AI Captures the Scene, But Misses the Mood with Midjourney
- 10 minutes read - 1919 wordsTable of Contents
In the realm of AI image generation, capturing the essence of a scene goes beyond simply replicating the elements described in a prompt. It involves understanding the nuances of composition, lighting, and overall mood. This blog post examines the performance of a generative AI model in creating images based on specific prompts, focusing on its ability to capture the desired aesthetic. We’ll explore the model’s strengths and weaknesses, highlighting its success in capturing camera position and shot composition, while also revealing its limitations in conveying the intended aesthetic. Through this analysis, we aim to shed light on the ongoing development of AI image generation and its potential to bridge the gap between human creativity and machine learning.
Created with: midjourney
Silhouetted Solitude: A Moment of Tranquility at Sunset
A lone figure stands on a hilltop, their silhouette stark against the vibrant hues of a setting sun. The scene evokes a sense of tranquility and contemplation, with the vastness of the sky and the empty landscape emphasizing the feeling of solitude. This image captures a moment of quiet reflection, leaving the viewer to ponder the figure’s thoughts and the mystery of their presence.
Prompt
leaning leaning into the wind: epic, hopeful ; A lone figure, silhouetted against a setting sun; wide shot; heroism; a vast, desolate landscape; cinematic
Characteristic
Shot : A solitary figure stands silhouetted against a setting sun on a vast, sandy plain.
Aesthetic Score : 0.6
Mood : melancholy, serene, contemplative
Quality
Entropy : 4.18
Noise : 115
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has a slight graininess and the colors are a bit faded. However, these are minor issues and do not detract significantly from the overall aesthetic.
Lost in the Darkness: Three Women Face the Unknown
A chilling scene unfolds as three young women huddle together in a shadowy cave, their faces illuminated by a single flashlight beam. The atmosphere is thick with mystery and suspense, hinting at a lurking danger. The play of light and shadow creates a dramatic effect, leaving viewers on the edge of their seats.
Prompt
leaning leaning forward, peering into the darkness: suspenseful, adventurous ; A group of adventurers, their faces illuminated by flickering torchlight; medium shot; adventure; a dark, mysterious cave; cinematic
Characteristic
Shot : Three women are looking out of a cave opening, lit by a flashlight. The cave walls are textured rock. The lighting is dramatic, with the light from the flashlight illuminating the women’s faces and the foreground, while the rest of the cave is dark.
Aesthetic Score : 0.7
Mood : suspenseful, mysterious, eerie
Quality
Entropy : 4.92
Noise : 98
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
The Glow of Focus: A Close-Up on Digital Intensity
A captivating image captures the essence of focused concentration. The close-up shot highlights the hands typing on a keyboard with red backlighting, while the blurred background and shallow depth of field emphasize the intensity of the moment. The low-key lighting adds a dramatic touch, creating a sense of digital immersion.
Prompt
leaning leaning forward, eyes glued to the screen: intense, focused ; A gamer’s hands, fingers flying across a keyboard; close-up; gaming; a brightly lit gaming setup; cinematic
Characteristic
Shot : Close-up of a person’s hands typing on a backlit keyboard, with a blurry computer screen in the background. The room is dimly lit, creating a sense of focus on the keyboard.
Aesthetic Score : 0.6
Mood : intense, focused, technological
Quality
Entropy : 4.87
Noise : 90
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Silhouettes of Love Against the Sunset Cityscape
A couple embraces on a balcony, their silhouettes framed against the breathtaking backdrop of a city bathed in the warm glow of sunset. The river below reflects the city lights, creating a tranquil and romantic scene.
Prompt
leaning leaning on the railing, arms around each other: romantic, awe-inspiring ; A couple leaning on a railing, gazing out at a breathtaking cityscape; medium shot; tourism; a vibrant, bustling city; cinematic
Characteristic
Shot : A couple is standing on a balcony overlooking a cityscape at dusk. The city lights are twinkling below, and the sky is a beautiful gradient of pink, orange, and purple. There is a river flowing through the city, and the couple is looking out at the view.
Aesthetic Score : 0.8
Mood : romantic, peaceful, hopeful
Quality
Entropy : 6.80
Noise : 91
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable artifacts or errors in the image.
A Moment of Solitude on the Mountain Ridge
A lone hiker finds peace and perspective atop a majestic mountain, overlooking a winding road that disappears into the valley. The vastness of the landscape and the smallness of the human figure create a sense of awe and solitude, capturing the essence of adventure and contemplation.
Prompt
leaning leaning against the signpost, gazing at the road: reflective, adventurous ; A backpacker, leaning against a weathered signpost, looking out at a winding mountain road; medium shot; travel; a scenic mountain range; cinematic
Characteristic
Shot : A lone hiker sits on a mountain ledge overlooking a winding road in a valley.
Aesthetic Score : 0.8
Mood : serene, adventurous, contemplative
Quality
Entropy : 6.67
Noise : 97
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors.
Golden Hour Friendship in a European Village
Four friends stroll down a cobblestone street, bathed in the warm glow of a setting sun. Their laughter and camaraderie create a joyful and nostalgic atmosphere, capturing the essence of friendship and travel.
