AI's Artistic Eye: Capturing Emotion, Missing the Shot with Leonardo-ai
- 9 minutes read - 1726 wordsTable of Contents
In the realm of artificial intelligence, generative models are pushing the boundaries of creativity. These models can generate images, text, and even music based on user prompts. However, their ability to accurately interpret and translate complex instructions remains a challenge. This blog post examines the performance of a generative AI model in creating images based on detailed scene descriptions, focusing on its ability to capture facial expressions and the overall aesthetic style. We’ll explore how the model excels in capturing the desired emotional tone but struggles with accurately representing camera position and scene details. Through this analysis, we gain insights into the strengths and weaknesses of generative AI models and the potential for future improvements.
Created with: leonardo-ai
Lost in the City Lights: A Moment of Pensive Mystery
A young man stands alone on a bustling city street, his gaze fixed on something unseen. The blurred lights of the urban landscape create a sense of intrigue, leaving us to wonder what secrets lie within his thoughts. This evocative image captures a moment of pensive mystery, inviting us to delve into the depths of his urban solitude.
Prompt
facial-expressions Excitement: Thrilled, anticipation ; A lone figure; eye-level; Single Person; bustling city street at night; cinematic
Characteristic
Shot : A man standing in an urban environment with neon lights in the background.
Aesthetic Score : 0.7
Mood : mysterious, urban, moody
Quality
Entropy : 6.26
Noise : 93
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurriness, slight noise in the shadows.
Superman Takes Flight in a Moment of Hope
A dynamic image captures Superman leaping from a rooftop, silhouetted against a vibrant city skyline and setting sun. The pose and lighting evoke a sense of heroic action and optimism, leaving viewers with a feeling of hope and inspiration.
Prompt
facial-expressions Excitement: Triumphant, exhilarating ; A superhero in mid-air; low-angle; Hero; cityscape with a dramatic sunset; cinematic
Characteristic
Shot : A man dressed as Superman jumps off a rooftop in a city with a sunset in the background.
Aesthetic Score : 0.6
Mood : heroic, dramatic, powerful
Quality
Entropy : 6.84
Noise : 94
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some minor artifacts in the sky and on the man’s costume.
Laughter and Sunshine: Capturing the Joy of Friendship
Three friends embrace the carefree spirit of a sunny day, their laughter echoing through the park. The blurred background adds a sense of motion and energy, highlighting the joy of the moment. This image captures the essence of friendship and the simple pleasures of life.
Prompt
facial-expressions Excitement: Joyful, carefree ; A group of friends laughing and running; eye-level; Normal People; a sunny park with a vibrant green lawn; cinematic
Characteristic
Shot : Three young women running through a park, laughing and enjoying themselves. The sun is shining, and the grass is green.
Aesthetic Score : 0.7
Mood : joyful, carefree, energetic
Quality
Entropy : 6.83
Noise : 99
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : None
Lost in the Game: A Gamer’s Intense Focus
A close-up shot captures a man engrossed in a video game, his headphones on, face illuminated by the glow of two monitors. The low light and dramatic framing create a sense of suspense and intensity, highlighting the gamer’s focused and determined state.
Prompt
facial-expressions Excitement: Intense, focused ; A gamer’s hands furiously tapping on a keyboard; close-up; Gamer; a dimly lit room with glowing screens; cinematic
Characteristic
Shot : A man is sitting at a desk, wearing headphones and looking at a computer screen. The room is dimly lit and there are other computer screens visible in the background.
Aesthetic Score : 0.6
Mood : focused, intense, gamer
Quality
Entropy : 6.06
Noise : 90
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly blurry, the resolution is slightly lower, and the colors are a bit muted.
Silhouetted Hope: A Woman Contemplates the Sunset
A solitary figure stands on a cliff, silhouetted against the vibrant hues of a setting sun. The vast ocean stretches before her, mirroring the contemplative mood of the scene. The dramatic contrast between the dark sky and the bright water evokes a sense of serenity and hope.
Prompt
facial-expressions Excitement: Awe-inspiring, liberating ; A woman standing on a cliff overlooking a vast ocean; eye-level; Single Person; dramatic clouds and a setting sun; cinematic
Characteristic
Shot : A lone figure stands on a cliff edge overlooking a vast ocean, with a dramatic sunset in the background. Waves crash in the distance, creating a sense of both peace and power.
