AI's Artistic Eye: Capturing Poses, But Missing the Mark on Camera Angles with Midjourney
- 10 minutes read - 2066 words
Table of Contents
In the realm of AI image generation, capturing the essence of a prompt is paramount. This includes not only the subject matter but also the desired aesthetic, shot composition, and even the camera angle. While recent advancements have shown remarkable progress in understanding and translating prompts into visually compelling images, there are still areas where AI models struggle. One such area is the accurate representation of camera position. This blog post delves into the results of an experiment that tested an AI model’s ability to generate images based on prompts that included specific poses and camera angles, revealing both its strengths and weaknesses in this domain.
Created with: midjourney
Two Figures Stand at the Edge of the World
A breathtaking view of a mountain peak, where two figures stand silhouetted against a vast expanse of clouds and snow-capped mountains. The scene evokes a sense of peace, serenity, and awe, highlighting the smallness of humanity against the grandeur of nature.
Prompt
looking-at-each-other looking at each other, one looking at the view, the other looking at the viewer: determined, awe-inspired ; A lone adventurer, standing on a mountain peak; wide shot; adventure; a vast, breathtaking landscape with clouds swirling below; cinematic
Characteristic
Shot : Two figures stand on a mountain peak, overlooking a vast expanse of clouds and snow-capped mountains in the distance. The sky is a bright blue with white clouds.
Aesthetic Score : 0.7
Mood : serene, awe-inspiring, adventurous
Quality
Entropy : 6.18
Noise : 86
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The figures and the mountain peak are somewhat lacking in detail, and the clouds have a slightly artificial texture.
The Weight of War: A Moment of Grief on the Battlefield
A haunting image captures the somber reality of war. Two soldiers stand over a fallen comrade amidst the smoke and fire of battle, their faces etched with grief and the weight of loss. The stark contrast of light and shadow amplifies the tragedy, leaving a lasting impression of the human cost of conflict.
Prompt
looking-at-each-other looking at each other, one with concern, the other with determination: tense, hopeful ; Two soldiers, one injured, the other holding a shield; medium shot; heroism; a battlefield with smoke and fire in the background; cinematic
Characteristic
Shot : Two soldiers, one carrying a large metal object, are standing over a dead or injured soldier in a war-torn battlefield. The scene is set during a sunset with smoke and flames in the background.
Aesthetic Score : 0.6
Mood : grim, somber, serious
Quality
Entropy : 6.81
Noise : 106
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No obvious artifacts or errors, but some details may be slightly blurry or soft.
Neon Nights: A Tale of Intense Intimacy
In the heart of a dimly lit room, two men stand face to face, their expressions illuminated by the mysterious neon glow. The intense gazes and dramatic lighting create a sense of tension and intimacy, painting a picture of a story waiting to unfold.
Prompt
looking-at-each-other looking at each other, one with a triumphant grin, the other with a frustrated frown: intense, focused ; Two gamers, heads bent over a screen; close-up; gaming; a dimly lit room with neon lights reflecting on their faces; cinematic
Characteristic
Shot : Two men are facing each other, their profiles illuminated by neon lights, in what seems to be a gaming setup.
Aesthetic Score : 0.6
Mood : intense, dramatic, intimate
Quality
Entropy : 6.37
Noise : 99
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some minor artifacts, particularly around the edges of the subjects and the background, likely due to compression. There is also a slight blurriness to the image, which may be intentional.
Capturing Parisian Memories: Tourists Embrace the Eiffel Tower’s Grandeur
Three tourists, radiating joy and adventure, stroll past the iconic Eiffel Tower in Paris, capturing the moment with their phones. The towering landmark adds a sense of grandeur and scale to their happy, touristy experience.
Prompt
looking-at-each-other looking at each other, some pointing at the landmark, others taking photos: excited, curious ; A group of tourists, standing in front of a famous landmark; medium shot; tourism; a bustling city street with people and vehicles passing by; cinematic
Characteristic
Shot : Three tourists walking in front of the Eiffel Tower, taking pictures with their phones.
Aesthetic Score : 0.7
Mood : happy, touristy, carefree
Quality
Entropy : 6.84
Noise : 106
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some slight noise present in the image, particularly in the shadows, but it is minimal.
A Moment of Joy and Connection on a Train Ride
Two young women share a warm and intimate smile on a train journey, their connection highlighted by the soft lighting and the blurry backdrop of passing scenery. The mood is joyful, carefree, and full of intimacy.
Prompt
looking-at-each-other looking at each other, one with a wistful smile, the other with a thoughtful expression: reflective, nostalgic ; Two friends, sitting on a train, looking out the window; medium shot; travel; a scenic landscape with rolling hills and fields; cinematic
Characteristic
Shot : Two young women sit facing each other in a train, looking at each other with smiles. They are silhouetted against a window, and the background is a blurry field.
Aesthetic Score : 0.7
Mood : joyful, intimate, connection
Quality
Entropy : 6.07
Noise : 95
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight graininess and a few minor artifacts.
