AI's Artistic Eye: Capturing Poses, Missing the Shot with Leonardo-ai
- 9 minutes read - 1799 wordsTable of Contents
Dramatic style poses are often used in photography and filmmaking to create a sense of excitement, tension, or emotion. These poses can be used to emphasize the subject’s personality, to tell a story, or to simply create a visually striking image. For example, a lone warrior standing on a hilltop with his arms outstretched might be used to convey a sense of power and heroism. Or, a couple riding a motorcycle on a winding road might be used to convey a sense of freedom and adventure. In this blog post, we explore the capabilities of a generative AI model in capturing these dramatic poses and the challenges it faces in accurately translating scene descriptions into visual representations.
Created with: leonardo-ai
Warrior’s Resolve in the Heart of the Inferno
A female warrior, clad in battle-worn armor, stands defiant amidst a smoky, fiery landscape. Flames lick at her feet, fueling her determination as she grips her sword, ready to face any challenge. The dramatic scene captures the intensity and ferocity of a warrior’s spirit.
Prompt
poses action-pose: determined, heroic ; Lone warrior; wide shot; Heroism; Epic battle scene with smoke and fire; cinematic
Characteristic
Shot : A female warrior in armor stands in a battle-torn landscape, a sword in hand, with smoke and fire behind her.
Aesthetic Score : 0.7
Mood : epic, dramatic, powerful
Quality
Entropy : 6.89
Noise : 98
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
Contemplating the Peaks: A Hiker Finds Serenity Amidst Dramatic Clouds
A lone hiker stands on a mountaintop, dwarfed by the majestic snow-capped peaks and a sky filled with dramatic clouds. The scene evokes a sense of serenity, contemplation, and adventure, capturing the awe-inspiring beauty of nature.
Prompt
poses action-pose: adventurous, awe-inspired ; Adventurer standing on a cliff edge; medium shot; Adventure; Majestic mountain range with clouds; cinematic
Characteristic
Shot : A lone hiker stands on a rocky peak, looking out at a snow-capped mountain range. The sky is cloudy, but there is a hint of sunlight breaking through. The overall impression is one of peace and solitude.
Aesthetic Score : 0.75
Mood : serene, contemplative, adventurous
Quality
Entropy : 6.79
Noise : 98
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible artifacts or errors. Image quality is high.
Neon Glow, Intense Focus: Gamer Lost in the Digital World
A young man, headphones on, is completely absorbed in a game, his face illuminated by vibrant neon lights. The scene captures the intensity and futuristic atmosphere of the gaming world, with the dramatic lighting highlighting his focused concentration.
Prompt
poses action-pose: focused, intense ; Gamer holding a controller; close-up; Gaming; Neon-lit gaming room with multiple screens; cinematic
Characteristic
Shot : A young man is sitting in a dimly lit room wearing headphones and playing a video game. The room is decorated with colorful neon lights, suggesting a gaming setup.
Aesthetic Score : 0.7
Mood : intense, focused, futuristic
Quality
Entropy : 6.01
Noise : 86
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant image errors are present, but the overall image appears slightly overexposed, especially in the background, and the sharpness could be improved.
Sun-Kissed Selfie: Capturing Joy in Front of a Majestic Building
A man beams with happiness as he takes a selfie in front of a grand building. His sunglasses and hat add to the carefree vibe, while the bright sun and his infectious smile create a sense of pure joy. The bustling background adds a touch of life to this cheerful scene.
Prompt
poses action-pose: happy, excited ; Tourist taking a selfie in front of a famous landmark; medium shot; Tourism; Busy city square with people and street performers; cinematic
Characteristic
Shot : A man in sunglasses and a hat is taking a selfie in front of a large church or cathedral. There are people walking around in the background. It is a sunny day.
Aesthetic Score : 0.6
Mood : happy, touristy, cheerful
Quality
Entropy : 6.97
Noise : 101
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed. There are a few artifacts in the background, particularly around the edges of the church.
Freedom on Two Wheels: A Woman’s Joyful Ride Through a Sun-Kissed Vineyard
Capture the essence of adventure and freedom as a woman speeds through a picturesque vineyard on a sunny day. This image evokes a sense of joy and exhilaration, showcasing the beauty of the countryside and the thrill of the open road.
