【AI绘画】Midjourney进阶：对角线构图详解

landscape, river, Diagonal Composition, long shot, wide shot, 8k, ultra details --ar 16:9

film still, landscape, Diagonal Composition, long shot, wide shot, 8k, ultra details --ar 16:9

 film still, architectural design, guide line composition, Diagonal Composition, 8k, ultra details --ar 16:9

A white steel structure bridge, Diagonal Composition, an interior view of the modern city center with sunlight shining through large windows, a symmetrical composition, architectural photography, architectural details, steel beams, people walking on it, bright colors, and a modern architectural style with geometric lines, set against an urban landscape background. --ar 16:9

Cinematic still of a countryside road, overlooking fields and hills in the distance, Diagonal Composition, seen from a hilltop with trees on both sides of the path, in the style of a Wes Anderson movie. The scene is captured in morning light, during the daytime, with a low-angle shot, the camera looking down at the dirt trail. A tall wooden fence runs along the side of a long, straight line of rows of crops, with a few scattered green trees and a small wooden post next to the path. The distant horizon line is visible in the background. --ar 16:9

landscape, river, Diagonal Composition, dynamic flow, long shot, wide shot, 8k, ultra details --ar 16:9

mountain landscape, Diagonal Composition, depth, layered perspective, high detail, 8k --ar 16:9

portrait photography, Diagonal Composition, dynamic balance, symmetry, 8k, ultra details --ar 16:9

landscape, mountains, river, road, Diagonal Composition, natural depth, dynamic flow, 8k, ultra details --ar 16:9

architectural photography, tilted lines, staircase, corridor, Diagonal Composition, geometric depth, high contrast, 8k, ultra details --ar 16:9

portrait photography, Diagonal Composition, dynamic pose, eye direction, emotional depth, 8k, ultra details --ar 16:9

landscape, river, mountains, cinematic light, ultra realistic, high contrast, 8k --ar 16:9

landscape, river, mountains, Diagonal Composition, dynamic depth, leading lines, cinematic light, ultra realistic, high contrast, 8k --ar 16:9

import torch, torchvision.transforms as transforms; from torchvision.models import vgg19; import torch.nn.functional as F; from PIL import Image; import matplotlib.pyplot as plt; class StyleTransferModel(torch.nn.Module): def __init__(self): super(StyleTransferModel, self).__init__(); self.vgg = vgg19(pretrained=True).features; for param in self.vgg.parameters(): param.requires_grad_(False); def forward(self, x): layers = {'0': 'conv1_1', '5': 'conv2_1', '10': 'conv3_1', '19': 'conv4_1', '21': 'conv4_2', '28': 'conv5_1'}; features = {}; for name, layer in self.vgg._modules.items(): x = layer(x); if name in layers: features[layers[name]] = x; return features; def load_image(img_path, max_size=400, shape=None): image = Image.open(img_path).convert('RGB'); if max(image.size) > max_size: size = max_size; else: size = max(image.size); if shape is not None: size = shape; in_transform = transforms.Compose([transforms.Resize((size, size)), transforms.ToTensor(), transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))]); image = in_transform(image)[:3, :, :].unsqueeze(0); return image; def im_convert(tensor): image = tensor.to('cpu').clone().detach(); image = image.numpy().squeeze(); image = image.transpose(1, 2, 0); image = image * (0.229, 0.224, 0.225) + (0.485, 0.456, 0.406); image = image.clip(0, 1); return image; def gram_matrix(tensor): _, d, h, w = tensor.size(); tensor = tensor.view(d, h * w); gram = torch.mm(tensor, tensor.t()); return gram; content = load_image('content.jpg').to('cuda'); style = load_image('style.jpg', shape=content.shape[-2:]).to('cuda'); model = StyleTransferModel().to('cuda'); style_features = model(style); content_features = model(content); style_grams = {layer: gram_matrix(style_features[layer]) for layer in style_features}; target = content.clone().requires_grad_(True).to('cuda'); style_weights = {'conv1_1': 1.0, 'conv2_1': 0.8, 'conv3_1': 0.5, 'conv4_1': 0.3, 'conv5_1': 0.1}; content_weight = 1e4; style_weight = 1e2; optimizer = torch.optim.Adam([target], lr=0.003); for i in range(1, 3001): target_features = model(target); content_loss = F.mse_loss(target_features['conv4_2'], content_features['conv4_2']); style_loss = 0; for layer in style_weights: target_feature = target_features[layer]; target_gram = gram_matrix(target_feature); style_gram = style_grams[layer]; layer_style_loss = style_weights[layer] * F.mse_loss(target_gram, style_gram); b, c, h, w = target_feature.shape; style_loss += layer_style_loss / (c * h * w); total_loss = content_weight * content_loss + style_weight * style_loss; optimizer.zero_grad(); total_loss.backward(); optimizer.step(); if i % 500 == 0: print('Iteration {}, Total loss: {}'.format(i, total_loss.item())); plt.imshow(im_convert(target)); plt.axis('off'); plt.show()