AI Captures the Moment: A Look at Dramatic Poses in Generated Images with Imagen-v2
- 9 minutes read - 1823 wordsTable of Contents
Dramatic poses are a powerful tool in visual storytelling, conveying emotions and narratives through body language. In the realm of AI-generated images, capturing these poses effectively is a crucial step towards creating truly compelling and engaging visuals. This blog post explores the results of an experiment that tested an AI model’s ability to generate images with dramatic poses, analyzing its strengths and weaknesses in understanding scene composition, camera position, and aesthetic appeal. We’ll delve into specific examples, highlighting how the model captures the essence of adventure, heroism, and other themes through its portrayal of dramatic poses.
Created with: imagen-v2
Solitude on the Mountaintop: A Serene Escape Above the Clouds
A lone figure stands silhouetted against a breathtaking panorama of pink and blue skies, gazing out over a sea of clouds. The vastness of the landscape and the figure’s isolation evoke a sense of serenity and contemplation, highlighting the power of nature to inspire awe and introspection.
Prompt
poses looking-at-each-other: determined, awe-inspired ; A lone adventurer, standing on a mountain peak; wide shot; adventure; a vast, breathtaking landscape with clouds swirling below; cinematic
Characteristic
Shot : A lone hiker stands on a rocky mountain peak overlooking a sea of clouds with other mountain peaks in the distance.
Aesthetic Score : 0.8
Mood : serene, adventurous, contemplative
Quality
Entropy : 6.55
Noise : 110
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : No significant errors.
On the Brink of Battle: Soldiers Brace for Action
A close-up shot captures the intensity of two soldiers, their faces etched with determination, as they prepare for an impending conflict. The gritty atmosphere and dramatic lighting heighten the sense of tension and anticipation, leaving the viewer on the edge of their seat.
Prompt
poses looking-at-each-other: tense, hopeful ; Two soldiers, one injured, the other holding a shield; medium shot; heroism; a battlefield with smoke and fire in the background; cinematic
Characteristic
Shot : Two soldiers in wartime, one holding a wooden staff, the other holding a shield, both look determined and ready to fight. The background is blurry, suggesting a battlefield scene.
Aesthetic Score : 0.7
Mood : intense, serious, gritty
Quality
Entropy : 6.49
Noise : 100
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some slight noise and grain, which is likely intentional to create a vintage aesthetic. The lighting is uneven, leading to some areas of darkness.
Lost in the Digital Realm: Two Gamers Immersed in a World of Mystery
A captivating image of two young people, a boy and a girl, engrossed in a virtual experience. The dramatic blue lighting highlights their intense focus, creating a sense of mystery and intrigue. Are they playing a game, exploring a virtual world, or something more? This image captures the allure and intensity of the digital realm.
Prompt
poses looking-at-each-other: intense, focused ; Two gamers, heads bent over a screen; close-up; gaming; a dimly lit room with neon lights reflecting on their faces; cinematic
Characteristic
Shot : Two young adults wearing headsets, looking intently in the same direction, in a dimly lit room, lit by neon-like colors.
Aesthetic Score : 0.6
Mood : intense, focused, mysterious
Quality
Entropy : 6.26
Noise : 86
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : Some artifacts and noise are visible, particularly in the shadows.
A Moment of Suspense in a European Square
Three figures stand in a muted, melancholic scene, their expressions and postures hinting at an impending event. The soft lighting and the imposing archway create a sense of tension and anticipation, leaving the viewer wondering what lies ahead.
Prompt
poses looking-at-each-other: excited, curious ; A group of tourists, standing in front of a famous landmark; medium shot; tourism; a bustling city street with people and vehicles passing by; cinematic
Characteristic
Shot : Three people standing in front of the Brandenburg Gate in Berlin, Germany. The scene is set in a public square with a lot of people in the background.
Aesthetic Score : 0.6
Mood : melancholy, introspective, contemplative
Quality
Entropy : 6.68
Noise : 93
Prompt Clip Score : 0.21
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some artifacts in the background, and the color saturation is a bit too high.
Lost in the Landscape: A Moment of Tranquility on the Train
A young woman, lost in thought, gazes out the window of a moving train, her pensive expression mirroring the tranquil beauty of the passing green landscape. The intimate composition draws the viewer into her private world, inviting contemplation and a sense of wistful longing.
Prompt
poses looking-at-each-other: reflective, nostalgic ; Two friends, sitting on a train, looking out the window; medium shot; travel; a scenic landscape with rolling hills and fields; cinematic
Characteristic
Shot : A young woman sits on a train, looking out the window at a passing landscape of rolling green hills. A man sits behind her, partially obscured by the train seat.
