【AI绘画】Midjourney前置指令/blend、/info、/subscribe详解

/*
* 提示：该行代码过长，系统自动注释不进行高亮。一键复制会移除系统注释 
* import torch, torch.nn as nn, torch.optim as optim; from torch.utils.data import Dataset, DataLoader; from torchvision import transforms, utils; from PIL import Image; import numpy as np, cv2, os, random; class PaintingDataset(Dataset): def __init__(self, root_dir, transform=None): self.root_dir = root_dir; self.transform = transform; self.image_files = os.listdir(root_dir); def __len__(self): return len(self.image_files); def __getitem__(self, idx): img_name = os.path.join(self.root_dir, self.image_files[idx]); image = Image.open(img_name).convert('RGB'); if self.transform: image = self.transform(image); return image; class ResidualBlock(nn.Module): def __init__(self, in_channels): super(ResidualBlock, self).__init__(); self.conv_block = nn.Sequential(nn.Conv2d(in_channels, in_channels, kernel_size=3, stride=1, padding=1), nn.InstanceNorm2d(in_channels), nn.ReLU(inplace=True), nn.Conv2d(in_channels, in_channels, kernel_size=3, stride=1, padding=1), nn.InstanceNorm2d(in_channels)); def forward(self, x): return x + self.conv_block(x); class Generator(nn.Module): def __init__(self): super(Generator, self).__init__(); self.downsampling = nn.Sequential(nn.Conv2d(3, 64, kernel_size=7, stride=1, padding=3), nn.InstanceNorm2d(64), nn.ReLU(inplace=True), nn.Conv2d(64, 128, kernel_size=3, stride=2, padding=1), nn.InstanceNorm2d(128), nn.ReLU(inplace=True), nn.Conv2d(128, 256, kernel_size=3, stride=2, padding=1), nn.InstanceNorm2d(256), nn.ReLU(inplace=True)); self.residuals = nn.Sequential(*[ResidualBlock(256) for _ in range(9)]); self.upsampling = nn.Sequential(nn.ConvTranspose2d(256, 128, kernel_size=3, stride=2, padding=1, output_padding=1), nn.InstanceNorm2d(128), nn.ReLU(inplace=True), nn.ConvTranspose2d(128, 64, kernel_size=3, stride=2, padding=1, output_padding=1), nn.InstanceNorm2d(64), nn.ReLU(inplace=True), nn.Conv2d(64, 3, kernel_size=7, stride=1, padding=3), nn.Tanh()); def forward(self, x): x = self.downsampling(x); x = self.residuals(x); x = self.upsampling(x); return x; class Discriminator(nn.Module): def __init__(self): super(Discriminator, self).__init__(); self.model = nn.Sequential(nn.Conv2d(3, 64, kernel_size=4, stride=2, padding=1), nn.LeakyReLU(0.2, inplace=True), nn.Conv2d(64, 128, kernel_size=4, stride=2, padding=1), nn.InstanceNorm2d(128), nn.LeakyReLU(0.2, inplace=True), nn.Conv2d(128, 256, kernel_size=4, stride=2, padding=1), nn.InstanceNorm2d(256), nn.LeakyReLU(0.2, inplace=True), nn.Conv2d(256, 512, kernel_size=4, stride=2, padding=1), nn.InstanceNorm2d(512), nn.LeakyReLU(0.2, inplace=True), nn.Conv2d(512, 1, kernel_size=4, stride=1, padding=1)); def forward(self, x): return self.model(x); def initialize_weights(model): for m in model.modules(): if isinstance(m, (nn.Conv2d, nn.ConvTranspose2d)): nn.init.normal_(m.weight.data, 0.0, 0.02); elif isinstance(m, nn.InstanceNorm2d): nn.init.normal_(m.weight.data, 1.0, 0.02); nn.init.constant_(m.bias.data, 0); device = torch.device("cuda" if torch.cuda.is_available() else "cpu"); generator = Generator().to(device); discriminator = Discriminator().to(device); initialize_weights(generator); initialize_weights(discriminator); transform = transforms.Compose([transforms.Resize(256), transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])]); dataset = PaintingDataset(root_dir='path_to_paintings', transform=transform); dataloader = DataLoader(dataset, batch_size=16, shuffle=True); criterion = nn.MSELoss(); optimizerG = optim.Adam(generator.parameters(), lr=0.0002, betas=(0.5, 0.999)); optimizerD = optim.Adam(discriminator.parameters(), lr=0.0002, betas=(0.5, 0.999)); def generate_noise_image(height, width): return torch.randn(1, 3, height, width, device=device); for epoch in range(100): for i, data in enumerate(dataloader): real_images = data.to(device); batch_size = real_images.size(0); optimizerD.zero_grad(); noise_image = generate_noise_image(256, 256); fake_images = generator(noise_image); real_labels = torch.ones(batch_size, 1, 16, 16, device=device); fake_labels = torch.zeros(batch_size, 1, 16, 16, device=device); output_real = discriminator(real_images); output_fake = discriminator(fake_images.detach()); loss_real = criterion(output_real, real_labels); loss_fake = criterion(output_fake, fake_labels); lossD = (loss_real + loss_fake) / 2; lossD.backward(); optimizerD.step(); optimizerG.zero_grad(); output_fake = discriminator(fake_images); lossG = criterion(output_fake, real_labels); lossG.backward(); optimizerG.step(); with torch.no_grad(): fake_image = generator(generate_noise_image(256, 256)).detach().cpu(); grid = utils.make_grid(fake_image, normalize=True); utils.save_image(grid, f'output/fake_painting_epoch_{epoch}.png'); def apply_style_transfer(content_img, style_img, output_img, num_steps=500, style_weight=1000000, content_weight=1): vgg = models.vgg19(pretrained=True).features.to(device).eval(); for param in vgg.parameters(): param.requires_grad = False; content_img = Image.open(content_img).convert('RGB'); style_img = Image.open(style_img).convert('RGB'); content_img = transform(content_img).unsqueeze(0).to(device); style_img = transform(style_img).unsqueeze(0).to(device); target = content_img.clone().requires_grad_(True).to(device); optimizer = optim.LBFGS([target]); content_layers = ['conv_4']; style_layers = ['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']; def get_features(image, model): layers = {'0': 'conv_1', '5': 'conv_2', '10': 'conv_3', '19': 'conv_4', '28': 'conv_5'}; features = {}; x = image; for name, layer in model._modules.items(): x = layer(x); if name in layers: features[layers[name]] = x; return features; def gram_matrix(tensor): _, d, h, w = tensor.size(); tensor = tensor.view(d, h * w); gram = torch.mm(tensor, tensor.t()); return gram; content_features = get_features(content_img, vgg); style_features = get_features(style_img, vgg); style_grams = {layer: gram_matrix(style_features[layer]) for layer in style_features}; for step in range(num_steps): def closure(): target_features = get_features(target, vgg); content_loss = torch.mean((target_features[content_layers[0]] - content_features[content_layers[0]])**2); style_loss = 0; for layer in style_layers: target_gram = gram_matrix(target_features[layer]); style_gram = style_grams[layer]; layer_style_loss = torch.mean((target_gram - style_gram)**2); style_loss += layer_style_loss / (target_gram.shape[1] ** 2); total_loss = content_weight * content_loss + style_weight * style_loss; optimizer.zero_grad(); total_loss.backward(); return total_loss; optimizer.step(closure); target = target.squeeze().cpu().clamp_(0, 1); utils.save_image(target, output_img);
*/