AI Captures the Scene, But Misses the Mood with Freepik
- 9 minutes read - 1709 wordsTable of Contents
In the realm of artificial intelligence, generative models are rapidly advancing, pushing the boundaries of what machines can create. One area where these models are showing promise is in image generation. By analyzing text prompts, these models can generate images that correspond to the described scenes. However, while they may excel in capturing the basic elements of a scene, they often struggle to replicate the desired aesthetic style. This blog post explores the results of a generative AI model tasked with creating images based on specific scene descriptions, highlighting its strengths and weaknesses in capturing the intended mood and aesthetic.
Created with: freepik
A Handshake Among the Stars: A Symbol of Hope in the Vastness of Space
Two astronauts, silhouetted against a breathtaking starry sky, extend a hand of friendship. This powerful image evokes a sense of wonder and possibility, suggesting the potential for collaboration and peace in the exploration of the cosmos.
Prompt
poses holding-hands: Hopeful, determined, camaraderie ; Two astronauts; wide shot; heroism; the vastness of space with stars and planets in the background; cinematic
Characteristic
Shot : Two astronauts in space suits are shaking hands in front of a starry sky background.
Aesthetic Score : 0.7
Mood : hopeful, futuristic, unity
Quality
Entropy : 6.77
Noise : 74
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.90
Image errors : Slight blurring on the astronauts’ helmets and some minor pixelation in the background.
Lost in the Jungle’s Embrace: A Serene Adventure Awaits
Four explorers stand on a sun-dappled trail, the lush jungle whispering secrets around them. A sense of mystery and wonder fills the air, inviting you to follow their path into the unknown. This breathtaking scene captures the essence of adventure, serenity, and hope.
Prompt
poses holding-hands: Excited, adventurous, trusting ; A group of explorers; medium shot; adventure; a dense jungle with sunlight filtering through the canopy; cinematic
Characteristic
Shot : Four people are walking on a path in a lush green jungle with sunlight breaking through the canopy
Aesthetic Score : 0.7
Mood : adventurous, hopeful, inspiring
Quality
Entropy : 6.77
Noise : 80
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors
Focused on the Task at Hand
Two young men, bathed in warm light, are deeply engrossed in their work at a desk filled with computer monitors. Their serious expressions and the dramatic lighting create a sense of intense focus and professionalism.
Prompt
poses holding-hands: Focused, competitive, collaborative ; Two gamers; close-up; gaming; a brightly lit gaming setup with glowing screens and controllers; cinematic
Characteristic
Shot : Two young men are sitting at a desk in front of multiple computer screens, they are wearing headsets and looking at each other, one of the men is using a mixer, the scene is dimly lit with warm light coming from the desk lamp
Aesthetic Score : 0.7
Mood : focused, intense, serious
Quality
Entropy : 6.78
Noise : 57
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly blurry, especially in the background.
Love in the City of Light: A Tale of Two Hearts
In the heart of Paris, with the iconic Eiffel Tower standing tall in the background, two hands intertwine in a romantic and hopeful embrace. The blurred cityscape adds a sense of intimacy and privacy, making this a perfect depiction of love in the City of Light.
Prompt
poses holding-hands: Romantic, happy, adventurous ; A couple; medium shot; tourism; a picturesque cityscape with iconic landmarks in the background; cinematic
Characteristic
Shot : A couple’s hands holding each other in front of the Eiffel Tower at sunset.
Aesthetic Score : 0.7
Mood : romantic, intimate, hopeful
Quality
Entropy : 6.62
Noise : 34
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some noise and graininess in the image, particularly in the background.
A Serene Journey Through Majestic Mountains
Three figures walk along a paved road, their journey dwarfed by the towering mountains in the background. The scene evokes a sense of peace, adventure, and the vastness of nature.
Prompt
poses holding-hands: Joyful, connected, adventurous ; A family; long shot; travel; a scenic mountain range with a winding road leading to the peak; cinematic
Characteristic
Shot : Three people, two women and one man, are walking down a road through a mountain pass. The mountains are covered in green grass and trees, and there is a blue sky in the background. The people are holding hands and are walking in a line.
Aesthetic Score : 0.7
Mood : serene, adventurous, happy
Quality
Entropy : 6.52
Noise : 61
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no noticeable artifacts or errors in the image.
