AI's Artistic Journey: Capturing Poses, But Missing the Mood with Dall-e-3
- 10 minutes read - 2024 words
Table of Contents
In the realm of visual storytelling, capturing the essence of a scene goes beyond simply placing objects and characters in the right positions. It’s about conveying emotions, moods, and a sense of place through the interplay of light, color, and composition. This is where the art of posing comes in. Dramatic poses, whether a lone figure silhouetted against a setting sun or a group of adventurers huddled around a campfire, can evoke powerful emotions and draw the viewer into the narrative. This blog post delves into an experiment using a generative AI model to create images based on specific poses and scene descriptions, exploring the model’s ability to understand and execute camera positions, shot composition, and most importantly, the desired aesthetic.
Created with: dall-e-3
Silhouettes of Hope: A Journey Begins at Sunset
Two figures stand on a rocky outcrop, their silhouettes stark against the fiery sunset. The vast, desert landscape stretches before them, promising adventure and a hopeful future. The dramatic lighting and the figures’ enigmatic forms create a sense of mystery and intrigue, hinting at the epic journey that lies ahead.
Prompt
poses leaning: epic, hopeful ; A lone figure, silhouetted against a setting sun; wide shot; heroism; a vast, desolate landscape; cinematic
Characteristic
Shot : Two figures silhouetted against a setting sun, standing on a rocky ridge overlooking a vast, hazy landscape.
Aesthetic Score : 0.7
Mood : epic, hopeful, dramatic
Quality
Entropy : 6.31
Noise : 96
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slight overexposure in the sky and some minor noise in the shadows. The details in the landscape are somewhat blurry and lacking in clarity.
Shadows and Secrets: A Group of Adventurers Faces the Unknown
A group of adventurers, illuminated by flickering torches, huddle together in a dark cave, their faces etched with apprehension and excitement. The light and shadow play creates a sense of mystery and intrigue, drawing the viewer’s eye to the center of the scene where the adventurers are gathered, anticipating what lies ahead in the darkness.
Prompt
poses leaning: suspenseful, adventurous ; A group of adventurers, their faces illuminated by flickering torchlight; medium shot; adventure; a dark, mysterious cave; cinematic
Characteristic
Shot : A group of people are huddled together in a dark cave, holding lanterns and torches for light. They appear to be looking at something in the distance, with expressions of fear and caution.
Aesthetic Score : 0.7
Mood : intense, suspenseful, mysterious
Quality
Entropy : 6.77
Noise : 92
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image is overall well-rendered, but some minor artifacts are present in the background and on the character’s faces. The lighting is slightly uneven.
Fingers Fly, Danger Lurks: A Close-Up on the Edge of Action
A tense, close-up shot captures the intensity of a gamer’s focus as they navigate a virtual battlefield. The blurred figure in the background, armed with a rifle, adds a layer of suspense to the scene, highlighting the high stakes of the game.
Prompt
poses leaning: intense, focused ; A gamer’s hands, fingers flying across a keyboard; close-up; gaming; a brightly lit gaming setup; cinematic
Characteristic
Shot : A close-up of a person’s hands typing on a keyboard. In the background, another person is holding a gun. The scene is lit by an orange light.
Aesthetic Score : 0.6
Mood : intense, dark, action
Quality
Entropy : 6.34
Noise : 83
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has a slight blur and some noise, particularly in the background. The colors are slightly oversaturated.
A Moment of Dreamy Intimacy: Couple Gazes at City Skyline
In this romantic and contemplative scene, a couple shares a quiet moment together as they look out at a city skyline at night. The man leans on a railing, while the woman rests her head on his shoulder, both lost in the dreamy atmosphere created by the warm lighting and soft focus. The city lights blur in the background, adding to the sense of wonder and intimacy.
Prompt
poses leaning: romantic, awe-inspiring ; A couple leaning on a railing, gazing out at a breathtaking cityscape; medium shot; tourism; a vibrant, bustling city; cinematic
Characteristic
Shot : A young couple is looking out over a city skyline at night. They are standing on a balcony with a railing.
Aesthetic Score : 0.8
Mood : romantic, dreamy, urban
Quality
Entropy : 6.71
Noise : 102
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.70
Image errors : The lighting in the image is slightly artificial. The background city is not particularly clear, with many out of focus areas.
A Moment of Contemplation on the Road Less Traveled
A lone woman sits on a wooden post, her gaze fixed on a winding dirt road that disappears into a valley. Two large backpacks rest on her lap, hinting at a journey of exploration. The vastness of the mountainous landscape behind her creates a sense of awe and wonder, inviting viewers to contemplate the possibilities that lie ahead.
Prompt
poses leaning: reflective, adventurous ; A backpacker, leaning against a weathered signpost, looking out at a winding mountain road; medium shot; travel; a scenic mountain range; cinematic
Characteristic
Shot : A woman is sitting on a wooden post with two large backpacks, overlooking a winding mountain road and a valley with a river running through it. The scene is set against the backdrop of a mountain range, and the sky is a clear blue with some clouds.
