AI Captures Scenes, But Struggles with Camera Angles with Midjourney
- 9 minutes read - 1821 wordsTable of Contents
Generative AI models are revolutionizing the way we create images. These models can generate realistic and visually appealing images based on text prompts, offering exciting possibilities for various applications. However, understanding the nuances of scene descriptions and accurately capturing camera positions remains a challenge. This blog post explores the capabilities of a generative AI model in this domain, analyzing its performance across different scenarios and highlighting its strengths and weaknesses.
Created with: midjourney
Finding Peace in a Cozy Cafe
A young woman finds solace and contentment in a warm cafe, her smile radiating warmth as she gazes out the window. The steam rising from her coffee adds to the cozy atmosphere, creating a scene of pure peace and relaxation.
Prompt
Contentment Contentment, a slight smile: Peaceful and relaxed ; A single person; eye-level; Single Persons; a cozy cafe with soft lighting and the aroma of coffee; cinematic
Characteristic
Shot : A young woman sits at a cafe table, looking out the window, with a cup of coffee in front of her. The cafe is warmly lit and has a cozy, inviting atmosphere.
Aesthetic Score : 0.8
Mood : cozy, relaxed, content
Quality
Entropy : 6.61
Noise : 97
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has a slight blurriness, but it’s likely due to the artistic style.
Superman Silhouetted Against a Hopeful Sunset
A dramatic image captures Superman standing on a rooftop, his silhouette against the setting sun. The Empire State Building looms in the background, adding to the sense of grandeur and heroism. The mood is hopeful, suggesting a brighter future for the city.
Prompt
Contentment Contentment, a sense of accomplishment: Triumphant and serene ; A superhero; eye-level; Heroes; a cityscape at sunset, with the hero standing on a rooftop, looking out at the view; cinematic
Characteristic
Shot : A superhero stands on a rooftop overlooking a city skyline at sunset. The sun is setting in the background, casting a warm glow over the scene. The hero is looking out over the city, his cape billowing in the breeze.
Aesthetic Score : 0.7
Mood : heroic, dramatic, hopeful
Quality
Entropy : 6.32
Noise : 79
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slightly blurry texture. Some of the buildings in the distance appear as if they’re lacking detail and could be sharper.
Laughter and Light: Friends Share a Joyful Dinner
A group of friends gather around a table, their laughter filling the air. Warm lighting and a focus on their shared joy create a sense of intimacy and connection, capturing the essence of a happy and convivial evening.
Prompt
Contentment Contentment, smiles and laughter: Warm and loving ; A family having dinner; eye-level; Normal People; a warm, well-lit kitchen with the family laughing and talking; cinematic
Characteristic
Shot : A group of friends are having dinner together at a table in a kitchen. They are laughing and enjoying each other’s company.
Aesthetic Score : 0.7
Mood : happy, warm, joyful
Quality
Entropy : 6.66
Noise : 93
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly grainy. The lighting is also a bit uneven, but the composition is good.
Lost in the Digital Cityscape
A man sits in a dimly lit room, his gaze fixed on a computer screen displaying a vibrant, yet muted, cityscape. The digital painting evokes a sense of calm contemplation, inviting viewers to share in the moment of quiet introspection.
Prompt
Contentment Contentment, a slight grin: Focused and absorbed ; A gamer; eye-level; Gamer; a dimly lit room with a computer screen displaying a game, the gamer is focused but relaxed; cinematic
Characteristic
Shot : A young man is sitting at a desk in a dimly lit room, looking at a computer monitor. The light from the monitor illuminates his face and the desk, creating a stark contrast against the dark background.
Aesthetic Score : 0.6
Mood : focused, calm, contemplative
Quality
Entropy : 5.53
Noise : 67
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slight digital artifacting effect, particularly in the darker areas, indicating potential compression or processing.
Sunlit Serenity: A Moment of Tranquility
A woman finds peace in the warm glow of sunlight as she reads a book in a comfortable armchair. The scene evokes a sense of tranquility and solitude, highlighting the beauty of simple moments.
Prompt
Contentment Contentment, a relaxed expression: Peaceful and introspective ; A woman reading a book; eye-level; Single Persons; a sunlit window seat with a comfortable armchair and a cup of tea; cinematic
Characteristic
Shot : A woman in a white dress sits in a chair by a window, reading a book. Sunlight streams in, illuminating her and the room.
Aesthetic Score : 0.8
Mood : serene, peaceful, contemplative
Quality
Entropy : 6.70
Noise : 95
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors or artifacts.
Firefighter’s Gentle Rescue Wins Over Tiny Kitten
A heartwarming scene unfolds as a firefighter, with a tender touch, rescues a frightened kitten clinging to a tree branch. The image captures the contrast between the rugged firefighter and the vulnerable kitten, evoking a sense of warmth and compassion.
