7, minSize=(minsize, minsize), + flags=cv2.CASCADE_SCALE_IMAGE) + except Exception: + continue + + if faces: + rects = [[f[0], f[1], f[0] + f[2], f[1] + f[3]] for f in faces] + return [PointOfInterest((r[0] + r[2]) // 2, (r[1] + r[3]) // 2, size=abs(r[0] - r[2]), + weight=1 / len(rects)) for r in rects] return [] @@ -200,7 +202,7 @@ def image_corner_points(im, settings): # naive attempt at preventing focal points from collecting at watermarks near the bottom gd = ImageDraw.Draw(grayscale) - gd.rectangle([0, im.height*.9, im.width, im.height], fill="#999") + gd.rectangle([0, im.height * .9, im.width, im.height], fill="#999") np_im = np.array(grayscale) @@ -208,7 +210,7 @@ def image_corner_points(im, settings): np_im, maxCorners=100, qualityLevel=0.04, - minDistance=min(grayscale.width, grayscale.height)*0.06, + minDistance=min(grayscale.width, grayscale.height) * 0.06, useHarrisDetector=False, ) @@ -217,8 +219,8 @@ def image_corner_points(im, settings): focal_points = [] for point in points: - x, y = point.ravel() - focal_points.append(PointOfInterest(x, y, size=4, weight=1/len(points))) + x, y = point.ravel() + focal_points.append(PointOfInterest(x, y, size=4, weight=1 / len(points))) return focal_points @@ -227,13 +229,13 @@ def image_entropy_points(im, settings): landscape = im.height < im.width portrait = im.height > im.width if landscape: - move_idx = [0, 2] - move_max = im.size[0] + move_idx = [0, 2] + move_max = im.size[0] elif portrait: - move_idx = [1, 3] - move_max = im.size[1] + move_idx = [1, 3] + move_max = im.size[1] else: - return [] + return [] e_max = 0 crop_current = [0, 0, settings.crop_width, settings.crop_height] @@ -243,14 +245,14 @@ def image_entropy_points(im, settings): e = image_entropy(crop) if (e > e_max): - e_max = e - crop_best = list(crop_current) + e_max = e + crop_best = list(crop_current) crop_current[move_idx[0]] += 4 crop_current[move_idx[1]] += 4 - x_mid = int(crop_best[0] + settings.crop_width/2) - y_mid = int(crop_best[1] + settings.crop_height/2) + x_mid = int(crop_best[0] + settings.crop_width / 2) + y_mid = int(crop_best[1] + settings.crop_height / 2) return [PointOfInterest(x_mid, y_mid, size=25, weight=1.0)] -- cgit v1.2.3 From 11d23e8ca55c097ecfa255a05b63f194e25f08be Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Sat, 2 Dec 2023 18:01:11 +0300 Subject: remove Train/Preprocessing tab and put all its functionality into extras batch images mode --- javascript/ui.js | 17 ++ modules/api/api.py | 15 -- modules/api/models.py | 3 - modules/postprocessing.py | 92 +++++++--- modules/scripts_postprocessing.py | 86 ++++++++- modules/shared_options.py | 1 + modules/textual_inversion/preprocess.py | 232 ------------------------ modules/textual_inversion/ui.py | 7 - modules/ui.py | 107 ----------- modules/ui_postprocessing.py | 16 +- modules/ui_toprow.py | 6 +- scripts/postprocessing_caption.py | 30 +++ scripts/postprocessing_codeformer.py | 16 +- scripts/postprocessing_create_flipped_copies.py | 32 ++++ scripts/postprocessing_focal_crop.py | 54 ++++++ scripts/postprocessing_gfpgan.py | 13 +- scripts/postprocessing_split_oversized.py | 71 ++++++++ scripts/postprocessing_upscale.py | 12 ++ scripts/processing_autosized_crop.py | 64 +++++++ 19 files changed, 460 insertions(+), 414 deletions(-) delete mode 100644 modules/textual_inversion/preprocess.py create mode 100644 scripts/postprocessing_caption.py create mode 100644 scripts/postprocessing_create_flipped_copies.py create mode 100644 scripts/postprocessing_focal_crop.py create mode 100644 scripts/postprocessing_split_oversized.py create mode 100644 scripts/processing_autosized_crop.py (limited to 'modules/textual_inversion') diff --git a/javascript/ui.js b/javascript/ui.js index 2e262602..410fc44e 100644 --- a/javascript/ui.js +++ b/javascript/ui.js @@ -170,6 +170,23 @@ function submit_img2img() { return res; } +function submit_extras() { + showSubmitButtons('extras', false); + + var id = randomId(); + + requestProgress(id, gradioApp().getElementById('extras_gallery_container'), gradioApp().getElementById('extras_gallery'), function() { + showSubmitButtons('extras', true); + }); + + var res = create_submit_args(arguments); + + res[0] = id; + + console.log(res); + return res; +} + function restoreProgressTxt2img() { showRestoreProgressButton("txt2img", false); var id = localGet("txt2img_task_id"); diff --git a/modules/api/api.py b/modules/api/api.py index 09083874..b3d74e51 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -22,7 +22,6 @@ from modules.api import models from modules.shared import opts from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images from modules.textual_inversion.textual_inversion import create_embedding, train_embedding -from modules.textual_inversion.preprocess import preprocess from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork from PIL import PngImagePlugin, Image from modules.sd_models_config import find_checkpoint_config_near_filename @@ -235,7 +234,6 @@ class Api: self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"]) self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse) self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse) - self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse) self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=models.TrainResponse) self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=models.TrainResponse) self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=models.MemoryResponse) @@ -675,19 +673,6 @@ class Api: finally: shared.state.end() - def preprocess(self, args: dict): - try: - shared.state.begin(job="preprocess") - preprocess(**args) # quick operation unless blip/booru interrogation is enabled - shared.state.end() - return models.PreprocessResponse(info='preprocess complete') - except KeyError as e: - return models.PreprocessResponse(info=f"preprocess error: invalid token: {e}") - except Exception as e: - return models.PreprocessResponse(info=f"preprocess error: {e}") - finally: - shared.state.end() - def train_embedding(self, args: dict): try: shared.state.begin(job="train_embedding") diff --git a/modules/api/models.py b/modules/api/models.py index a0d80af8..33894b3e 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -202,9 +202,6 @@ class TrainResponse(BaseModel): class CreateResponse(BaseModel): info: str = Field(title="Create info", description="Response string from create embedding or hypernetwork task.") -class PreprocessResponse(BaseModel): - info: str = Field(title="Preprocess info", description="Response string from preprocessing task.") - fields = {} for key, metadata in opts.data_labels.items(): value = opts.data.get(key) diff --git a/modules/postprocessing.py b/modules/postprocessing.py index 0a134ee4..3c85a74c 100644 --- a/modules/postprocessing.py +++ b/modules/postprocessing.py @@ -6,7 +6,7 @@ from modules import shared, images, devices, scripts, scripts_postprocessing, ui from modules.shared import opts -def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, show_extras_results, *args, save_output: bool = True): +def run_postprocessing(id_task, extras_mode, image, image_folder, input_dir, output_dir, show_extras_results, *args, save_output: bool = True): devices.torch_gc() shared.state.begin(job="extras") @@ -29,11 +29,7 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, image_list = shared.listfiles(input_dir) for filename in image_list: - try: - image = Image.open(filename) - except Exception: - continue - yield image, filename + yield filename, filename else: assert image, 'image not selected' yield image, None @@ -45,37 +41,85 @@ def run_postprocessing(extras_mode, image, image_folder, input_dir, output_dir, infotext = '' - for image_data, name in get_images(extras_mode, image, image_folder, input_dir): + data_to_process = list(get_images(extras_mode, image, image_folder, input_dir)) + shared.state.job_count = len(data_to_process) + + for image_placeholder, name in data_to_process: image_data: Image.Image + shared.state.nextjob() shared.state.textinfo = name + shared.state.skipped = False + + if shared.state.interrupted: + break + + if isinstance(image_placeholder, str): + try: + image_data = Image.open(image_placeholder) + except Exception: + continue + else: + image_data = image_placeholder + + shared.state.assign_current_image(image_data) parameters, existing_pnginfo = images.read_info_from_image(image_data) if parameters: existing_pnginfo["parameters"] = parameters - pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB")) + initial_pp = scripts_postprocessing.PostprocessedImage(image_data.convert("RGB")) - scripts.scripts_postproc.run(pp, args) + scripts.scripts_postproc.run(initial_pp, args) - if opts.use_original_name_batch and name is not None: - basename = os.path.splitext(os.path.basename(name))[0] - forced_filename = basename - else: - basename = '' - forced_filename = None + if shared.state.skipped: + continue + + used_suffixes = {} + for pp in [initial_pp, *initial_pp.extra_images]: + suffix = pp.get_suffix(used_suffixes) + + if opts.use_original_name_batch and name is not None: + basename = os.path.splitext(os.path.basename(name))[0] + forced_filename = basename + suffix + else: + basename = '' + forced_filename = None + + infotext = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in pp.info.items() if v is not None]) + + if opts.enable_pnginfo: + pp.image.info = existing_pnginfo + pp.image.info["postprocessing"] = infotext + + if save_output: + fullfn, _ = images.save_image(pp.image, path=outpath, basename=basename, extension=opts.samples_format, info=infotext, short_filename=True, no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=forced_filename, suffix=suffix) - infotext = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in pp.info.items() if v is not None]) + if pp.caption: + caption_filename = os.path.splitext(fullfn)[0] + ".txt" + if os.path.isfile(caption_filename): + with open(caption_filename, encoding="utf8") as file: + existing_caption = file.read().strip() + else: + existing_caption = "" - if opts.enable_pnginfo: - pp.image.info = existing_pnginfo - pp.image.info["postprocessing"] = infotext + action = shared.opts.postprocessing_existing_caption_action + if action == 'Prepend' and existing_caption: + caption = f"{existing_caption} {pp.caption}" + elif action == 'Append' and existing_caption: + caption = f"{pp.caption} {existing_caption}" + elif action == 'Keep' and existing_caption: + caption = existing_caption + else: + caption = pp.caption - if save_output: - images.save_image(pp.image, path=outpath, basename=basename, extension=opts.samples_format, info=infotext, short_filename=True, no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=forced_filename) + caption = caption.strip() + if caption: + with open(caption_filename, "w", encoding="utf8") as file: + file.write(caption) - if extras_mode != 2 or show_extras_results: - outputs.append(pp.image) + if extras_mode != 2 or show_extras_results: + outputs.append(pp.image) image_data.close() @@ -99,9 +143,11 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_ "upscaler_2_visibility": extras_upscaler_2_visibility, }, "GFPGAN": { + "enable": True, "gfpgan_visibility": gfpgan_visibility, }, "CodeFormer": { + "enable": True, "codeformer_visibility": codeformer_visibility, "codeformer_weight": codeformer_weight, }, diff --git a/modules/scripts_postprocessing.py b/modules/scripts_postprocessing.py