Aesthetic Score : 0.7
Mood : serene, adventurous, contemplative
Quality
Entropy : 6.66
Noise : 107
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some slight artifacts, particularly in the shadows and highlights. These are mostly cosmetic, however, and do not detract significantly from the overall image.
Joyful Laughter Echoes Through the Cobblestone Streets
A vibrant group of young adults share a moment of pure joy, their laughter echoing through the charming cobblestone streets. The close-up shot captures their infectious energy and creates a sense of intimacy, while the blurred background adds a touch of dreamy ambiance.
Prompt
poses leaning: joyful, carefree ; A group of friends, laughing and leaning on each other, as they walk down a cobblestone street; wide shot; groups; a charming, historic town; cinematic
Characteristic
Shot : A group of friends are laughing and smiling, looking directly at the camera in a narrow street. The scene is full of energy and life, with the cobblestone street and the old buildings providing a backdrop.
Aesthetic Score : 0.7
Mood : joyful, exuberant, lively
Quality
Entropy : 6.71
Noise : 104
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : No visible errors or artifacts. The image is sharp and well-exposed.
Defiance in the Face of the Storm
A solitary figure stands on a cliff edge, arms outstretched, facing a raging storm at sea. Silhouetted against the dramatic sky and crashing waves, the image evokes a sense of power and vulnerability, capturing the raw intensity of nature’s fury.
Prompt
poses leaning: powerful, defiant ; A lone figure, standing on a cliff edge, arms outstretched, leaning into the wind; wide shot; heroism; a dramatic, stormy sea; cinematic
Characteristic
Shot : A lone figure stands on a cliff overlooking a stormy sea, arms outstretched as if embracing the wind and the waves. The silhouette of the figure is stark against the gray sky and the turbulent water.
Aesthetic Score : 0.7
Mood : dramatic, epic, lonely
Quality
Entropy : 6.76
Noise : 110
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts, especially in the water and sky. The figure’s face and clothing are slightly blurry.
Mysterious Encampment: Shadows Dance in the Jungle Firelight
A group of adventurers huddle around a crackling campfire, their faces illuminated by the dancing flames. The jungle surrounds them, shrouded in mystery and shadows. This scene evokes a sense of adventure, warmth, and the unknown.
Prompt
poses leaning: intimate, suspenseful ; A group of explorers, huddled around a campfire, sharing stories; medium shot; adventure; a dense, mysterious forest; cinematic
Characteristic
Shot : A group of people are gathered around a campfire in a dark, lush forest setting. The light from the fire illuminates their faces and the surrounding foliage.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, tense
Quality
Entropy : 6.45
Noise : 102
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.60
Image errors : Some of the foliage in the background appears blurry and unrealistic.
Immersed in the Digital Realm
A woman, bathed in vibrant blue and red light, is completely engrossed in her digital world. Her intense gaze and the close-up framing capture the focused energy and immersion of her experience.
Prompt
poses leaning: intense, focused ; A gamer’s face, illuminated by the glow of a monitor, eyes wide with excitement; close-up; gaming; a dimly lit room; cinematic
Characteristic
Shot : A woman wearing headphones is focused on the screen in front of her, illuminated by a blue and red light source.
Aesthetic Score : 0.7
Mood : intense, focused, futuristic
Quality
Entropy : 6.54
Noise : 82
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image shows some artifacts in the hair and the lighting on the face, especially around the eyes.
Sunset Smiles: A Family Captures Golden Memories
A heartwarming scene unfolds as a family of four stands on a beach, bathed in the warm glow of a setting sun. Their eyes are fixed on the camera’s LCD screen, reflecting the vibrant hues of the sunset. The moment captures the joy and nostalgia of a shared experience, leaving a lasting impression of happiness.
Prompt
poses leaning: peaceful, heartwarming ; A family, leaning on each other, watching a sunset over a vast ocean; wide shot; travel; a serene, sandy beach; cinematic
Characteristic
Shot : A family of four is standing on a beach, watching a sunset through a camera lens. The camera is mounted on a tripod.
Aesthetic Score : 0.6
Mood : peaceful, warm, sentimental
Quality
Entropy : 6.69
Noise : 95
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has a slight amount of noise in the shadows. This is likely due to the high ISO setting used to capture the image. The image also has a few minor artifacts, particularly in the background.
Conclusion
The results show that the generative AI model performed well in understanding and executing camera positions and shot composition, but struggled with achieving the desired aesthetic. Here’s a breakdown:
- Camera Position: The model scored a 0.48, which falls slightly below the “good” range of 0.5 to 0.75. This suggests that while the model generally understood the camera positions described in the prompt, there were some discrepancies between the intended and actual camera angles in the generated image.
- Shot Analysis: The model scored a 0.57, placing it within the “good” range. This indicates that the model successfully captured the overall shot composition described in the prompt, demonstrating a good understanding of the scene’s layout and framing.
- Aesthetic Analysis: The model scored a 0.03, which is significantly lower than the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated considerably from the intended aesthetic described in the prompt. The model may have struggled to capture the desired mood, style, or visual elements.
Overall, the model shows promise in understanding and executing camera positions and shot composition, but needs improvement in achieving the desired aesthetic.
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://openai.com/index/dall-e-3/