AI's Artistic Journey: Capturing Poses, But Missing the Mood with Freepik
- 9 minutes read - 1831 wordsTable of Contents
In the realm of artificial intelligence, image generation has emerged as a fascinating area of exploration. Generative AI models, trained on vast datasets of images and text, can now create stunning visuals based on textual descriptions. However, the ability to capture the nuances of human expression, particularly in poses and aesthetics, remains a challenge. This blog post delves into the capabilities and limitations of a generative AI model in creating images based on text prompts, focusing on its performance in capturing poses and aesthetics.
Created with: freepik
A Solitary Figure in a War-Torn City
A lone figure, cloaked in brown, walks through the ruins of a war-torn city. The setting sun casts a melancholic glow on the scene, highlighting the stark contrast between the figure’s solitude and the devastation around them. This image evokes a sense of somber contemplation and mystery, leaving the viewer to ponder the story behind the lone figure and the city’s fate.
Prompt
poses walking-away: Melancholy, yet hopeful ; Lone figure in a tattered cloak; wide shot; Heroism; Ruins of a fallen city bathed in the golden light of a setting sun; cinematic
Characteristic
Shot : A lone figure walks down a destroyed street in the aftermath of a war, bathed in the golden light of sunrise.
Aesthetic Score : 0.7
Mood : melancholy, hopeful, somber
Quality
Entropy : 6.76
Noise : 71
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.60
Image errors : The image appears slightly blurry and some details in the background appear artificial, suggesting potential AI manipulation.
Lost in the Green: A Hiker’s Journey Through Mystery
A lone hiker ventures into a lush, verdant forest bathed in soft, diffused light. The air hangs heavy with mystery, inviting you to explore the unknown paths ahead. This serene and adventurous scene evokes a sense of wonder and intrigue, leaving you captivated by the beauty and the promise of discovery.
Prompt
poses walking-away: Excited, adventurous ; A young adventurer with a backpack; medium shot; Adventure; Lush jungle with a hidden path leading into the unknown; cinematic
Characteristic
Shot : A person is walking on a path through a lush green forest. The path is lined with large trees and leafy plants. The person is wearing a backpack and is looking forward.
Aesthetic Score : 0.7
Mood : mysterious, tranquil, adventurous
Quality
Entropy : 6.83
Noise : 77
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Neon Dreams: A Young Man’s Focus in a Futuristic Cityscape
Immersed in a world of neon lights and urban sprawl, a young man sits at his desk, headphones on, eyes fixed on his computer screen. The intensity of his focus, the vibrant colors, and the futuristic setting create a captivating scene that hints at a world of possibilities.
Prompt
poses walking-away: Focused, determined ; A gamer with a headset; close-up; Gaming; Neon-lit cityscape reflected in a computer screen; cinematic
Characteristic
Shot : A young man is playing video games. The scene is set in a dimly lit room with a cityscape in the background. The man is wearing headphones and a hoodie. There are multiple monitors in front of him.
Aesthetic Score : 0.6
Mood : focused, intense, futuristic
Quality
Entropy : 6.78
Noise : 53
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image is slightly blurry, and there are some artifacts around the edges of the monitors.
A Timeless Romance on the Cobblestone Streets of Europe
Experience the nostalgic charm of a European town as a couple embarks on a romantic journey down a narrow cobblestone street. With pastel-colored buildings in shades of orange and blue lining their path, the couple’s intimate connection is emphasized by their back-turned view. The dramatic effect of the cobblestone street leading towards the vanishing point invites the viewer to join them on this happy and mysterious adventure.
Prompt
poses walking-away: Romantic, carefree ; A couple holding hands; medium shot; Tourism; Picturesque European street with cobblestone paths and colorful buildings; cinematic
Characteristic
Shot : A couple walks hand-in-hand down a cobblestone street in a European city. The buildings lining the street are brightly colored and the couple’s backs are turned to the camera.
Aesthetic Score : 0.7
Mood : romantic, cozy, nostalgic
Quality
Entropy : 6.83
Noise : 83
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.30
Image errors : No major errors. Some minor color banding may be present.
Chasing the Setting Sun, and a New Beginning
A lone traveler, silhouetted against the fiery sunset, watches an airplane take off. His brown jacket and suitcase suggest a journey, while the dramatic light evokes a sense of both melancholy and hopeful anticipation.
Prompt
poses walking-away: Nostalgic, bittersweet ; A lone traveler with a suitcase; long shot; Travel; Airport runway with a departing airplane in the distance; cinematic
Characteristic
Shot : A man walks towards a plane taking off at an airport runway at sunset. He is pulling a suitcase behind him.