Aesthetic Score : 0.8
Mood : serene, contemplative, vast
Quality
Entropy : 6.69
Noise : 103
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors.
Warrior’s Cry: A Moment of Epic Battle
A female warrior in golden armor stands defiant, her scream echoing through the smoke and fire of a chaotic battlefield. This dramatic scene captures the intensity and urgency of a pivotal moment in an epic conflict.
Prompt
facial-expressions Excitement: Brave, adrenaline-fueled ; A hero charging into battle; low-angle; Hero; a chaotic battlefield with explosions and smoke; cinematic
Characteristic
Shot : A female warrior in golden armor stands defiantly against a backdrop of explosions and smoke.
Aesthetic Score : 0.8
Mood : epic, dramatic, powerful
Quality
Entropy : 6.95
Noise : 98
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible artifacts or errors.
Birthday Joy: Friends Celebrate with Laughter and Balloons
Capture the pure happiness of a birthday celebration with this image. Four friends gather on a couch, their faces lit up with smiles and laughter as they gaze at a cluster of colorful balloons. The birthday hat and vibrant colors create a joyful and celebratory atmosphere.
Prompt
facial-expressions Excitement: Happy, celebratory ; A family celebrating a birthday; eye-level; Normal People; a brightly decorated living room with balloons and streamers; cinematic
Characteristic
Shot : Four friends are celebrating a birthday, they are sitting on a couch, there are colorful balloons and gifts in the scene
Aesthetic Score : 0.6
Mood : joyful, celebratory, playful
Quality
Entropy : 6.96
Noise : 105
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors
Lost in Thought: A Portrait of Mystery
A close-up portrait bathed in ethereal blue and pink light, capturing a moment of pensive contemplation. The blurred background adds to the sense of mystery, drawing the viewer’s attention to the man’s enigmatic gaze.
Prompt
facial-expressions Excitement: Engrossed, focused ; A gamer’s face illuminated by the screen; close-up; Gamer; a dark room with neon lights reflecting on the screen; cinematic
Characteristic
Shot : A close-up portrait of a young man’s face lit by a blue and purple light source, likely a screen or another device. The subject is looking to the left, his expression is thoughtful and introspective.
Aesthetic Score : 0.7
Mood : mysterious, contemplative, introspective
Quality
Entropy : 6.02
Noise : 86
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors or artifacts.
A Night of Thrilling Speed: Sledding Through the Glass Tunnel
Experience the rush of adrenaline as a man races down a glass-enclosed track at night. The motion blur captures the intensity of the moment, while the man’s upward gaze hints at the exhilarating freedom of the ride.
Prompt
facial-expressions Excitement: Thrilling, exhilarating ; A man riding a rollercoaster; POV shot; Single Person; a fast-paced ride with twists and turns; cinematic
Characteristic
Shot : A man is riding a sled down a track at night. The track is made of metal and is surrounded by glass walls. The man is wearing a blue shirt and is screaming as he rides.
Aesthetic Score : 0.7
Mood : intense, thrilling, adrenaline
Quality
Entropy : 6.60
Noise : 105
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some minor artifacts, such as the blurring of the man’s hair.
Man Defies the Storm, City Lights Witness His Cry
A solitary figure stands atop a rooftop, silhouetted against a dramatic cityscape. He throws his head back, yelling into the swirling storm clouds, his pose a testament to raw emotion. The scene is a powerful blend of tension, hope, and dramatic intensity.
Prompt
facial-expressions Excitement: Victorious, powerful ; A hero standing triumphantly on a rooftop; high-angle; Hero; a cityscape with a dramatic storm in the background; cinematic
Characteristic
Shot : A man stands on a rooftop, arms outstretched, facing a stormy sky. A city is visible in the background, and the ground is wet, indicating rain.
Aesthetic Score : 0.7
Mood : dramatic, intense, powerful
Quality
Entropy : 6.92
Noise : 104
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : No significant errors
Conclusion
The results of the analysis 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 0.3, which is considered below average. This suggests that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.49, which is also below average. This indicates that the model didn’t fully understand the scene described in the prompt and didn’t create an image that accurately reflects it.
- Aesthetic Analysis: The model scored 0.14, which is considered very good. This means that the generated image closely matched the expected aesthetic style, despite the issues with camera position and shot analysis.
Overall, the model seems to be better at capturing the desired aesthetic style than accurately interpreting the camera position and scene description. This suggests that the model might need further training to improve its understanding of these aspects.
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