index bac1335d..901cad08 100644 --- a/modules/scripts_postprocessing.py +++ b/modules/scripts_postprocessing.py @@ -1,13 +1,56 @@ +import dataclasses import os import gradio as gr from modules import errors, shared +@dataclasses.dataclass +class PostprocessedImageSharedInfo: + target_width: int = None + target_height: int = None + + class PostprocessedImage: def __init__(self, image): self.image = image self.info = {} + self.shared = PostprocessedImageSharedInfo() + self.extra_images = [] + self.nametags = [] + self.disable_processing = False + self.caption = None + + def get_suffix(self, used_suffixes=None): + used_suffixes = {} if used_suffixes is None else used_suffixes + suffix = "-".join(self.nametags) + if suffix: + suffix = "-" + suffix + + if suffix not in used_suffixes: + used_suffixes[suffix] = 1 + return suffix + + for i in range(1, 100): + proposed_suffix = suffix + "-" + str(i) + + if proposed_suffix not in used_suffixes: + used_suffixes[proposed_suffix] = 1 + return proposed_suffix + + return suffix + + def create_copy(self, new_image, *, nametags=None, disable_processing=False): + pp = PostprocessedImage(new_image) + pp.shared = self.shared + pp.nametags = self.nametags.copy() + pp.info = self.info.copy() + pp.disable_processing = disable_processing + + if nametags is not None: + pp.nametags += nametags + + return pp class ScriptPostprocessing: @@ -42,10 +85,17 @@ class ScriptPostprocessing: pass - def image_changed(self): - pass + def process_firstpass(self, pp: PostprocessedImage, **args): + """ + Called for all scripts before calling process(). Scripts can examine the image here and set fields + of the pp object to communicate things to other scripts. + args contains a dictionary with all values returned by components from ui() + """ + pass + def image_changed(self): + pass def wrap_call(func, filename, funcname, *args, default=None, **kwargs): @@ -118,16 +168,42 @@ class ScriptPostprocessingRunner: return inputs def run(self, pp: PostprocessedImage, args): - for script in self.scripts_in_preferred_order(): - shared.state.job = script.name + scripts = [] + for script in self.scripts_in_preferred_order(): script_args = args[script.args_from:script.args_to] process_args = {} for (name, _component), value in zip(script.controls.items(), script_args): process_args[name] = value - script.process(pp, **process_args) + scripts.append((script, process_args)) + + for script, process_args in scripts: + script.process_firstpass(pp, **process_args) + + all_images = [pp] + + for script, process_args in scripts: + if shared.state.skipped: + break + + shared.state.job = script.name + + for single_image in all_images.copy(): + + if not single_image.disable_processing: + script.process(single_image, **process_args) + + for extra_image in single_image.extra_images: + if not isinstance(extra_image, PostprocessedImage): + extra_image = single_image.create_copy(extra_image) + + all_images.append(extra_image) + + single_image.extra_images.clear() + + pp.extra_images = all_images[1:] def create_args_for_run(self, scripts_args): if not self.ui_created: diff --git a/modules/shared_options.py b/modules/shared_options.py index d8a27180..859dee40 100644 --- a/modules/shared_options.py +++ b/modules/shared_options.py @@ -357,6 +357,7 @@ options_templates.update(options_section(('postprocessing', "Postprocessing", "p 'postprocessing_enable_in_main_ui': OptionInfo([], "Enable postprocessing operations in txt2img and img2img tabs", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}), 'postprocessing_operation_order': OptionInfo([], "Postprocessing operation order", ui_components.DropdownMulti, lambda: {"choices": [x.name for x in shared_items.postprocessing_scripts()]}), 'upscaling_max_images_in_cache': OptionInfo(5, "Maximum number of images in upscaling cache", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}), + 'postprocessing_existing_caption_action': OptionInfo("Ignore", "Action for existing captions", gr.Radio, {"choices": ["Ignore", "Keep", "Prepend", "Append"]}).info("when generating captions using postprocessing; Ignore = use generated; Keep = use original; Prepend/Append = combine both"), })) options_templates.update(options_section((None, "Hidden options"), { diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py deleted file mode 100644 index 789fa083..00000000 --- a/modules/textual_inversion/preprocess.py +++ /dev/null @@ -1,232 +0,0 @@ -import os -from PIL import Image, ImageOps -import math -import tqdm - -from modules import shared, images, deepbooru -from modules.textual_inversion import autocrop - - -def preprocess(id_task, process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.15, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None): - try: - if process_caption: - shared.interrogator.load() - - if process_caption_deepbooru: - deepbooru.model.start() - - preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru, split_threshold, overlap_ratio, process_focal_crop, process_focal_crop_face_weight, process_focal_crop_entropy_weight, process_focal_crop_edges_weight, process_focal_crop_debug, process_multicrop, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold) - - finally: - - if process_caption: - shared.interrogator.send_blip_to_ram() - - if process_caption_deepbooru: - deepbooru.model.stop() - - -def listfiles(dirname): - return os.listdir(dirname) - - -class PreprocessParams: - src = None - dstdir = None - subindex = 0 - flip = False - process_caption = False - process_caption_deepbooru = False - preprocess_txt_action = None - - -def save_pic_with_caption(image, index, params: PreprocessParams, existing_caption=None): - caption = "" - - if params.process_caption: - caption += shared.interrogator.generate_caption(image) - - if params.process_caption_deepbooru: - if caption: - caption += ", " - caption += deepbooru.model.tag_multi(image) - - filename_part = params.src - filename_part = os.path.splitext(filename_part)[0] - filename_part = os.path.basename(filename_part) - - basename = f"{index:05}-{params.subindex}-{filename_part}" - image.save(os.path.join(params.dstdir, f"{basename}.png")) - - if params.preprocess_txt_action == 'prepend' and existing_caption: - caption = f"{existing_caption} {caption}" - elif params.preprocess_txt_action == 'append' and existing_caption: - caption = f"{caption} {existing_caption}" - elif params.preprocess_txt_action == 'copy' and existing_caption: - caption = existing_caption - - caption = caption.strip() - - if caption: - with open(os.path.join(params.dstdir, f"{basename}.txt"), "w", encoding="utf8") as file: - file.write(caption) - - params.subindex += 1 - - -def save_pic(image, index, params, existing_caption=None): - save_pic_with_caption(image, index, params, existing_caption=existing_caption) - - if params.flip: - save_pic_with_caption(ImageOps.mirror(image), index, params, existing_caption=existing_caption) - - -def split_pic(image, inverse_xy, width, height, overlap_ratio): - if inverse_xy: - from_w, from_h = image.height, image.width - to_w, to_h = height, width - else: - from_w, from_h = image.width, image.height - to_w, to_h = width, height - h = from_h * to_w // from_w - if inverse_xy: - image = image.resize((h, to_w)) - else: - image = image.resize((to_w, h)) - - split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio))) - y_step = (h - to_h) / (split_count - 1) - for i in range(split_count): - y = int(y_step * i) - if inverse_xy: - splitted = image.crop((y, 0, y + to_h, to_w)) - else: - splitted = image.crop((0, y, to_w, y + to_h)) - yield splitted - -# not using torchvision.transforms.CenterCrop because it doesn't allow float regions -def center_crop(image: Image, w: int, h: int): - iw, ih = image.size - if ih / h < iw / w: - sw = w * ih / h - box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih - else: - sh = h * iw / w - box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2 - return image.resize((w, h), Image.Resampling.LANCZOS, box) - - -def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold): - iw, ih = image.size - err = lambda w, h: 1-(lambda x: x if x < 1 else 1/x)(iw/ih/(w/h)) - wh = max(((w, h) for w in range(mindim, maxdim+1, 64) for h in range(mindim, maxdim+1, 64) - if minarea <= w * h <= maxarea and err(w, h) <= threshold), - key= lambda wh: (wh[0]*wh[1], -err(*wh))[::1 if objective=='Maximize area' else -1], - default=None - ) - return wh and center_crop(image, *wh) - - -def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None): - width = process_width - height = process_height - src = os.path.abspath(process_src) - dst = os.path.abspath(process_dst) - split_threshold = max(0.0, min(1.0, split_threshold)) - overlap_ratio = max(0.0, min(0.9, overlap_ratio)) - - assert src != dst, 'same directory specified as source and destination' - - os.makedirs(dst, exist_ok=True) - - files = listfiles(src) - - shared.state.job = "preprocess" - shared.state.textinfo = "Preprocessing..." - shared.state.job_count = len(files) - - params = PreprocessParams() - params.dstdir = dst - params.flip = process_flip - params.process_caption = process_caption - params.process_caption_deepbooru = process_caption_deepbooru - params.preprocess_txt_action = preprocess_txt_action - - pbar = tqdm.tqdm(files) - for index, imagefile in enumerate(pbar): - params.subindex = 0 - filename = os.path.join(src, imagefile) - try: - img = Image.open(filename) - img = ImageOps.exif_transpose(img) - img = img.convert("RGB") - except Exception: - continue - - description = f"Preprocessing [Image {index}/{len(files)}]" - pbar.set_description(description) - shared.state.textinfo = description - - params.src = filename - - existing_caption = None - existing_caption_filename = f"{os.path.splitext(filename)[0]}.txt" - if os.path.exists(existing_caption_filename): - with open(existing_caption_filename, 'r', encoding="utf8") as file: - existing_caption = file.read() - - if shared.state.interrupted: - break - - if img.height > img.width: - ratio = (img.width * height) / (img.height * width) - inverse_xy = False - else: - ratio = (img.height * width) / (img.width * height) - inverse_xy = True - - process_default_resize = True - - if process_split and ratio < 1.0 and ratio <= split_threshold: - for splitted in split_pic(img, inverse_xy, width, height, overlap_ratio): - save_pic(splitted, index, params, existing_caption=existing_caption) - process_default_resize = False - - if process_focal_crop and img.height != img.width: - - dnn_model_path = None - try: - dnn_model_path = autocrop.download_and_cache_models() - except Exception as e: - print("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", e) - - autocrop_settings = autocrop.Settings( - crop_width = width, - crop_height = height, - face_points_weight = process_focal_crop_face_weight, - entropy_points_weight = process_focal_crop_entropy_weight, - corner_points_weight = process_focal_crop_edges_weight, - annotate_image = process_focal_crop_debug, - dnn_model_path = dnn_model_path, - ) - for focal in autocrop.crop_image(img, autocrop_settings): - save_pic(focal, index, params, existing_caption=existing_caption) - process_default_resize = False - - if process_multicrop: - cropped = multicrop_pic(img, process_multicrop_mindim, process_multicrop_maxdim, process_multicrop_minarea, process_multicrop_maxarea, process_multicrop_objective, process_multicrop_threshold) - if cropped is not None: - save_pic(cropped, index, params, existing_caption=existing_caption) - else: - print(f"skipped {img.width}x{img.height} image {filename} (can't find suitable size within error threshold)") - process_default_resize = False - - if process_keep_original_size: - save_pic(img, index, params, existing_caption=existing_caption) - process_default_resize = False - - if process_default_resize: - img = images.resize_image(1, img, width, height) - save_pic(img, index, params, existing_caption=existing_caption) - - shared.state.nextjob() diff --git a/modules/textual_inversion/ui.py b/modules/textual_inversion/ui.py index 35c4feef..f149ad1f 100644 --- a/modules/textual_inversion/ui.py +++ b/modules/textual_inversion/ui.py @@ -3,7 +3,6 @@ import html import gradio as gr import modules.textual_inversion.textual_inversion -import modules.textual_inversion.preprocess from modules import sd_hijack, shared @@ -15,12 +14,6 @@ def create_embedding(name, initialization_text, nvpt, overwrite_old): return gr.Dropdown.update(choices=sorted(sd_hijack.model_hijack.embedding_db.word_embeddings.keys())), f"Created: {filename}", "" -def preprocess(*args): - modules.textual_inversion.preprocess.preprocess(*args) - - return f"Preprocessing {'interrupted' if shared.state.interrupted else 'finished'}.", "" - - def train_embedding(*args): assert not shared.cmd_opts.lowvram, 'Training models with lowvram not possible' diff --git a/modules/ui.py b/modules/ui.py index 08e0ad77..d80486dd 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -912,71 +912,6 @@ def create_ui(): with gr.Column(): create_hypernetwork = gr.Button(value="Create hypernetwork", variant='primary', elem_id="train_create_hypernetwork") - with gr.Tab(label="Preprocess images", id="preprocess_images"): - process_src = gr.Textbox(label='Source directory', elem_id="train_process_src") - process_dst = gr.Textbox(label='Destination directory', elem_id="train_process_dst") - process_width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="train_process_width") - process_height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="train_process_height") - preprocess_txt_action = gr.Dropdown(label='Existing Caption txt Action', value="ignore", choices=["ignore", "copy", "prepend", "append"], elem_id="train_preprocess_txt_action") - - with gr.Row(): - process_keep_original_size = gr.Checkbox(label='Keep original size', elem_id="train_process_keep_original_size") - process_flip = gr.Checkbox(label='Create flipped copies', elem_id="train_process_flip") - process_split = gr.Checkbox(label='Split oversized images', elem_id="train_process_split") - process_focal_crop = gr.Checkbox(label='Auto focal point crop', elem_id="train_process_focal_crop") - process_multicrop = gr.Checkbox(label='Auto-sized crop', elem_id="train_process_multicrop") - process_caption = gr.Checkbox(label='Use BLIP for caption', elem_id="train_process_caption") - process_caption_deepbooru = gr.Checkbox(label='Use deepbooru for caption', visible=True, elem_id="train_process_caption_deepbooru") - - with gr.Row(visible=False) as process_split_extra_row: - process_split_threshold = gr.Slider(label='Split image threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_split_threshold") - process_overlap_ratio = gr.Slider(label='Split image overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="train_process_overlap_ratio") - - with gr.Row(visible=False) as process_focal_crop_row: - process_focal_crop_face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_face_weight") - process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_entropy_weight") - process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_edges_weight") - process_focal_crop_debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug") - - with gr.Column(visible=False) as process_multicrop_col: - gr.Markdown('Each image is center-cropped with an automatically chosen width and height.') - with gr.Row(): - process_multicrop_mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="train_process_multicrop_mindim") - process_multicrop_maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="train_process_multicrop_maxdim") - with gr.Row(): - process_multicrop_minarea = gr.Slider(minimum=64*64, maximum=2048*2048, step=1, label="Area lower bound", value=64*64, elem_id="train_process_multicrop_minarea") - process_multicrop_maxarea = gr.Slider(minimum=64*64, maximum=2048*2048, step=1, label="Area upper bound", value=640*640, elem_id="train_process_multicrop_maxarea") - with gr.Row(): - process_multicrop_objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="train_process_multicrop_objective") - process_multicrop_threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="train_process_multicrop_threshold") - - with gr.Row(): - with gr.Column(scale=3): - gr.HTML(value="") - - with gr.Column(): - with gr.Row(): - interrupt_preprocessing = gr.Button("Interrupt", elem_id="train_interrupt_preprocessing") - run_preprocess = gr.Button(value="Preprocess", variant='primary', elem_id="train_run_preprocess") - - process_split.change( - fn=lambda show: gr_show(show), - inputs=[process_split], - outputs=[process_split_extra_row], - ) - - process_focal_crop.change( - fn=lambda show: gr_show(show), - inputs=[process_focal_crop], - outputs=[process_focal_crop_row], - ) - - process_multicrop.change( - fn=lambda show: gr_show(show), - inputs=[process_multicrop], - outputs=[process_multicrop_col], - ) - def get_textual_inversion_template_names(): return sorted(textual_inversion.textual_inversion_templates) @@ -1077,42 +1012,6 @@ def create_ui(): ] ) - run_preprocess.click( - fn=wrap_gradio_gpu_call(textual_inversion_ui.preprocess, extra_outputs=[gr.update()]), - _js="start_training_textual_inversion", - inputs=[ - dummy_component, - process_src, - process_dst, - process_width, - process_height, - preprocess_txt_action, - process_keep_original_size, - process_flip, - process_split, - process_caption, - process_caption_deepbooru, - process_split_threshold, - process_overlap_ratio, - process_focal_crop, - process_focal_crop_face_weight, - process_focal_crop_entropy_weight, - process_focal_crop_edges_weight, - process_focal_crop_debug, - process_multicrop, - process_multicrop_mindim, - process_multicrop_maxdim, - process_multicrop_minarea, - process_multicrop_maxarea, - process_multicrop_objective, - process_multicrop_threshold, - ], - outputs=[ - ti_output, - ti_outcome, - ], - ) - train_embedding.click( fn=wrap_gradio_gpu_call(textual_inversion_ui.train_embedding, extra_outputs=[gr.update()]), _js="start_training_textual_inversion", @@ -1186,12 +1085,6 @@ def create_ui(): outputs=[], ) - interrupt_preprocessing.click( - fn=lambda: shared.state.interrupt(), - inputs=[], - outputs=[], - ) - loadsave = ui_loadsave.UiLoadsave(cmd_opts.ui_config_file) settings = ui_settings.UiSettings() diff --git a/modules/ui_postprocessing.py b/modules/ui_postprocessing.py index 802e1ce7..fbad0800 100644 --- a/modules/ui_postprocessing.py +++ b/modules/ui_postprocessing.py @@ -1,9 +1,10 @@ import gradio as gr -from modules import scripts, shared, ui_common, postprocessing, call_queue +from modules import scripts, shared, ui_common, postprocessing, call_queue, ui_toprow import modules.generation_parameters_copypaste as parameters_copypaste def create_ui(): + dummy_component = gr.Label(visible=False) tab_index = gr.State(value=0) with gr.Row(equal_height=False, variant='compact'): @@ -20,11 +21,13 @@ def create_ui(): extras_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, placeholder="Leave blank to save images to the default path.", elem_id="extras_batch_output_dir") show_extras_results = gr.Checkbox(label='Show result images', value=True, elem_id="extras_show_extras_results") - submit = gr.Button('Generate', elem_id="extras_generate", variant='primary') - script_inputs = scripts.scripts_postproc.setup_ui() with gr.Column(): + toprow = ui_toprow.Toprow(is_compact=True, is_img2img=False, id_part="extras") + toprow.create_inline_toprow_image() + submit = toprow.submit + result_images, html_info_x, html_info, html_log = ui_common.create_output_panel("extras", shared.opts.outdir_extras_samples) tab_single.select(fn=lambda: 0, inputs=[], outputs=[tab_index]) @@ -33,7 +36,9 @@ def create_ui(): submit.click( fn=call_queue.wrap_gradio_gpu_call(postprocessing.run_postprocessing, extra_outputs=[None, '']), + _js="submit_extras", inputs=[ + dummy_component, tab_index, extras_image, image_batch, @@ -45,8 +50,9 @@ def create_ui(): outputs=[ result_images, html_info_x, - html_info, - ] + html_log, + ], + show_progress=False, ) parameters_copypaste.add_paste_fields("extras", extras_image, None) diff --git a/modules/ui_toprow.py b/modules/ui_toprow.py index 985b5a2d..88838f97 100644 --- a/modules/ui_toprow.py +++ b/modules/ui_toprow.py @@ -34,8 +34,10 @@ class Toprow: submit_box = None - def __init__(self, is_img2img, is_compact=False): - id_part = "img2img" if is_img2img else "txt2img" + def __init__(self, is_img2img, is_compact=False, id_part=None): + if id_part is None: + id_part = "img2img" if is_img2img else "txt2img" + self.id_part = id_part self.is_img2img = is_img2img self.is_compact = is_compact diff --git a/scripts/postprocessing_caption.py b/scripts/postprocessing_caption.py new file mode 100644 index 00000000..243e3ad9 --- /dev/null +++ b/scripts/postprocessing_caption.py @@ -0,0 +1,30 @@ +from modules import scripts_postprocessing, ui_components, deepbooru, shared +import gradio as gr + + +class ScriptPostprocessingCeption(scripts_postprocessing.ScriptPostprocessing): + name = "Caption" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Caption") as enable: + option = gr.CheckboxGroup(value=["Deepbooru"], choices=["Deepbooru", "BLIP"], show_label=False) + + return { + "enable": enable, + "option": option, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option): + if not enable: + return + + captions = [pp.caption] + + if "Deepbooru" in option: + captions.append(deepbooru.model.tag(pp.image)) + + if "BLIP" in option: + captions.append(shared.interrogator.generate_caption(pp.image)) + + pp.caption = ", ".join([x for x in captions if x]) diff --git a/scripts/postprocessing_codeformer.py b/scripts/postprocessing_codeformer.py index a7d80d40..e1e156dd 100644 --- a/scripts/postprocessing_codeformer.py +++ b/scripts/postprocessing_codeformer.py @@ -1,28 +1,28 @@ from PIL import Image import numpy as np -from modules import scripts_postprocessing, codeformer_model +from modules import scripts_postprocessing, codeformer_model, ui_components import gradio as gr -from modules.ui_components import FormRow - class ScriptPostprocessingCodeFormer(scripts_postprocessing.ScriptPostprocessing): name = "CodeFormer" order = 3000 def ui(self): - with FormRow(): - codeformer_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer visibility", value=0, elem_id="extras_codeformer_visibility") - codeformer_weight = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="CodeFormer weight (0 = maximum effect, 1 = minimum effect)", value=0, elem_id="extras_codeformer_weight") + with ui_components.InputAccordion(False, label="CodeFormer") as enable: + with gr.Row(): + codeformer_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Visibility", value=1.0, elem_id="extras_codeformer_visibility") + codeformer_weight = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Weight (0 = maximum effect, 1 = minimum