Aesthetic Score : 0.7
Mood : reflective, hopeful, adventurous
Quality
Entropy : 6.63
Noise : 47
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : None
Sunset Smiles: Three Friends Embrace Joy on the Beach
Capture the essence of carefree happiness as three young women stroll along a sandy beach at sunset, their laughter echoing in the warm, golden light. This heartwarming scene radiates joy and freedom, creating a dreamy atmosphere that’s sure to evoke a sense of contentment.
Prompt
poses walking-away: Joyful, carefree ; A group of friends laughing; wide shot; Groups; Beach at sunset with the ocean waves crashing in the background; cinematic
Characteristic
Shot : Three young women are walking along a sandy beach at sunset, holding hands. The beach is empty except for them, and the setting sun creates a warm glow.
Aesthetic Score : 0.7
Mood : happy, carefree, summery
Quality
Entropy : 6.52
Noise : 54
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors.
A Warrior’s Journey Through the Misty Forest
A lone warrior strides down a path shrouded in mist, the light of dawn breaking through the trees. The scene evokes a sense of mystery, adventure, and epic scale, with the mist adding depth and the light offering hope.
Prompt
poses walking-away: Determined, resolute ; A lone warrior with a sword; medium shot; Heroism; Dark forest with a path leading into the shadows; cinematic
Characteristic
Shot : A lone figure in medieval garb walks down a path through a dense, misty forest.
Aesthetic Score : 0.8
Mood : mysterious, somber, adventurous
Quality
Entropy : 6.75
Noise : 60
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight blur, particularly in the background. Some of the foliage in the foreground appears to be slightly pixelated.
Unveiling the Secrets of the Jungle Temple
Three adventurers trek through a dense jungle, their path leading towards the enigmatic ruins of an ancient temple. The composition draws the viewer’s eye towards the temple, leaving them to wonder what mysteries lie within. The dramatic lighting and sense of anticipation create a mood of adventure and hope, promising a thrilling journey ahead.
Prompt
poses walking-away: Curious, excited ; A group of explorers with maps; wide shot; Adventure; Ancient ruins with a mysterious entrance; cinematic
Characteristic
Shot : Three people with backpacks walk in an ancient ruin. They walk away from the viewer toward a large stone structure. The setting is a sunny day with the lighting coming from the front and right of the image. There is a lot of greenery in the background of the image
Aesthetic Score : 0.6
Mood : adventurous, mysterious, hopeful
Quality
Entropy : 6.75
Noise : 90
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.80
Image errors : No apparent image errors
Lost in the Digital Realm: A Moment of Immersive Thought
A man, enveloped in a VR headset and headphones, stands in a dimly lit room, his eyes closed, lost in the virtual world. The blurred background emphasizes his isolation and the immersive nature of the experience, creating a sense of futuristic wonder and thoughtful contemplation.
Prompt
poses walking-away: Immersed, excited ; A gamer with a controller; close-up; Gaming; Virtual reality headset with a fantastical world displayed; cinematic
Characteristic
Shot : A young man wearing a VR headset and holding a controller, standing in a dimly lit, indoor space with a blurry background of people and screens, presumably an event or a gaming convention
Aesthetic Score : 0.7
Mood : futuristic, techy, immersive
Quality
Entropy : 6.88
Noise : 51
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are some artifacts and graininess in the image, particularly in the background. There is also some minor blurriness in the subject’s face.
A Tranquil Departure: Couple Walks Away on a Train Platform
A couple, hand in hand, walks away from the camera on a train platform, their figures silhouetted against the backdrop of bustling trains. The scene evokes a sense of tranquility and adventure, capturing the bittersweet moment of departure.
Prompt
poses walking-away: Emotional, bittersweet ; A family with luggage; long shot; Travel; Train station platform with a departing train in the distance; cinematic
Characteristic
Shot : A couple walks away from the camera, pulling suitcases on a train platform.
Aesthetic Score : 0.6
Mood : tranquil, hopeful, adventurous
Quality
Entropy : 6.82
Noise : 73
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : Slight blurriness in the background and edges, some graininess.
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 a 0.5, which falls within the “good” range. This indicates that the model was able to accurately capture the camera position described in the prompt.
- Shot Analysis: The model also scored a 0.5, indicating a “good” performance. This suggests that the model understood the scene described in the prompt and was able to create an image that reflected that understanding.
- Aesthetic Analysis: The model scored a 0.04, which is significantly lower than the “very good” range of -0.2 to 0.1. This suggests that the generated image did not match the expected aesthetic style as closely as it could have.
Overall, the model demonstrates a good understanding of camera position and shot composition, but needs improvement in capturing the desired aesthetic style.
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://www.freepik.com