AI-Generated Images: A Mixed Bag of Camera Angles and Emotional Depth with Leonardo-ai
- 9 minutes read - 1855 wordsTable of Contents
The world of AI image generation is rapidly evolving, with models capable of creating stunning visuals from text prompts. This experiment aimed to explore the capabilities of one such model, focusing on its ability to understand and implement specific camera angles, scene descriptions, and desired aesthetics. While the model demonstrated impressive results in capturing the essence of a scene and its aesthetic qualities, it struggled with accurately implementing camera angles. This blog post delves into the analysis of the generated images, highlighting both the model’s strengths and weaknesses, and providing insights into the future of AI-powered image creation.
Created with: leonardo-ai
A Solitary Figure Faces the Unknown
A lone figure, shrouded in a brown coat, stands amidst a desolate landscape, their gaze fixed on a distant horizon obscured by a brooding sky. The starkness of the scene evokes a sense of melancholy and solitude, hinting at an impending doom that hangs heavy in the air.
Prompt
facial-expressions Determination: Solitude and resilience ; A lone figure; eye-level; Single Person; A vast, desolate landscape; cinematic
Characteristic
Shot : A solitary figure stands on a barren, dry landscape, gazing out at a vast, cloudy sky.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, lonely
Quality
Entropy : 6.42
Noise : 96
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors.
Man Stands Defiant Amidst Burning Building
A lone figure, clad in a blue jacket adorned with an American flag patch, stands resolutely in front of a blazing inferno. Black smoke billows from the building, creating a dramatic and tense scene. The contrast between the man and the fire highlights the danger and chaos of the situation.
Prompt
facial-expressions Determination: Courage and unwavering resolve ; A hero standing tall; low-angle; Hero; A burning city in the background; cinematic
Characteristic
Shot : A man in a blue jacket with an American flag patch stands in front of a burning building with a serious expression. The smoke and fire are billowing up behind him and there is debris scattered on the ground.
Aesthetic Score : 0.7
Mood : dramatic, serious, intense
Quality
Entropy : 6.56
Noise : 96
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The smoke and fire are slightly blurry, which may be due to motion blur. The man’s face is also slightly out of focus. There are also some artifacts in the image, particularly in the smoke and fire.
The Weight of Industry: A Man’s Solitary Struggle
A lone worker, clad in blue overalls, pushes a heavy cart through a dimly lit factory aisle. His serious expression and the gritty, industrial setting evoke a sense of hard labor and isolation. The dramatic contrast of light and shadow adds to the image’s unsettling mood, highlighting the man’s solitary struggle within the vastness of the factory.
Prompt
facial-expressions Determination: Grit and perseverance ; A worker pushing a heavy cart; eye-level; Normal People; A bustling factory floor; cinematic
Characteristic
Shot : A man is pushing a cart filled with crates in a factory. The man is looking directly at the camera, while two other men are walking away from the camera in the background.
Aesthetic Score : 0.7
Mood : industrial, gritty, hardworking
Quality
Entropy : 6.78
Noise : 101
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise in the shadows, and the lighting is a little uneven. The image is also slightly overexposed.
Lost in the Code: A Moment of Intense Focus
A young man, bathed in the soft glow of his computer screen, is completely absorbed in his work. The dimly lit room adds to the sense of intensity, highlighting his focused expression and the quiet drama of his concentration.
Prompt
facial-expressions Determination: Concentration and drive ; A gamer intensely focused on a screen; close-up; Gamer; A dimly lit room with glowing monitors; cinematic
Characteristic
Shot : A young man is sitting in a dimly lit room, wearing headphones and looking intently at a computer screen. He is typing on a keyboard, suggesting he is engaged in a game or other digital activity. The screen is blurred, showcasing a game interface or perhaps a video.
Aesthetic Score : 0.6
Mood : focused, intense, digital
Quality
Entropy : 5.73
Noise : 84
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some noise and grain in the shadows and darker areas, but it is not distracting. The focus on the man’s face is excellent, but the screen is slightly out of focus.
A Window to Melancholy
A woman gazes out a grimy window, her reflection lost in the city’s haze. The brick walls and somber mood evoke a sense of isolation and quiet reflection.
Prompt
facial-expressions Determination: Inner strength and hope ; A woman staring out a window; eye-level; Single Person; A stormy sky; cinematic
Characteristic
Shot : A woman is looking out of a window, with a view of a city building outside. It is likely raining or has rained recently.
Aesthetic Score : 0.6
Mood : melancholy, pensive, reflective
Quality
Entropy : 6.65
Noise : 92
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The window panes are slightly blurry, making the image seem slightly out of focus. The graininess of the image is a bit distracting.
