AI Captures the Moment: A Look at Generative AI's Strengths and Weaknesses in Posing with Freepik
- 9 minutes read - 1758 wordsTable of Contents
Generative AI is revolutionizing the way we create images, offering a powerful tool for artists and designers. One fascinating aspect of this technology is its ability to generate images with specific poses. This blog post explores the capabilities of generative AI in capturing dramatic poses, analyzing its performance in understanding camera position, shot composition, and aesthetic. We’ll examine the results of a test using various prompts, highlighting the model’s strengths in capturing the desired aesthetic while revealing its limitations in accurately replicating camera position and shot composition.
Created with: freepik
A Solitary Figure Contemplates the Vastness
A lone traveler stands on a mountain peak, dwarfed by the sprawling misty valley and distant peaks. Dramatic clouds fill the sky, creating a sense of tranquility and adventure. This breathtaking scene evokes a feeling of contemplation and the vastness of the world.
Prompt
poses thoughtful-pose: determined, contemplative ; Lone figure standing on a mountain peak; wide shot; heroism; dramatic sky with clouds; cinematic
Characteristic
Shot : A lone figure stands on a mountaintop, looking out at a vast range of mountains in the distance. The sky is filled with dramatic clouds, and the sun is setting, casting a warm glow over the landscape.
Aesthetic Score : 0.8
Mood : serene, contemplative, majestic
Quality
Entropy : 6.70
Noise : 53
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors
Lost in the Jungle: A Man’s Quest for Ancient Secrets
A solitary figure stands amidst the lush greenery of a jungle, his gaze fixed on a weathered map. Behind him, the remnants of an ancient civilization rise from the undergrowth, hinting at a forgotten past. The air is thick with mystery and adventure, as the man contemplates the secrets that lie hidden within the ruins.
Prompt
poses thoughtful-pose: curious, adventurous ; Explorer looking at a map, surrounded by ancient ruins; medium shot; adventure; jungle foliage; cinematic
Characteristic
Shot : A man is sitting in front of an old ruin in a jungle. He’s looking into the distance and holding a map.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, pensive
Quality
Entropy : 6.91
Noise : 72
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No notable errors or artifacts.
Lost in the Glow: A Gamer’s Intense Focus in a Dimly Lit World
A young man, shrouded in blue, is completely absorbed in his game. The only light illuminating the scene comes from the screen and keyboard, creating a dramatic and futuristic atmosphere. His intense focus speaks volumes about the immersive power of gaming.
Prompt
poses thoughtful-pose: intense, focused ; Gamer intensely focused on a screen, hands on a controller; close-up; gaming; neon lights and gaming peripherals; cinematic
Characteristic
Shot : A young man wearing headphones is sitting at a desk in a dimly lit room, focused on gaming on his computer.
Aesthetic Score : 0.7
Mood : intense, focused, gamer
Quality
Entropy : 6.60
Noise : 49
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors.
Lost in the City Lights: A Moment of Melancholy
A young woman stands alone on a bridge, bathed in the soft glow of city lights. Her contemplative pose and the melancholic mood evoke a sense of loneliness and introspection, capturing the quiet beauty of urban solitude.
Prompt
poses thoughtful-pose: awe-struck, contemplative ; Tourist gazing at a breathtaking cityscape; medium shot; tourism; bustling city streets; cinematic
Characteristic
Shot : A young woman standing on a bridge at night, looking out at the city lights. The city is blurred in the background.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, lonely
Quality
Entropy : 6.68
Noise : 48
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight chromatic aberration, especially around the edges of the woman’s hair.
Silhouetted Against the Sunset: A Hiker’s Moment of Contemplation
A lone hiker finds solace on a cliff edge, bathed in the warm glow of a setting sun. The vast ocean stretches before them, creating a serene and contemplative atmosphere. The hiker’s silhouette against the sunset highlights their smallness in the grand landscape, adding a touch of adventure and dramatic effect to the scene.
Prompt
poses thoughtful-pose: relaxed, introspective ; Backpackers sitting on a cliff overlooking a vast ocean; wide shot; travel; sunset sky; cinematic
Characteristic
Shot : A person sits on a cliff overlooking a vast ocean, the sun setting in the distance, casting a warm glow on the landscape.
Aesthetic Score : 0.8
Mood : serene, peaceful, contemplative
Quality
Entropy : 6.70
Noise : 76
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no significant artifacts or errors in the image.
