aboutsummaryrefslogtreecommitdiffstats
path: root/modules/images.py
diff options
context:
space:
mode:
Diffstat (limited to 'modules/images.py')
-rw-r--r--modules/images.py90
1 files changed, 66 insertions, 24 deletions
diff --git a/modules/images.py b/modules/images.py
index ae3cdaf4..fd173829 100644
--- a/modules/images.py
+++ b/modules/images.py
@@ -16,8 +16,9 @@ from PIL import Image, ImageFont, ImageDraw, PngImagePlugin
from fonts.ttf import Roboto
import string
import json
+import hashlib
-from modules import sd_samplers, shared, script_callbacks
+from modules import sd_samplers, shared, script_callbacks, errors
from modules.shared import opts, cmd_opts
LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS)
@@ -130,7 +131,7 @@ class GridAnnotation:
self.size = None
-def draw_grid_annotations(im, width, height, hor_texts, ver_texts):
+def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
def wrap(drawing, text, font, line_length):
lines = ['']
for word in text.split():
@@ -194,32 +195,35 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts):
line.allowed_width = allowed_width
hor_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing for lines in hor_texts]
- ver_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing * len(lines) for lines in
- ver_texts]
+ ver_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing * len(lines) for lines in ver_texts]
pad_top = 0 if sum(hor_text_heights) == 0 else max(hor_text_heights) + line_spacing * 2
- result = Image.new("RGB", (im.width + pad_left, im.height + pad_top), "white")
- result.paste(im, (pad_left, pad_top))
+ result = Image.new("RGB", (im.width + pad_left + margin * (cols-1), im.height + pad_top + margin * (rows-1)), "white")
+
+ for row in range(rows):
+ for col in range(cols):
+ cell = im.crop((width * col, height * row, width * (col+1), height * (row+1)))
+ result.paste(cell, (pad_left + (width + margin) * col, pad_top + (height + margin) * row))
d = ImageDraw.Draw(result)
for col in range(cols):
- x = pad_left + width * col + width / 2
+ x = pad_left + (width + margin) * col + width / 2
y = pad_top / 2 - hor_text_heights[col] / 2
draw_texts(d, x, y, hor_texts[col], fnt, fontsize)
for row in range(rows):
x = pad_left / 2
- y = pad_top + height * row + height / 2 - ver_text_heights[row] / 2
+ y = pad_top + (height + margin) * row + height / 2 - ver_text_heights[row] / 2
draw_texts(d, x, y, ver_texts[row], fnt, fontsize)
return result
-def draw_prompt_matrix(im, width, height, all_prompts):
+def draw_prompt_matrix(im, width, height, all_prompts, margin=0):
prompts = all_prompts[1:]
boundary = math.ceil(len(prompts) / 2)
@@ -229,7 +233,7 @@ def draw_prompt_matrix(im, width, height, all_prompts):
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)
+ return draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin)
def resize_image(resize_mode, im, width, height, upscaler_name=None):
@@ -257,9 +261,12 @@ def resize_image(resize_mode, im, width, height, upscaler_name=None):
if scale > 1.0:
upscalers = [x for x in shared.sd_upscalers if x.name == upscaler_name]
- assert len(upscalers) > 0, f"could not find upscaler named {upscaler_name}"
+ if len(upscalers) == 0:
+ upscaler = shared.sd_upscalers[0]
+ print(f"could not find upscaler named {upscaler_name or '<empty string>'}, using {upscaler.name} as a fallback")
+ else:
+ upscaler = upscalers[0]
- upscaler = upscalers[0]
im = upscaler.scaler.upscale(im, scale, upscaler.data_path)
if im.width != w or im.height != h:
@@ -311,6 +318,7 @@ re_nonletters = re.compile(r'[\s' + string.punctuation + ']+')
re_pattern = re.compile(r"(.*?)(?:\[([^\[\]]+)\]|$)")
re_pattern_arg = re.compile(r"(.*)<([^>]*)>$")
max_filename_part_length = 128
+NOTHING_AND_SKIP_PREVIOUS_TEXT = object()
def sanitize_filename_part(text, replace_spaces=True):
@@ -340,10 +348,15 @@ class FilenameGenerator:
'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
'datetime': lambda self, *args: self.datetime(*args), # accepts formats: [datetime], [datetime<Format>], [datetime<Format><Time Zone>]
'job_timestamp': lambda self: getattr(self.p, "job_timestamp", shared.state.job_timestamp),
+ 'prompt_hash': lambda self: hashlib.sha256(self.prompt.encode()).hexdigest()[0:8],
'prompt': lambda self: sanitize_filename_part(self.prompt),
'prompt_no_styles': lambda self: self.prompt_no_style(),
'prompt_spaces': lambda self: sanitize_filename_part(self.prompt, replace_spaces=False),
'prompt_words': lambda self: self.prompt_words(),
+ 'batch_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.batch_size == 1 else self.p.batch_index + 1,
+ 'generation_number': lambda self: NOTHING_AND_SKIP_PREVIOUS_TEXT if self.p.n_iter == 1 and self.p.batch_size == 1 else self.p.iteration * self.p.batch_size + self.p.batch_index + 1,
+ 'hasprompt': lambda self, *args: self.hasprompt(*args), # accepts formats:[hasprompt<prompt1|default><prompt2>..]