Campfire Nights Under a Starry Sky
A group of friends gather around a crackling campfire, bathed in the warm glow of the flames. The night sky above is a canvas of twinkling stars, creating a serene and nostalgic atmosphere. This cozy scene evokes feelings of friendship, warmth, and wonder.
Prompt
looking-at-each-other looking at each other, sharing stories and laughter: warm, intimate ; A group of friends, huddled together around a campfire; close-up; groups; a dark forest with stars twinkling in the sky; cinematic
Characteristic
Shot : A group of friends are sitting around a campfire under a starry sky.
Aesthetic Score : 0.7
Mood : cozy, peaceful, serene
Quality
Entropy : 5.13
Noise : 74
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : There are some minor artifacts and blurriness in the image, particularly around the edges of the figures.
Solitude at Sunset
A lone figure silhouetted against the fiery sunset, finding peace and contemplation amidst the gentle waves crashing on the shore. This serene scene evokes a sense of tranquility and the beauty of solitude.
Prompt
looking-at-each-other looking at the horizon, lost in thought: melancholy, contemplative ; A lone figure, standing on a deserted beach; wide shot; adventure; a vast ocean with crashing waves and a setting sun; cinematic
Characteristic
Shot : A lone figure stands on a beach at sunset, looking out at the ocean. The sun is setting in the distance, casting a golden glow over the sky and water.
Aesthetic Score : 0.7
Mood : peaceful, contemplative, serene
Quality
Entropy : 6.11
Noise : 112
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some slight artifacts, particularly around the edges.
Lost in the Vastness: Astronauts Adrift Against Earth’s Majesty
Two astronauts, tethered together, float amidst the cosmic expanse. The Earth, a vibrant blue marble, hangs in the distance, while a sea of stars stretches endlessly beyond. The image captures a profound sense of solitude and awe, highlighting the fragility of human existence against the immensity of space.
Prompt
looking-at-each-other looking at each other, one with a smile, the other with a determined expression: awe-inspired, hopeful ; Two astronauts, floating in space; medium shot; heroism; a view of Earth from space with stars and galaxies in the background; cinematic
Characteristic
Shot : Two astronauts floating in space, tethered together, with Earth in the background and a starry nebula above.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, hopeful
Quality
Entropy : 6.31
Noise : 101
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image appears to have some subtle artifacts, particularly in the nebula and Earth’s surface. The colors also appear slightly desaturated.
Sunlight Illuminates Adventure in the Jungle
Four young explorers trek through a dense jungle, bathed in the golden rays of the sun. The light beams create an air of mystery and wonder, beckoning them deeper into the unknown. This adventurous scene captures a sense of hope and curiosity, promising an exciting journey ahead.
Prompt
looking-at-each-other looking at each other, one pointing at something in the distance, others with expressions of wonder: curious, adventurous ; A group of explorers, standing in a jungle clearing; medium shot; adventure; lush greenery with sunlight filtering through the leaves; cinematic
Characteristic
Shot : A group of four explorers, two men and two women, are standing in a lush green jungle, looking up at the sunlight filtering through the canopy.
Aesthetic Score : 0.7
Mood : adventurous, hopeful, curious
Quality
Entropy : 6.48
Noise : 121
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The painting style is somewhat stylized, with a noticeable painterly texture. There’s some blurring and color mixing, especially in the foliage. The light beams are somewhat unnatural and too uniform.
Silhouettes of Love Against the City Lights
A couple stands on a bridge, their silhouettes framed against the twinkling cityscape. The night air is filled with romance, dreams, and a touch of nostalgia. This scene captures the intimacy of a shared moment against the backdrop of a vibrant city.
Prompt
looking-at-each-other looking at each other, one with a loving gaze, the other with a shy smile: romantic, intimate ; Two lovers, standing on a bridge overlooking a city; medium shot; tourism; a cityscape with twinkling lights and a river flowing below; cinematic
Characteristic
Shot : A couple is standing on a bridge at night, gazing at the city lights across a river. The scene is romantic and peaceful, with a soft, dreamy atmosphere.
Aesthetic Score : 0.7
Mood : romantic, dreamy, peaceful
Quality
Entropy : 6.38
Noise : 93
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image has a slightly blurry or soft focus effect, which may be intentional but could be distracting for some viewers. The city lights in the background have a somewhat unnatural and repetitive pattern, which could be more realistic and varied.
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 0.45, which is considered okay. This means the generated image’s camera position was somewhat similar to what was requested in the prompt. A score closer to 0.75 or higher would indicate a better understanding of the desired camera position.
- Shot Analysis: The model scored 0.5, which is also considered okay. This means the generated image’s shot composition was somewhat similar to what was requested in the prompt. A score closer to 0.75 or higher would indicate a better understanding of the desired shot composition.
- Aesthetic Analysis: The model scored 0.02, which is considered very good. This means the generated image’s aesthetic was very close to what was expected based on the prompt. A score closer to -0.2 would indicate an even better match.
Overall, the model seems to be better at understanding the aesthetic and shot composition of the prompt than the camera position.
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