Prompt
Contentment Contentment, a smile of relief: Relieved and happy ; A firefighter rescuing a kitten from a tree; eye-level; Heroes; a lush green park with sunlight filtering through the leaves; cinematic
Characteristic
Shot : A firefighter in full gear is gently reaching out to a kitten perched on a tree branch in a lush, green forest setting, illuminated by dappled sunlight.
Aesthetic Score : 0.7
Mood : gentle, hopeful, heartwarming
Quality
Entropy : 6.52
Noise : 92
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.30
Image errors : Some minor image artifacts are present, particularly in the background, indicating potential digital manipulation or compression.
Summer Days and Happy Faces: A Picnic Under the Sun
A group of friends bask in the warmth of a sunny day, enjoying a carefree picnic under a sprawling tree. The red and white checkered blanket, overflowing basket of goodies, and their relaxed smiles evoke a sense of nostalgia and pure joy, capturing the essence of a perfect summer afternoon.
Prompt
Contentment Contentment, laughter and smiles: Joyful and carefree ; A group of friends having a picnic; eye-level; Normal People; a sunny meadow with a checkered blanket and a basket of food; cinematic
Characteristic
Shot : A group of four friends are enjoying a picnic under a tree in a grassy field. They are laughing and talking, and there are drinks and food on the blanket.
Aesthetic Score : 0.6
Mood : happy, carefree, summery
Quality
Entropy : 6.53
Noise : 114
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly grainy and the colors are a bit washed out.
Champion’s Glory: Confetti Rain Down on Triumphant Young Man
A young man basks in the spotlight, holding a trophy aloft as confetti rains down around him. The scene is electric with excitement and triumph, captured in a moment of pure joy and celebration.
Prompt
Contentment Contentment, a wide grin and a sense of accomplishment: Excited and triumphant ; A gamer winning a tournament; eye-level; Gamer; a brightly lit stage with a cheering crowd and the gamer holding up a trophy; cinematic
Characteristic
Shot : A gamer holding up a trophy in a crowded arena with confetti falling. The lights are bright and the scene is energetic.
Aesthetic Score : 0.8
Mood : triumphant, exciting, celebratory
Quality
Entropy : 6.57
Noise : 105
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The confetti seems slightly blurred in places.
Peaceful Moments on the Porch
A heartwarming painting capturing the serenity of an older man enjoying a sunny afternoon on his porch swing. The blooming tree, soft light, and his contented smile evoke a sense of peace and nostalgia.
Prompt
Contentment Contentment, a wistful smile: Peaceful and nostalgic ; A man sitting on a porch swing; eye-level; Single Persons; a quiet suburban street with a blooming garden and the sound of birds chirping; cinematic
Characteristic
Shot : A man is sitting on a porch swing in a backyard. There is a blooming tree in the background. The scene is painted in a realistic style.
Aesthetic Score : 0.7
Mood : tranquil, peaceful, nostalgic
Quality
Entropy : 6.74
Noise : 118
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.00
Image errors : The brushstrokes in the painting are slightly visible.
Reunited and It Feels So Good: Couple’s Joyful Embrace at Train Station
A heartwarming scene unfolds as a couple, reunited after a long separation, embraces in front of a cheering crowd at a train station. The image captures the raw emotion of their reunion, with the surrounding crowd adding to the sense of occasion and joy.
Prompt
Contentment Contentment, tears of joy and hugs: Joyful and emotional ; A group of soldiers returning home; eye-level; Heroes; a bustling airport terminal with families waiting to greet their loved ones; cinematic
Characteristic
Shot : A man and woman embrace at an airport, likely after a long separation. They are surrounded by a crowd of people also waiting or departing.
Aesthetic Score : 0.7
Mood : joyful, emotional, hopeful
Quality
Entropy : 6.48
Noise : 108
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.00
Image errors : Some minor graininess in the image, potentially due to the age of the photograph
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.1, indicating it did not perform well in capturing the intended camera position. This suggests the model may not be very sensitive to camera position instructions.
- Shot Analysis: The model scored 0.47, which is considered good. This means the model was able to understand the scene in the prompt and create an image that reflects it fairly well.
- Aesthetic Analysis: The model scored 0.07, which is considered very good. This means the generated image closely matched the expected aesthetic, indicating the model is capable of producing visually appealing results.
Overall, the model shows promise in understanding scene descriptions and creating visually pleasing images, but needs improvement in accurately capturing camera positions.
Sources:
- https://dramaresource.com/storytelling/
- https://seedsoftellers.eu/resources/the-body-language-for-young-tellers/
- https://digitalcollections.sit.edu/cgi/viewcontent.cgi?article=1288&context=sandanona&filename=1&type=additional
- https://citeseerx.ist.psu.edu/document?doi=7f842882e9bb1fa2c0e96939bc8d2c37e34e17c0&repid=rep1&type=pdf
- https://www.twinkl.co.uk/search?q=drama+facial+expression
- https://midjourney.com