+ 'clip_skip': lambda self: opts.data["CLIP_stop_at_last_layers"],
}
default_time_format = '%Y%m%d%H%M%S'
@@ -352,6 +365,22 @@ class FilenameGenerator:
self.seed = seed
self.prompt = prompt
self.image = image
+
+ def hasprompt(self, *args):
+ lower = self.prompt.lower()
+ if self.p is None or self.prompt is None:
+ return None
+ outres = ""
+ for arg in args:
+ if arg != "":
+ division = arg.split("|")
+ expected = division[0].lower()
+ default = division[1] if len(division) > 1 else ""
+ if lower.find(expected) >= 0:
+ outres = f'{outres}{expected}'
+ else:
+ outres = outres if default == "" else f'{outres}{default}'
+ return sanitize_filename_part(outres)
def prompt_no_style(self):
if self.p is None or self.prompt is None:
@@ -395,9 +424,9 @@ class FilenameGenerator:
for m in re_pattern.finditer(x):
text, pattern = m.groups()
- res += text
if pattern is None:
+ res += text
continue
pattern_args = []
@@ -418,11 +447,13 @@ class FilenameGenerator:
print(f"Error adding [{pattern}] to filename", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
- if replacement is not None:
- res += str(replacement)
+ if replacement == NOTHING_AND_SKIP_PREVIOUS_TEXT:
+ continue
+ elif replacement is not None:
+ res += text + str(replacement)
continue
- res += f'[{pattern}]'
+ res += f'{text}[{pattern}]'
return res
@@ -548,8 +579,10 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
elif extension.lower() in (".jpg", ".jpeg", ".webp"):
if image_to_save.mode == 'RGBA':
image_to_save = image_to_save.convert("RGB")
+ elif image_to_save.mode == 'I;16':
+ image_to_save = image_to_save.point(lambda p: p * 0.0038910505836576).convert("RGB" if extension.lower() == ".webp" else "L")
- image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality)
+ image_to_save.save(temp_file_path, format=image_format, quality=opts.jpeg_quality, lossless=opts.webp_lossless)
if opts.enable_pnginfo and info is not None:
exif_bytes = piexif.dump({
@@ -566,21 +599,28 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
os.replace(temp_file_path, filename_without_extension + extension)
fullfn_without_extension, extension = os.path.splitext(params.filename)
+ if hasattr(os, 'statvfs'):
+ max_name_len = os.statvfs(path).f_namemax
+ fullfn_without_extension = fullfn_without_extension[:max_name_len - max(4, len(extension))]
+ params.filename = fullfn_without_extension + extension
+ fullfn = params.filename
_atomically_save_image(image, fullfn_without_extension, extension)
image.already_saved_as = fullfn
- target_side_length = 4000
- oversize = image.width > target_side_length or image.height > target_side_length
- if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > 4 * 1024 * 1024):
+ oversize = image.width > opts.target_side_length or image.height > opts.target_side_length
+ if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > opts.img_downscale_threshold * 1024 * 1024):
ratio = image.width / image.height
if oversize and ratio > 1:
- image = image.resize((target_side_length, image.height * target_side_length // image.width), LANCZOS)
+ image = image.resize((round(opts.target_side_length), round(image.height * opts.target_side_length / image.width)), LANCZOS)
elif oversize:
- image = image.resize((image.width * target_side_length // image.height, target_side_length), LANCZOS)
+ image = image.resize((round(image.width * opts.target_side_length / image.height), round(opts.target_side_length)), LANCZOS)
- _atomically_save_image(image, fullfn_without_extension, ".jpg")
+ try:
+ _atomically_save_image(image, fullfn_without_extension, ".jpg")
+ except Exception as e:
+ errors.display(e, "saving image as downscaled JPG")
if opts.save_txt and info is not None:
txt_fullfn = f"{fullfn_without_extension}.txt"
@@ -631,6 +671,8 @@ Steps: {json_info["steps"]}, Sampler: {sampler}, CFG scale: {json_info["scale"]}
def image_data(data):
+ import gradio as gr
+
try:
image = Image.open(io.BytesIO(data))
textinfo, _ = read_info_from_image(image)
@@ -646,7 +688,7 @@ def image_data(data):
except Exception:
pass
- return '', None
+ return gr.update(), None
def flatten(img, bgcolor):