Prompt
poses action-pose: free, adventurous ; Couple riding a motorcycle on a winding road; wide shot; Travel; Scenic countryside with rolling hills and vineyards; cinematic
Characteristic
Shot : A woman riding a motorcycle on a winding road through a vineyard
Aesthetic Score : 0.7
Mood : adventure, freedom, summer
Quality
Entropy : 6.88
Noise : 107
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors
City Lights, Rooftop Vibes, and Good Company
Three friends bask in the warm glow of city lights, enjoying drinks and laughter on a rooftop patio. The scene exudes joy, relaxation, and a sense of camaraderie, making it a perfect snapshot of a night out with friends.
Prompt
poses action-pose: joyful, celebratory ; Group of friends celebrating with drinks; medium shot; Groups; Rooftop bar with city lights in the background; cinematic
Characteristic
Shot : Three friends enjoying drinks on a rooftop patio at dusk, with a city skyline in the background.
Aesthetic Score : 0.8
Mood : relaxed, happy, social
Quality
Entropy : 6.38
Noise : 97
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable errors or artifacts.
Silhouetted Against the City: A Woman on the Edge
A mysterious figure in a futuristic outfit crouches on a rooftop, silhouetted against the vibrant cityscape at dusk. The low angle and dramatic lighting create a sense of suspense and action, hinting at a story waiting to unfold.
Prompt
poses action-pose: powerful, confident ; Superhero landing on a rooftop; wide shot; Heroism; City skyline with skyscrapers and neon lights; cinematic
Characteristic
Shot : A woman in a futuristic outfit is crouching on a rooftop overlooking a city skyline at dusk.
Aesthetic Score : 0.7
Mood : dramatic, intense, futuristic
Quality
Entropy : 6.75
Noise : 96
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable artifacts or errors in the image.
Lost in the Jungle: A Man’s Determined Journey
A lone adventurer navigates a dense, verdant jungle, his backpack heavy with supplies and his gaze fixed on the unknown. The dappled sunlight filtering through the canopy creates an atmosphere of mystery and intrigue, hinting at the challenges and discoveries that lie ahead. His determined expression speaks of a spirit unyielding, ready to face whatever the jungle throws his way.
Prompt
poses action-pose: determined, adventurous ; Explorer navigating a jungle path; medium shot; Adventure; Lush green jungle with vines and sunlight filtering through the canopy; cinematic
Characteristic
Shot : A man is walking through a dense jungle, his face is determined and serious. There are large green leaves surrounding him.
Aesthetic Score : 0.7
Mood : adventurous, intense, mysterious
Quality
Entropy : 6.72
Noise : 103
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors or artifacts
Behind the Scenes: A Glimpse into the Excitement of a Live Event
This collage captures the energy and anticipation of a major event, showcasing the audience, the stage, and the backstage crew working tirelessly to bring the show to life. The diverse perspectives create a dynamic and immersive experience, highlighting the professionalism and excitement that define this event.
Prompt
poses action-pose: intense, focused ; Gamer competing in an esports tournament; close-up; Gaming; Stadium filled with cheering fans and bright lights; cinematic
Characteristic
Shot : A collage of images showing the behind-the-scenes action of a large esports event, with a focus on the control room and the production team. The event is taking place in a large arena, with a packed audience.
Aesthetic Score : 0.6
Mood : intense, focused, professional
Quality
Entropy : 6.27
Noise : 105
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some of the images appear slightly blurry, especially the close-ups. There is also some noise in the images, especially in the darker areas.
Silhouettes of Hope: A Family’s Sunset Stroll
A heartwarming scene of a family walking hand-in-hand on a beach at sunset, their silhouettes against the vibrant sky creating a powerful image of hope and togetherness. The tranquil mood and beautiful composition evoke feelings of happiness and optimism.
Prompt
poses action-pose: happy, relaxed ; Family posing for a photo in front of a sunset; medium shot; Travel; Beach with golden sand and turquoise water; cinematic
Characteristic
Shot : A family of three, a man, woman and a girl, are walking on a beach towards a setting sun. The beach is sandy and the ocean is calm, with a few waves breaking gently.
Aesthetic Score : 0.7
Mood : tranquil, serene, heartwarming
Quality
Entropy : 6.72
Noise : 104
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors. Slight noise in the sky and sand, but it’s a minor cosmetic detail that doesn’t detract from the image.
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 0.4, which is considered below average. This suggests that the model didn’t accurately capture the intended camera positions described in the prompt.
- Shot Analysis: The model scored 0.48, 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 reflected the intended shot.
- Aesthetic Analysis: The model scored 0.00000000000000011102230246251566, which is considered very good. This means the generated image closely matched the expected aesthetic style.
Overall, the model seems to be struggling with understanding and implementing the camera positions and shot descriptions provided in the prompt. However, it excels at generating images that match the desired aesthetic.