Aesthetic Score : 0.7
Mood : melancholy, contemplative, wistful
Quality
Entropy : 6.41
Noise : 102
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts and graininess present in the image, particularly in the background. These are likely due to the film stock used to capture the image.
Campfire Nights: Tranquility Under the Stars
A cozy scene of four friends gathered around a crackling campfire, bathed in the warm glow of the flames and the twinkling light of a star-filled sky. The image evokes a sense of peace, nostalgia, and the simple joys of shared moments under the open sky.
Prompt
poses looking-at-each-other: warm, intimate ; A group of friends, huddled together around a campfire; close-up; groups; a dark forest with stars twinkling in the sky; cinematic
Characteristic
Shot : Four people are sitting around a campfire under a starry night sky.
Aesthetic Score : 0.7
Mood : cozy, warm, nostalgic
Quality
Entropy : 6.46
Noise : 111
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image appears slightly overexposed, which results in blown out highlights, particularly in the night sky. Some noise is visible, which might be a result of high ISO.
Solitude at Sunset: A Man Contemplates the Vastness of the Ocean
A solitary figure stands on a sandy beach, bathed in the golden hues of a setting sun. The crashing waves and the breathtaking sky create a sense of awe and tranquility, inviting contemplation and introspection. This image captures the beauty of nature and the power of solitude.
Prompt
poses looking-at-each-other: melancholy, contemplative ; A lone figure, standing on a deserted beach; wide shot; adventure; a vast ocean with crashing waves and a setting sun; cinematic
Characteristic
Shot : A man stands alone on a beach, facing away from the camera, looking out at the ocean. The sun is setting in the background, casting a warm glow on the scene. There are waves crashing in the background.
Aesthetic Score : 0.7
Mood : reflective, tranquil, peaceful
Quality
Entropy : 6.86
Noise : 97
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors in the image
Lost in the Cosmic Tapestry: Astronauts Adrift Amidst a Mystical Planet
Two astronauts, silhouetted against the backdrop of a distant, ethereal planet, float weightlessly in the vast expanse of space. The image evokes a sense of awe and wonder, highlighting the boundless nature of the universe and the fragility of human existence within it.
Prompt
poses looking-at-each-other: awe-inspired, hopeful ; Two astronauts, floating in space; medium shot; heroism; a view of Earth from space with stars and galaxies in the background; cinematic
Characteristic
Shot : Two astronauts floating in space with a planet in the background.
Aesthetic Score : 0.6
Mood : lonely, serene, cosmic
Quality
Entropy : 5.76
Noise : 112
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.70
Image errors : The stars are a bit too uniform and repetitive, and there’s a slight blur in some areas, especially around the astronauts, which might be due to over-sharpening or motion blur.
Lost in the Jungle: Explorers Face the Unknown
Four explorers, clad in rugged attire, stand amidst the dense foliage of a mysterious jungle. Their expressions are a mix of determination and apprehension, hinting at the challenges that lie ahead. The dramatic lighting casts long shadows, adding to the sense of suspense and mystery. What secrets await them in the heart of this untamed wilderness?
Prompt
poses looking-at-each-other: curious, adventurous ; A group of explorers, standing in a jungle clearing; medium shot; adventure; lush greenery with sunlight filtering through the leaves; cinematic
Characteristic
Shot : Four people are standing in a jungle, looking somewhat concerned. They are wearing explorer-like clothes.
Aesthetic Score : 0.6
Mood : suspenseful, mysterious, adventurous
Quality
Entropy : 6.81
Noise : 104
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : There is some noise in the image and the background is a little bit blurry.
Love Story in the Golden Hour
A couple embraces the romantic glow of a city sunset, their closeness and the warm hues painting a picture of intimacy and hope.
Prompt
poses looking-at-each-other: romantic, intimate ; Two lovers, standing on a bridge overlooking a city; medium shot; tourism; a cityscape with twinkling lights and a river flowing below; cinematic
Characteristic
Shot : A couple stands close to each other in front of a cityscape at dusk.
Aesthetic Score : 0.7
Mood : romantic, intimate, hopeful
Quality
Entropy : 6.38
Noise : 116
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : None
Conclusion
The results show that the generative AI model performed well in understanding the scene and camera position, 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 0.53, which is considered good. This indicates the model successfully captured the intended shot type and composition.
- Aesthetic Analysis: The model scored 0.02, which is considered very good. This means the generated image’s aesthetic closely matched the expected aesthetic.
Overall, the model demonstrates a good understanding of the scene and shot type, but needs improvement in accurately capturing the desired camera position. The aesthetic analysis suggests the model is capable of producing visually appealing images.
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://deepmind.google/technologies/imagen-2/