File size: 8,274 Bytes
436faa6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 |
import numpy as np
import torch
import torch.nn.functional as F
from PIL import Image
import math
import comfy.utils
class Blend:
def __init__(self):
pass
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"image1": ("IMAGE",),
"image2": ("IMAGE",),
"blend_factor": ("FLOAT", {
"default": 0.5,
"min": 0.0,
"max": 1.0,
"step": 0.01
}),
"blend_mode": (["normal", "multiply", "screen", "overlay", "soft_light"],),
},
}
RETURN_TYPES = ("IMAGE",)
FUNCTION = "blend_images"
CATEGORY = "image/postprocessing"
def blend_images(self, image1: torch.Tensor, image2: torch.Tensor, blend_factor: float, blend_mode: str):
if image1.shape != image2.shape:
image2 = image2.permute(0, 3, 1, 2)
image2 = comfy.utils.common_upscale(image2, image1.shape[2], image1.shape[1], upscale_method='bicubic', crop='center')
image2 = image2.permute(0, 2, 3, 1)
blended_image = self.blend_mode(image1, image2, blend_mode)
blended_image = image1 * (1 - blend_factor) + blended_image * blend_factor
blended_image = torch.clamp(blended_image, 0, 1)
return (blended_image,)
def blend_mode(self, img1, img2, mode):
if mode == "normal":
return img2
elif mode == "multiply":
return img1 * img2
elif mode == "screen":
return 1 - (1 - img1) * (1 - img2)
elif mode == "overlay":
return torch.where(img1 <= 0.5, 2 * img1 * img2, 1 - 2 * (1 - img1) * (1 - img2))
elif mode == "soft_light":
return torch.where(img2 <= 0.5, img1 - (1 - 2 * img2) * img1 * (1 - img1), img1 + (2 * img2 - 1) * (self.g(img1) - img1))
else:
raise ValueError(f"Unsupported blend mode: {mode}")
def g(self, x):
return torch.where(x <= 0.25, ((16 * x - 12) * x + 4) * x, torch.sqrt(x))
def gaussian_kernel(kernel_size: int, sigma: float, device=None):
x, y = torch.meshgrid(torch.linspace(-1, 1, kernel_size, device=device), torch.linspace(-1, 1, kernel_size, device=device), indexing="ij")
d = torch.sqrt(x * x + y * y)
g = torch.exp(-(d * d) / (2.0 * sigma * sigma))
return g / g.sum()
class Blur:
def __init__(self):
pass
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"image": ("IMAGE",),
"blur_radius": ("INT", {
"default": 1,
"min": 1,
"max": 31,
"step": 1
}),
"sigma": ("FLOAT", {
"default": 1.0,
"min": 0.1,
"max": 10.0,
"step": 0.1
}),
},
}
RETURN_TYPES = ("IMAGE",)
FUNCTION = "blur"
CATEGORY = "image/postprocessing"
def blur(self, image: torch.Tensor, blur_radius: int, sigma: float):
if blur_radius == 0:
return (image,)
batch_size, height, width, channels = image.shape
kernel_size = blur_radius * 2 + 1
kernel = gaussian_kernel(kernel_size, sigma, device=image.device).repeat(channels, 1, 1).unsqueeze(1)
image = image.permute(0, 3, 1, 2) # Torch wants (B, C, H, W) we use (B, H, W, C)
padded_image = F.pad(image, (blur_radius,blur_radius,blur_radius,blur_radius), 'reflect')
blurred = F.conv2d(padded_image, kernel, padding=kernel_size // 2, groups=channels)[:,:,blur_radius:-blur_radius, blur_radius:-blur_radius]
blurred = blurred.permute(0, 2, 3, 1)
return (blurred,)
class Quantize:
def __init__(self):
pass
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"image": ("IMAGE",),
"colors": ("INT", {
"default": 256,
"min": 1,
"max": 256,
