aboutsummaryrefslogtreecommitdiffstats
path: root/modules/img2img.py
diff options
context:
space:
mode:
Diffstat (limited to 'modules/img2img.py')
-rw-r--r--modules/img2img.py66
1 files changed, 52 insertions, 14 deletions
diff --git a/modules/img2img.py b/modules/img2img.py
index 03e934e9..ca58b5d8 100644
--- a/modules/img2img.py
+++ b/modules/img2img.py
@@ -4,9 +4,9 @@ import sys
import traceback
import numpy as np
-from PIL import Image, ImageOps, ImageChops
+from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops
-from modules import devices
+from modules import devices, sd_samplers
from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
from modules.shared import opts, state
import modules.shared as shared
@@ -19,22 +19,28 @@ import modules.scripts
def process_batch(p, input_dir, output_dir, args):
processing.fix_seed(p)
- images = [file for file in [os.path.join(input_dir, x) for x in os.listdir(input_dir)] if os.path.isfile(file)]
+ images = shared.listfiles(input_dir)
print(f"Will process {len(images)} images, creating {p.n_iter * p.batch_size} new images for each.")
+ save_normally = output_dir == ''
+
p.do_not_save_grid = True
- p.do_not_save_samples = True
+ p.do_not_save_samples = not save_normally
state.job_count = len(images) * p.n_iter
for i, image in enumerate(images):
state.job = f"{i+1} out of {len(images)}"
+ if state.skipped:
+ state.skipped = False
if state.interrupted:
break
img = Image.open(image)
+ # Use the EXIF orientation of photos taken by smartphones.
+ img = ImageOps.exif_transpose(img)
p.init_images = [img] * p.batch_size
proc = modules.scripts.scripts_img2img.run(p, *args)
@@ -48,27 +54,49 @@ def process_batch(p, input_dir, output_dir, args):
left, right = os.path.splitext(filename)
filename = f"{left}-{n}{right}"
- processed_image.save(os.path.join(output_dir, filename))
+ if not save_normally:
+ os.makedirs(output_dir, exist_ok=True)
+ processed_image.save(os.path.join(output_dir, filename))
-def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, init_img, init_img_with_mask, init_img_inpaint, init_mask_inpaint, mask_mode, steps: int, sampler_index: int, mask_blur: int, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, *args):
+def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, init_img, init_img_with_mask, init_img_with_mask_orig, init_img_inpaint, init_mask_inpaint, mask_mode, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, *args):
is_inpaint = mode == 1
is_batch = mode == 2
if is_inpaint:
+ # Drawn mask
if mask_mode == 0:
- image = init_img_with_mask['image']
- mask = init_img_with_mask['mask']
- alpha_mask = ImageOps.invert(image.split()[-1]).convert('L').point(lambda x: 255 if x > 0 else 0, mode='1')
- mask = ImageChops.lighter(alpha_mask, mask.convert('L')).convert('L')
- image = image.convert('RGB')
+ is_mask_sketch = isinstance(init_img_with_mask, dict)
+ is_mask_paint = not is_mask_sketch
+ if is_mask_sketch:
+ # Sketch: mask iff. not transparent
+ image, mask = init_img_with_mask["image"], init_img_with_mask["mask"]
+ alpha_mask = ImageOps.invert(image.split()[-1]).convert('L').point(lambda x: 255 if x > 0 else 0, mode='1')
+ mask = ImageChops.lighter(alpha_mask, mask.convert('L')).convert('L')
+ else:
+ # Color-sketch: mask iff. painted over
+ image = init_img_with_mask
+ orig = init_img_with_mask_orig or init_img_with_mask
+ pred = np.any(np.array(image) != np.array(orig), axis=-1)
+ mask = Image.fromarray(pred.astype(np.uint8) * 255, "L")
+ mask = ImageEnhance.Brightness(mask).enhance(1 - mask_alpha / 100)
+ blur = ImageFilter.GaussianBlur(mask_blur)
+ image = Image.composite(image.filter(blur), orig, mask.filter(blur))
+
+ image = image.convert("RGB")
+ # Uploaded mask
else:
image = init_img_inpaint
mask = init_mask_inpaint
+ # No mask
else:
image = init_img
mask = None
+ # Use the EXIF orientation of photos taken by smartphones.
+ if image is not None:
+ image = ImageOps.exif_transpose(image)
+
assert 0. <= denoising_strength <= 1., 'can only work with strength in [0.0, 1.0]'
p = StableDiffusionProcessingImg2Img(
@@ -84,7 +112,7 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
seed_resize_from_h=seed_resize_from_h,
seed_resize_from_w=seed_resize_from_w,
seed_enable_extras=seed_enable_extras,
- sampler_index=sampler_index,
+ sampler_name=sd_samplers.samplers_for_img2img[sampler_index].name,
batch_size=batch_size,
n_iter=n_iter,
steps=steps,
@@ -103,7 +131,12 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
inpaint_full_res_padding=inpaint_full_res_padding,
inpainting_mask_invert=inpainting_mask_invert,
)
- print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
+
+ p.scripts = modules.scripts.scripts_txt2img
+ p.script_args = args
+
+ if shared.cmd_opts.enable_console_prompts:
+ print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
p.extra_generation_params["Mask blur"] = mask_blur
@@ -118,10 +151,15 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
if processed is None:
processed = process_images(p)
+ p.close()
+
shared.total_tqdm.clear()
generation_info_js = processed.js()
if opts.samples_log_stdout:
print(generation_info_js)
- return processed.images, generation_info_js, plaintext_to_html(processed.info)
+ if opts.do_not_show_images:
+ processed.images = []
+
+ return processed.images, generation_info_js, plaintext_to_html(processed.info), plaintext_to_html(processed.comments)