Knight of the Storm: A Hero Stands Against the Odds
A lone knight in full armor faces a tempestuous sky, his red cape billowing in the wind. The dramatic scene evokes a sense of impending danger and heroic determination.
Prompt
facial-expressions Determination: Victory and unwavering resolve ; A hero raising a sword; low-angle; Hero; A battlefield with fallen enemies; cinematic
Characteristic
Shot : A lone knight in full armor stands in a field, looking up at a stormy sky.
Aesthetic Score : 0.8
Mood : dramatic, heroic, tense
Quality
Entropy : 6.87
Noise : 98
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts, the image is clean
Flames of Despair: Family Faces Loss in Burning Home
A poignant scene unfolds as a family, two adults and a young girl, stand before their burning home. Smoke billows into the air, and the flames lick at the windows, casting an ominous glow. The adults’ expressions are etched with concern, while the girl’s face reflects fear. The image captures the raw emotion of loss and the stark reality of destruction.
Prompt
facial-expressions Determination: Resilience and unity ; A family huddled together; eye-level; Normal People; A burning house in the background; cinematic
Characteristic
Shot : Three people, two men and a young girl, stand in front of a house engulfed in flames. The house is in the background, with the flames and smoke rising up. The composition of the image is centered on the figures, with the house and flames providing a dramatic backdrop.
Aesthetic Score : 0.6
Mood : dramatic, somber, serious
Quality
Entropy : 6.77
Noise : 102
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No major artifacts or errors in the image
In the Zone: A Gamer’s Focus Under Neon Lights
A young man is locked in a battle, his fingers flying across the keyboard. The vibrant blue and purple hues of his gaming setup create an atmosphere of intense focus and competition. The close-up shot captures the raw energy of the moment, drawing you into the heart of the action.
Prompt
facial-expressions Determination: Excitement and focus ; A gamer’s hands furiously typing on a keyboard; close-up; Gamer; A brightly lit gaming room; cinematic
Characteristic
Shot : A young man is intensely focused on a computer keyboard, lit by colorful keyboard lights and a blue light source in the background. Another person is out of focus in the background, suggesting a gaming or work environment.
Aesthetic Score : 0.6
Mood : focused, intense, determined
Quality
Entropy : 6.47
Noise : 95
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : The lighting is somewhat harsh and creates some unnatural shadows. The background is slightly blurry and lacks visual interest.
Lost in the Mist: A Figure Walks a Path of Mystery
A lone figure disappears into the swirling fog of a dense forest, creating an eerie and atmospheric scene. The path ahead seems endless, shrouded in mystery and hinting at a journey into the unknown.
Prompt
facial-expressions Determination: Hope and perseverance ; A lone figure walking towards a distant light; eye-level; Single Person; A dark, foreboding forest; cinematic
Characteristic
Shot : A lone figure walks through a dark, foggy forest. The trees are tall and thick, and the air is thick with mist. The path is narrow and winding, and the figure is lost in thought.
Aesthetic Score : 0.7
Mood : mysterious, eerie, contemplative
Quality
Entropy : 6.22
Noise : 104
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, and the fog is a little too thick. The figure is a bit blurry, and the path is not very clear.
Silhouetted Against the City: A Moment of Contemplation at Golden Hour
A solitary figure, clad in black, stands on a rooftop overlooking a sprawling metropolis bathed in the warm glow of golden hour. The dramatic lighting casts long shadows, highlighting the man’s silhouette and the city’s towering structures. The scene evokes a sense of seriousness and contemplation, capturing the essence of urban life at its most captivating.
Prompt
facial-expressions Determination: Confidence and unwavering resolve ; A hero standing on a rooftop; high-angle; Hero; A city skyline bathed in sunlight; cinematic
Characteristic
Shot : A man in a black jacket stands on a rooftop overlooking a city skyline at sunset.
Aesthetic Score : 0.7
Mood : mysterious, contemplative, urban
Quality
Entropy : 6.67
Noise : 91
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable errors in the image.
Conclusion
The analysis of the generated image shows mixed results:
- Camera Position: The model performed okay at understanding and implementing the camera position specified in the prompt. The score of 0.3 falls below the “good” range of 0.5 to 0.75.
- Shot Analysis: The model did a pretty good job of understanding the scene described in the prompt. The score of 0.58 falls within the “good” range of 0.5 to 0.75.
- Aesthetic Analysis: The model did a very good job of capturing the desired aesthetic. The score of 0.14 falls within the “very good” range of -0.2 to 0.1.
Overall, the model seems to be better at understanding the scene and aesthetic than the camera position.
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://leonardo.ai