Hands United: A Celebration of Hope and Togetherness
A powerful image captures the spirit of unity as a group of women stand together, their hands stacked high, symbolizing strength and connection. The low angle and blurred background create a sense of intimacy, drawing the viewer’s focus to the powerful message of hope and togetherness.
Prompt
poses holding-hands: Happy, celebratory, connected ; A group of friends; medium shot; groups; a vibrant festival with colorful decorations and music; cinematic
Characteristic
Shot : A group of people, possibly friends, are standing in a crowded street, with colourful string lights in the background. They are holding their hands together in a circle. The focus is on the hands, which are in the foreground.
Aesthetic Score : 0.7
Mood : joyful, hopeful, unity
Quality
Entropy : 6.80
Noise : 55
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.30
Image errors : There are some minor artifacts and blurriness around the edges of the hands, particularly on the fingertips.
Hands Framing Tranquility: A Mountain Valley Beckons
A serene mountain valley unfolds before you, its muted blues and grays painted by a cloudy sky. The winding road disappearing into the distance invites contemplation, while the clasped hands framing the view add a sense of intimacy and connection to this tranquil scene.
Prompt
poses holding-hands: Determined, courageous, triumphant ; A lone hiker; close-up; heroism; a breathtaking mountain vista with clouds swirling below; cinematic
Characteristic
Shot : A person’s hands are clasped together in front of a scenic mountain valley with a cloudy sky.
Aesthetic Score : 0.6
Mood : serene, contemplative, adventurous
Quality
Entropy : 6.51
Noise : 42
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible image errors
Innocence and Mystery on the Playground
Two young girls, hand in hand, walk away from the camera on a sunny playground. Their back-to-back posture adds a touch of mystery to their carefree joy, leaving you wondering what adventures await them. The sandbox in the foreground and swings in the background complete the picture of childhood bliss.
Prompt
poses holding-hands: Playful, innocent, carefree ; Two children; close-up; adventure; a playground with swings, slides, and a sandbox; cinematic
Characteristic
Shot : Two young girls in dresses are holding hands and walking away from the camera on a playground. The background is blurry and out of focus.
Aesthetic Score : 0.7
Mood : playful, innocent, friendship
Quality
Entropy : 6.58
Noise : 67
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
Hands United: A Moment of Hope and Togetherness
A powerful image capturing a group of people standing in a circle, hands clasped together in the foreground. The blurred background suggests a stage or performance setting, adding to the sense of unity and shared purpose. The mood is hopeful, radiating togetherness and a shared commitment.
Prompt
poses holding-hands: Passionate, connected, expressive ; A group of musicians; medium shot; groups; a dimly lit stage with spotlights shining on them; cinematic
Characteristic
Shot : A group of people are standing in a circle, holding hands, on a stage. The stage is lit by spotlights.
Aesthetic Score : 0.6
Mood : hopeful, togetherness, unity
Quality
Entropy : 6.70
Noise : 47
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors
Silhouettes of Love Against a Desert Sunset
A couple strolls hand-in-hand across a breathtaking desert landscape, their silhouettes framed against a vibrant sunset. The backlighting and vastness of the scene create a sense of mystery and romance, capturing the essence of adventure and serenity.
Prompt
poses holding-hands: Romantic, adventurous, hopeful ; A couple; long shot; travel; a vast desert landscape with a setting sun in the distance; cinematic
Characteristic
Shot : A couple walks hand-in-hand across a desert landscape at sunset. The warm light casts long shadows behind them, and the vast expanse of sand dunes creates a sense of isolation and wonder.
Aesthetic Score : 0.7
Mood : romantic, hopeful, serene
Quality
Entropy : 6.77
Noise : 46
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, leading to a lack of detail in the sand dunes.
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 0.5, which is considered good. This means the model was able to accurately capture the camera position described in the prompt.
- Shot Analysis: The model scored 0.68, also considered good. This indicates the model understood the scene described in the prompt and created an image that reflects that understanding.
- Aesthetic Analysis: The model scored 0.08, which is not very good. This suggests that the generated image did not match the expected aesthetic style described in the prompt.
Overall, the model demonstrates a good understanding of camera position and scene 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