"step": 1
}),
"dither": (["none", "floyd-steinberg"],),
},
}
RETURN_TYPES = ("IMAGE",)
FUNCTION = "quantize"
CATEGORY = "image/postprocessing"
def quantize(self, image: torch.Tensor, colors: int = 256, dither: str = "FLOYDSTEINBERG"):
batch_size, height, width, _ = image.shape
result = torch.zeros_like(image)
dither_option = Image.Dither.FLOYDSTEINBERG if dither == "floyd-steinberg" else Image.Dither.NONE
for b in range(batch_size):
tensor_image = image[b]
img = (tensor_image * 255).to(torch.uint8).numpy()
pil_image = Image.fromarray(img, mode='RGB')
palette = pil_image.quantize(colors=colors) # Required as described in https://github.com/python-pillow/Pillow/issues/5836
quantized_image = pil_image.quantize(colors=colors, palette=palette, dither=dither_option)
quantized_array = torch.tensor(np.array(quantized_image.convert("RGB"))).float() / 255
result[b] = quantized_array
return (result,)
class Sharpen:
def __init__(self):
pass
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"image": ("IMAGE",),
"sharpen_radius": ("INT", {
"default": 1,
"min": 1,
"max": 31,
"step": 1
}),
"sigma": ("FLOAT", {
"default": 1.0,
"min": 0.1,
"max": 10.0,
"step": 0.1
}),
"alpha": ("FLOAT", {
"default": 1.0,
"min": 0.0,
"max": 5.0,
"step": 0.1
}),
},
}
RETURN_TYPES = ("IMAGE",)
FUNCTION = "sharpen"
CATEGORY = "image/postprocessing"
def sharpen(self, image: torch.Tensor, sharpen_radius: int, sigma:float, alpha: float):
if sharpen_radius == 0:
return (image,)
batch_size, height, width, channels = image.shape
kernel_size = sharpen_radius * 2 + 1
kernel = gaussian_kernel(kernel_size, sigma) * -(alpha*10)
center = kernel_size // 2
kernel[center, center] = kernel[center, center] - kernel.sum() + 1.0
kernel = kernel.repeat(channels, 1, 1).unsqueeze(1)
tensor_image = image.permute(0, 3, 1, 2) # Torch wants (B, C, H, W) we use (B, H, W, C)
tensor_image = F.pad(tensor_image, (sharpen_radius,sharpen_radius,sharpen_radius,sharpen_radius), 'reflect')
sharpened = F.conv2d(tensor_image, kernel, padding=center, groups=channels)[:,:,sharpen_radius:-sharpen_radius, sharpen_radius:-sharpen_radius]
sharpened = sharpened.permute(0, 2, 3, 1)
result = torch.clamp(sharpened, 0, 1)
return (result,)
class ImageScaleToTotalPixels:
upscale_methods = ["nearest-exact", "bilinear", "area", "bicubic", "lanczos"]
crop_methods = ["disabled", "center"]
@classmethod
def INPUT_TYPES(s):
return {"required": { "image": ("IMAGE",), "upscale_method": (s.upscale_methods,),
"megapixels": ("FLOAT", {"default": 1.0, "min": 0.01, "max": 16.0, "step": 0.01}),
}}
RETURN_TYPES = ("IMAGE",)
FUNCTION = "upscale"
CATEGORY = "image/upscaling"
def upscale(self, image, upscale_method, megapixels):
samples = image.movedim(-1,1)
total = int(megapixels * 1024 * 1024)
scale_by = math.sqrt(total / (samples.shape[3] * samples.shape[2]))
width = round(samples.shape[3] * scale_by)
height = round(samples.shape[2] * scale_by)
s = comfy.utils.common_upscale(samples, width, height, upscale_method, "disabled")
s = s.movedim(1,-1)
return (s,)
NODE_CLASS_MAPPINGS = {
"ImageBlend": Blend,
"ImageBlur": Blur,
"ImageQuantize": Quantize,
"ImageSharpen": Sharpen,
"ImageScaleToTotalPixels": ImageScaleToTotalPixels,
}
|