90 lines
3.2 KiB
Python
90 lines
3.2 KiB
Python
"""
|
|
@author: initials AMA
|
|
@title: Ardenius
|
|
@nickname: Ardenius
|
|
@description: ARD Basic Load Image: adds width and height to the output of the default load image
|
|
"""
|
|
# licensed under General Public License v3.0 all rights reserved © 2024
|
|
# Owner initials: AMAA
|
|
# nickname: Ardenius
|
|
# email: ardenius7@gmail.com
|
|
# website: https://ko-fi.com/ardenius
|
|
# ➡️ follow me at https://ko-fi.com/ardenius in the top right corner (follow)
|
|
# 📸 Change the mood ! by Visiting my AI Image Gallery
|
|
# 🏆 Support me by getting Premium Members only Perks (Premium SD Models, ComfyUI custom nodes, and more to come)
|
|
# below code is based upon ComfyUI code licensed under General Public License v3.0 https://www.gnu.org/licenses/gpl-3.0.txt by
|
|
# contributers found here https://github.com/comfyanonymous/ComfyUI
|
|
# thus all code here is released to the user as per the GPL V3.0 terms.
|
|
|
|
import os
|
|
import json
|
|
import numpy as np
|
|
from PIL import Image, ImageOps, ImageSequence
|
|
import torch
|
|
import folder_paths
|
|
import node_helpers
|
|
|
|
|
|
class ARD_BASIC_LOAD_IMAGE:
|
|
@classmethod
|
|
def INPUT_TYPES(s):
|
|
input_dir = folder_paths.get_input_directory()
|
|
files = [f for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
|
|
return {"required":
|
|
{"image": (sorted(files), {"image_upload": True})},
|
|
}
|
|
|
|
CATEGORY = "image"
|
|
RETURN_NAMES = ("image", "mask", "width", "height")
|
|
RETURN_TYPES = ("IMAGE", "MASK", "INT", "INT")
|
|
|
|
FUNCTION = "ard_basic_load_image"
|
|
DESCRIPTION = "ARD Basic Load Image: adds width and height to the output of the default load image"
|
|
|
|
def ard_basic_load_image(self, image):
|
|
image_path = folder_paths.get_annotated_filepath(image)
|
|
|
|
img = node_helpers.pillow(Image.open, image_path)
|
|
|
|
output_images = []
|
|
output_masks = []
|
|
w, h = None, None
|
|
width = None
|
|
height = None
|
|
|
|
excluded_formats = ['MPO']
|
|
|
|
for i in ImageSequence.Iterator(img):
|
|
i = node_helpers.pillow(ImageOps.exif_transpose, i)
|
|
|
|
if i.mode == 'I':
|
|
i = i.point(lambda i: i * (1 / 255))
|
|
image = i.convert("RGB")
|
|
|
|
if len(output_images) == 0:
|
|
w = image.size[0]
|
|
h = image.size[1]
|
|
width = w
|
|
height = h
|
|
|
|
if image.size[0] != w or image.size[1] != h:
|
|
continue
|
|
|
|
image = np.array(image).astype(np.float32) / 255.0
|
|
image = torch.from_numpy(image)[None,]
|
|
if 'A' in i.getbands():
|
|
mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
|
|
mask = 1. - torch.from_numpy(mask)
|
|
else:
|
|
mask = torch.zeros((64,64), dtype=torch.float32, device="cpu")
|
|
output_images.append(image)
|
|
output_masks.append(mask.unsqueeze(0))
|
|
|
|
if len(output_images) > 1 and img.format not in excluded_formats:
|
|
output_image = torch.cat(output_images, dim=0)
|
|
output_mask = torch.cat(output_masks, dim=0)
|
|
else:
|
|
output_image = output_images[0]
|
|
output_mask = output_masks[0]
|
|
|
|
return (output_image, output_mask, width, height) |