Campfire Tales Under a Starry Sky
A group of friends gather around a crackling campfire, sharing stories and laughter under a breathtaking night sky. The Milky Way stretches across the heavens, casting a magical glow on their faces. This cozy scene evokes a sense of adventure, warmth, and companionship.
Prompt
poses thoughtful-pose: intimate, nostalgic ; Group of friends huddled around a campfire, sharing stories; medium shot; groups; starry night sky; cinematic
Characteristic
Shot : A group of young adults are sitting around a campfire in a forest at night. The night sky is visible above, with stars and the Milky Way.
Aesthetic Score : 0.7
Mood : cozy, warm, intimate
Quality
Entropy : 6.27
Noise : 59
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.30
Image errors : Some parts of the image are slightly blurry. The fire looks a bit artificial. The background is a bit too smooth, giving a slight CGI feel.
Solitude in the City Lights
A lone figure contemplates the sprawling cityscape at night, the reflection of the city lights creating a serene and melancholic atmosphere. The dramatic contrast between the individual and the vastness of the urban landscape evokes a sense of quiet contemplation.
Prompt
poses thoughtful-pose: reflective, hopeful ; A lone figure standing on a bridge, looking out at the city lights; medium shot; heroism; cityscape at night; cinematic
Characteristic
Shot : A lone figure in a brown coat stands on a pier overlooking a city skyline at night.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, urban
Quality
Entropy : 6.65
Noise : 59
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.70
Image errors : Slight blurriness around the edges and some artificial-looking reflections in the water.
Lost in the Green: A Mysterious Journey Begins
Four figures, cloaked in green, stand shrouded in the dappled light of a forest. Their gaze is fixed on something unseen, hinting at a journey filled with adventure and suspense. The play of light and shadow adds a layer of mystery, drawing the viewer into their enigmatic world.
Prompt
poses thoughtful-pose: determined, cautious ; A group of adventurers navigating a dense forest; wide shot; adventure; lush green foliage; cinematic
Characteristic
Shot : A group of four people, dressed in safari attire, walk through a dense forest. The lighting is soft and diffused, suggesting a cloudy or overcast day. The foliage is lush and green, and the trees are tall and thick.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, contemplative
Quality
Entropy : 6.84
Noise : 78
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly soft, and there is a minor amount of noise in the darker areas. There is also some blurring around the edges of the subjects.
Gamer’s Triumphant Moment Captured in a Burst of Joy
This image captures the pure joy of victory as a young gamer celebrates a win with a fist pump and a beaming smile. The vibrant lighting and focused expression highlight the intensity and excitement of the moment.
Prompt
poses thoughtful-pose: triumphant, excited ; A gamer celebrating a victory, fist raised in the air; close-up; gaming; vibrant gaming setup; cinematic
Characteristic
Shot : A young man is sitting at a computer desk, wearing headphones, looking excited and raising his fist. The scene is set in a gaming room, with multiple computer monitors, a keyboard, and a mouse visible. The lighting is warm and inviting, with a mix of soft and bright lights.
Aesthetic Score : 0.6
Mood : excited, energetic, focused
Quality
Entropy : 6.74
Noise : 48
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible errors in the image.
Sunset Serenity on the Beach
Three friends stand together, bathed in the golden light of a breathtaking sunset, as they gaze out at the tranquil ocean. The scene evokes a sense of peace and contemplation, capturing the beauty of a moment shared under the warm glow of the setting sun.
Prompt
poses thoughtful-pose: peaceful, hopeful ; A family standing on a beach, watching the sunrise; wide shot; tourism; golden sunrise over the ocean; cinematic
Characteristic
Shot : Three people standing on a beach, looking out at the ocean during a sunset.
Aesthetic Score : 0.7
Mood : calm, serene, reflective
Quality
Entropy : 6.76
Noise : 50
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly blurry, which is likely due to the movement of the subjects.
Conclusion
The results show that the generative AI model performed well in understanding the camera position and shot composition, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.4, which is considered okay. This means the generated image’s camera position was somewhat different from what was requested in the prompt.
- Shot Analysis: The model scored 0.49, which is also considered okay. This indicates that the generated image’s shot composition was somewhat different from what was requested in the prompt.
- Aesthetic Analysis: The model scored 0.01, which is considered very good. This means the generated image’s aesthetic was very close to what was expected based on the prompt.
Overall, the model seems to be better at understanding the aesthetic aspects of the prompt than the camera position and shot composition.
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