Prompt
leaning leaning on each other, arms around each other: joyful, carefree ; A group of friends, laughing and leaning on each other, as they walk down a cobblestone street; wide shot; groups; a charming, historic town; cinematic
Characteristic
Shot : Four friends are walking down a cobblestone street in a European town, laughing and having fun together. The sun is setting in the background, casting a warm glow on the scene.
Aesthetic Score : 0.7
Mood : joyful, carefree, friendly
Quality
Entropy : 6.60
Noise : 92
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors
A Solitary Figure Against the Fury of the Storm
A lone figure stands defiant on a clifftop, silhouetted against a tempestuous sea. Dark clouds gather overhead, mirroring the internal turmoil of the subject. The dramatic contrast between the individual and the vast, unforgiving landscape evokes a sense of isolation and vulnerability, leaving a lasting impression of melancholic power.
Prompt
leaning leaning into the wind, arms outstretched: powerful, defiant ; A lone figure, standing on a cliff edge, arms outstretched, leaning into the wind; wide shot; heroism; a dramatic, stormy sea; cinematic
Characteristic
Shot : A lone figure stands on a clifftop overlooking a stormy sea with large waves crashing against the rocks. The sky is dark and brooding, creating a dramatic and atmospheric scene.
Aesthetic Score : 0.7
Mood : dramatic, melancholic, powerful
Quality
Entropy : 6.54
Noise : 105
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors. The image appears to be professionally captured.
Lost in the Fog: A Campfire’s Flickering Hope
A group huddled around a campfire in a dense, fog-shrouded forest. The scene evokes a sense of mystery and isolation, with the flickering flames casting long shadows and offering a glimmer of warmth amidst the chilling atmosphere.
Prompt
leaning leaning forward, listening intently: intimate, suspenseful ; A group of explorers, huddled around a campfire, sharing stories; medium shot; adventure; a dense, mysterious forest; cinematic
Characteristic
Shot : A group of five people are gathered around a campfire in a dark, foggy forest. The scene is lit by the fire’s glow, which illuminates the figures and the surrounding trees. The forest is dense and mysterious, and the mood is one of suspense and intrigue.
Aesthetic Score : 0.7
Mood : mysterious, suspenseful, intriguing
Quality
Entropy : 5.62
Noise : 89
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable errors in the image.
Eyes Locked on the Screen: A Moment of Intrigue
A close-up shot captures the intensity in a person’s eyes as they stare intently at a screen. The viewer is left wondering what secrets lie within the digital world, creating a sense of suspense and curiosity.
Prompt
leaning leaning forward, eyes glued to the screen: intense, focused ; A gamer’s face, illuminated by the glow of a monitor, eyes wide with excitement; close-up; gaming; a dimly lit room; cinematic
Characteristic
Shot : A close-up of a person’s eyes looking at a screen in the dark, the eyes are wide and the image has a slightly eerie feel.
Aesthetic Score : 0.5
Mood : intense, eerie, mysterious
Quality
Entropy : 5.80
Noise : 67
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image appears to be digitally painted and has a slightly grainy texture. The eyes are a bit too large and the pupils are unrealistic.
Sunset Embrace: A Romantic Moment on the Beach
Experience the tranquility and nostalgia of a couple’s tender embrace on a sandy beach at sunset. The warm glow of the setting sun casts a romantic atmosphere, while the ocean in the background adds to the serene ambiance.
Prompt
leaning leaning on each other, arms around each other: peaceful, heartwarming ; A family, leaning on each other, watching a sunset over a vast ocean; wide shot; travel; a serene, sandy beach; cinematic
Characteristic
Shot : A couple is standing on a beach at sunset, they are hugging and looking out at the ocean
Aesthetic Score : 0.7
Mood : romantic, peaceful, nostalgic
Quality
Entropy : 6.21
Noise : 70
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image seems to be a digital painting, but the style is somewhat generic and lacks individuality. The textures are slightly unnatural.
Conclusion
The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis.
Here’s a breakdown:
- Camera Position: The model scored 0.5, which falls within the “good” range (0.5 to 0.75). This means the model was able to accurately capture the camera position described in the prompt.
- Shot Analysis: The model scored 0.57, also within the “good” range. This indicates the model understood the scene described in the prompt and created an image that reflects that understanding.
- Aesthetic Analysis: The model scored 0.04, which is significantly lower than the “very good” range (-0.2 to 0.1). This suggests that the generated image’s aesthetic deviated from the expected aesthetic described in the prompt.
Overall, the model demonstrates a good understanding of camera position and shot composition, but needs improvement in capturing the desired aesthetic.
Sources:
- https://www.writerswrite.co.za/cheat-sheets-for-writing-body-language/
- https://mads3df.wordpress.com/2013/09/04/storytelling-poses/
- https://www.pinterest.com/pegasister890/character-poses/
- https://www.youtube.com/watch?v=udky6ANxWws
- https://maven.com/articles/storytelling-techniques
- https://midjourney.com