effect)", value=0, elem_id="extras_codeformer_weight") return { + "enable": enable, "codeformer_visibility": codeformer_visibility, "codeformer_weight": codeformer_weight, } - def process(self, pp: scripts_postprocessing.PostprocessedImage, codeformer_visibility, codeformer_weight): - if codeformer_visibility == 0: + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, codeformer_visibility, codeformer_weight): + if codeformer_visibility == 0 or not enable: return restored_img = codeformer_model.codeformer.restore(np.array(pp.image, dtype=np.uint8), w=codeformer_weight) diff --git a/scripts/postprocessing_create_flipped_copies.py b/scripts/postprocessing_create_flipped_copies.py new file mode 100644 index 00000000..3425571d --- /dev/null +++ b/scripts/postprocessing_create_flipped_copies.py @@ -0,0 +1,32 @@ +from PIL import ImageOps, Image + +from modules import scripts_postprocessing, ui_components +import gradio as gr + + +class ScriptPostprocessingCreateFlippedCopies(scripts_postprocessing.ScriptPostprocessing): + name = "Create flipped copies" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Create flipped copies") as enable: + with gr.Row(): + option = gr.CheckboxGroup(value=["Horizontal"], choices=["Horizontal", "Vertical", "Both"], show_label=False) + + return { + "enable": enable, + "option": option, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option): + if not enable: + return + + if "Horizontal" in option: + pp.extra_images.append(ImageOps.mirror(pp.image)) + + if "Vertical" in option: + pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM)) + + if "Both" in option: + pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM).transpose(Image.Transpose.FLIP_LEFT_RIGHT)) diff --git a/scripts/postprocessing_focal_crop.py b/scripts/postprocessing_focal_crop.py new file mode 100644 index 00000000..d3baf298 --- /dev/null +++ b/scripts/postprocessing_focal_crop.py @@ -0,0 +1,54 @@ + +from modules import scripts_postprocessing, ui_components, errors +import gradio as gr + +from modules.textual_inversion import autocrop + + +class ScriptPostprocessingFocalCrop(scripts_postprocessing.ScriptPostprocessing): + name = "Auto focal point crop" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Auto focal point crop") as enable: + face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_face_weight") + entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_entropy_weight") + edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_edges_weight") + debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug") + + return { + "enable": enable, + "face_weight": face_weight, + "entropy_weight": entropy_weight, + "edges_weight": edges_weight, + "debug": debug, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, face_weight, entropy_weight, edges_weight, debug): + if not enable: + return + + if not pp.shared.target_width or not pp.shared.target_height: + return + + dnn_model_path = None + try: + dnn_model_path = autocrop.download_and_cache_models() + except Exception: + errors.report("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", exc_info=True) + + autocrop_settings = autocrop.Settings( + crop_width=pp.shared.target_width, + crop_height=pp.shared.target_height, + face_points_weight=face_weight, + entropy_points_weight=entropy_weight, + corner_points_weight=edges_weight, + annotate_image=debug, + dnn_model_path=dnn_model_path, + ) + + result, *others = autocrop.crop_image(pp.image, autocrop_settings) + + pp.image = result + pp.extra_images = [pp.create_copy(x, nametags=["focal-crop-debug"], disable_processing=True) for x in others] + diff --git a/scripts/postprocessing_gfpgan.py b/scripts/postprocessing_gfpgan.py index d854f3f7..6e756605 100644 --- a/scripts/postprocessing_gfpgan.py +++ b/scripts/postprocessing_gfpgan.py @@ -1,26 +1,25 @@ from PIL import Image import numpy as np -from modules import scripts_postprocessing, gfpgan_model +from modules import scripts_postprocessing, gfpgan_model, ui_components import gradio as gr -from modules.ui_components import FormRow - class ScriptPostprocessingGfpGan(scripts_postprocessing.ScriptPostprocessing): name = "GFPGAN" order = 2000 def ui(self): - with FormRow(): - gfpgan_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="GFPGAN visibility", value=0, elem_id="extras_gfpgan_visibility") + with ui_components.InputAccordion(False, label="GFPGAN") as enable: + gfpgan_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Visibility", value=1.0, elem_id="extras_gfpgan_visibility") return { + "enable": enable, "gfpgan_visibility": gfpgan_visibility, } - def process(self, pp: scripts_postprocessing.PostprocessedImage, gfpgan_visibility): - if gfpgan_visibility == 0: + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, gfpgan_visibility): + if gfpgan_visibility == 0 or not enable: return restored_img = gfpgan_model.gfpgan_fix_faces(np.array(pp.image, dtype=np.uint8)) diff --git a/scripts/postprocessing_split_oversized.py b/scripts/postprocessing_split_oversized.py new file mode 100644 index 00000000..c4a03160 --- /dev/null +++ b/scripts/postprocessing_split_oversized.py @@ -0,0 +1,71 @@ +import math + +from modules import scripts_postprocessing, ui_components +import gradio as gr + + +def split_pic(image, inverse_xy, width, height, overlap_ratio): + if inverse_xy: + from_w, from_h = image.height, image.width + to_w, to_h = height, width + else: + from_w, from_h = image.width, image.height + to_w, to_h = width, height + h = from_h * to_w // from_w + if inverse_xy: + image = image.resize((h, to_w)) + else: + image = image.resize((to_w, h)) + + split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio))) + y_step = (h - to_h) / (split_count - 1) + for i in range(split_count): + y = int(y_step * i) + if inverse_xy: + splitted = image.crop((y, 0, y + to_h, to_w)) + else: + splitted = image.crop((0, y, to_w, y + to_h)) + yield splitted + + +class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostprocessing): + name = "Split oversized images" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Split oversized images") as enable: + with gr.Row(): + split_threshold = gr.Slider(label='Threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_split_threshold") + overlap_ratio = gr.Slider(label='Overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="postprocess_overlap_ratio") + + return { + "enable": enable, + "split_threshold": split_threshold, + "overlap_ratio": overlap_ratio, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, split_threshold, overlap_ratio): + if not enable: + return + + width = pp.shared.target_width + height = pp.shared.target_height + + if not width or not height: + return + + if pp.image.height > pp.image.width: + ratio = (pp.image.width * height) / (pp.image.height * width) + inverse_xy = False + else: + ratio = (pp.image.height * width) / (pp.image.width * height) + inverse_xy = True + + if ratio >= 1.0 and ratio > split_threshold: + return + + result, *others = split_pic(pp.image, inverse_xy, width, height, overlap_ratio) + + pp.image = result + pp.extra_images = [pp.create_copy(x) for x in others] + diff --git a/scripts/postprocessing_upscale.py b/scripts/postprocessing_upscale.py index eb42a29e..ed709688 100644 --- a/scripts/postprocessing_upscale.py +++ b/scripts/postprocessing_upscale.py @@ -81,6 +81,14 @@ class ScriptPostprocessingUpscale(scripts_postprocessing.ScriptPostprocessing): return image + def process_firstpass(self, pp: scripts_postprocessing.PostprocessedImage, upscale_mode=1, upscale_by=2.0, upscale_to_width=None, upscale_to_height=None, upscale_crop=False, upscaler_1_name=None, upscaler_2_name=None, upscaler_2_visibility=0.0): + if upscale_mode == 1: + pp.shared.target_width = upscale_to_width + pp.shared.target_height = upscale_to_height + else: + pp.shared.target_width = int(pp.image.width * upscale_by) + pp.shared.target_height = int(pp.image.height * upscale_by) + def process(self, pp: scripts_postprocessing.PostprocessedImage, upscale_mode=1, upscale_by=2.0, upscale_to_width=None, upscale_to_height=None, upscale_crop=False, upscaler_1_name=None, upscaler_2_name=None, upscaler_2_visibility=0.0): if upscaler_1_name == "None": upscaler_1_name = None @@ -126,6 +134,10 @@ class ScriptPostprocessingUpscaleSimple(ScriptPostprocessingUpscale): "upscaler_name": upscaler_name, } + def process_firstpass(self, pp: scripts_postprocessing.PostprocessedImage, upscale_by=2.0, upscaler_name=None): + pp.shared.target_width = int(pp.image.width * upscale_by) + pp.shared.target_height = int(pp.image.height * upscale_by) + def process(self, pp: scripts_postprocessing.PostprocessedImage, upscale_by=2.0, upscaler_name=None): if upscaler_name is None or upscaler_name == "None": return diff --git a/scripts/processing_autosized_crop.py b/scripts/processing_autosized_crop.py new file mode 100644 index 00000000..c0980226 --- /dev/null +++ b/scripts/processing_autosized_crop.py @@ -0,0 +1,64 @@ +from PIL import Image + +from modules import scripts_postprocessing, ui_components +import gradio as gr + + +def center_crop(image: Image, w: int, h: int): + iw, ih = image.size + if ih / h < iw / w: + sw = w * ih / h + box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih + else: + sh = h * iw / w + box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2 + return image.resize((w, h), Image.Resampling.LANCZOS, box) + + +def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold): + iw, ih = image.size + err = lambda w, h: 1 - (lambda x: x if x < 1 else 1 / x)(iw / ih / (w / h)) + wh = max(((w, h) for w in range(mindim, maxdim + 1, 64) for h in range(mindim, maxdim + 1, 64) + if minarea <= w * h <= maxarea and err(w, h) <= threshold), + key=lambda wh: (wh[0] * wh[1], -err(*wh))[::1 if objective == 'Maximize area' else -1], + default=None + ) + return wh and center_crop(image, *wh) + + +class ScriptPostprocessingAutosizedCrop(scripts_postprocessing.ScriptPostprocessing): + name = "Auto-sized crop" + order = 4000 + + def ui(self): + with ui_components.InputAccordion(False, label="Auto-sized crop") as enable: + gr.Markdown('Each image is center-cropped with an automatically chosen width and height.') + with gr.Row(): + mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="postprocess_multicrop_mindim") + maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="postprocess_multicrop_maxdim") + with gr.Row(): + minarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area lower bound", value=64 * 64, elem_id="postprocess_multicrop_minarea") + maxarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area upper bound", value=640 * 640, elem_id="postprocess_multicrop_maxarea") + with gr.Row(): + objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="postprocess_multicrop_objective") + threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="postprocess_multicrop_threshold") + + return { + "enable": enable, + "mindim": mindim, + "maxdim": maxdim, + "minarea": minarea, + "maxarea": maxarea, + "objective": objective, + "threshold": threshold, + } + + def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, mindim, maxdim, minarea, maxarea, objective, threshold): + if not enable: + return + + cropped = multicrop_pic(pp.image, mindim, maxdim, minarea, maxarea, objective, threshold) + if cropped is not None: + pp.image = cropped + else: + print(f"skipped {pp.image.width}x{pp.image.height} image (can't find suitable size within error threshold)") -- cgit v1.2.3