AI's Artistic Struggle: Capturing the Essence of Dramatic Poses with Midjourney
- 9 minutes read - 1787 wordsTable of Contents
Dramatic poses are a powerful tool in visual storytelling, conveying emotions, actions, and the essence of a scene. They are often used in photography, film, and art to create a sense of drama, heroism, or adventure. But can AI truly capture the essence of these poses? In this blog post, we explore the results of an experiment where an AI model was tasked with generating images based on descriptions of dramatic poses. The results reveal both the strengths and limitations of AI in artistic expression, highlighting its ability to capture aesthetics while struggling with scene understanding.
Created with: midjourney
A Solitary Figure Bathed in Lightning
A lone figure stands on a windswept cliff, silhouetted against a stormy sea. A dramatic lightning bolt illuminates the sky, emphasizing the figure’s isolation and the ominous mood of the scene.
Prompt
silhouette silhouette: epic, determined ; Lone figure standing on a clifftop, overlooking a vast, stormy sea; wide shot; heroism; dramatic sky with lightning; cinematic
Characteristic
Shot : A lone figure stands on a cliff overlooking a stormy sea with lightning striking in the distance. The sky is dark and dramatic, and the water is choppy.
Aesthetic Score : 0.7
Mood : dramatic, foreboding, intense
Quality
Entropy : 6.16
Noise : 108
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.70
Image errors : The lightning bolt appears somewhat artificial, with a lack of realistic branching and glow.
Silhouettes of Hope: A Journey into the Sunset
A group of figures walk towards a breathtaking sunset, their silhouettes painted against the fiery sky. The scene evokes a sense of tranquility, hope, and adventure, leaving a lasting impression of a journey into the unknown.
Prompt
silhouette silhouette: hopeful, adventurous ; A group of adventurers silhouetted against the setting sun, walking towards a distant mountain range; medium shot; adventure; desert landscape; cinematic
Characteristic
Shot : A group of people walking away from the camera towards the sun setting over a mountain range. The scene is a wide shot, so the people are small figures against the large backdrop of the mountains and sky.
Aesthetic Score : 0.7
Mood : peaceful, hopeful, adventurous
Quality
Entropy : 6.18
Noise : 49
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image
Lost in the Neon Glow: A Gamer’s Intense Focus
A close-up shot captures the hands of a gamer gripping a controller, their face illuminated by the vibrant, blurred neon lights of a futuristic cityscape. The scene exudes an intense, focused energy, drawing the viewer into the heart of the action.
Prompt
silhouette silhouette: intense, focused ; A gamer’s hands silhouetted against a glowing computer screen, holding a controller; close-up; gaming; neon lights and digital interfaces; cinematic
Characteristic
Shot : A person is playing a video game with a controller, the background is a blurred screen with blue and purple lights.
Aesthetic Score : 0.6
Mood : intense, focused, gaming
Quality
Entropy : 6.37
Noise : 78
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible errors in the image.
Silhouettes of Love Against the Eiffel Tower
A romantic and dreamy scene of a couple silhouetted against the iconic Eiffel Tower at night. The city lights twinkle in the background, creating a sense of nostalgia and mystery. This image captures the essence of love and adventure in the City of Lights.
Prompt
silhouette silhouette: romantic, nostalgic ; A couple holding hands, silhouetted against the iconic Eiffel Tower; medium shot; tourism; Parisian cityscape at night; cinematic
Characteristic
Shot : A silhouetted couple stands in front of the Eiffel Tower at night, with the city lights twinkling in the background.
Aesthetic Score : 0.7
Mood : romantic, nostalgic, serene
Quality
Entropy : 4.59
Noise : 93
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Silhouettes of Hope in the Desert Sunset
A solitary figure walks towards the setting sun in a dusty desert landscape, their silhouette casting a sense of mystery and intrigue. The scene evokes a melancholic yet hopeful mood, with a touch of serenity. The dramatic effect of the silhouette against the vibrant sunset creates a captivating image.
Prompt
silhouette silhouette: lonely, contemplative ; A lone traveler walking down a dusty road, silhouetted against the rising sun; long shot; travel; vast, open desert landscape; cinematic
Characteristic
Shot : A lone figure walks down a dusty road towards a setting sun in a vast desert landscape. The sun is partially obscured by clouds, creating a warm, golden glow.
Aesthetic Score : 0.8
Mood : tranquil, contemplative, hopeful
Quality
Entropy : 6.55
Noise : 95
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable artifacts or errors.
Silhouettes of Celebration: A Toast to Mystery
Capture the festive spirit of a dimly lit bar or club, where silhouettes of people toasting with wine glasses create a sense of mystery and intimacy. The blurred lights in the background add to the dramatic effect, making this image perfect for evoking a celebratory mood.
Prompt
silhouette silhouette: joyful, celebratory ; A group of friends raising their glasses in a toast, silhouetted against a brightly lit bar; medium shot; groups; vibrant nightlife scene; cinematic
Characteristic
Shot : Silhouettes of people toasting with glasses of wine in a dimly lit bar or club. Colorful lights in the background.
Aesthetic Score : 0.6
Mood : festive, celebratory, mysterious
Quality
Entropy : 5.41
Noise : 99
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no noticeable artifacts or errors in the image.
Leap of Faith: Silhouette of a Daredevil at Sunset
A dramatic silhouette of a man leaping from a towering building against a vibrant sunset cityscape. The image evokes a sense of danger, suspense, and adventure, leaving the viewer wondering about the man’s fate and the motivations behind his daring leap.
Prompt
silhouette silhouette: powerful, heroic ; A superhero leaping from a tall building, silhouetted against the city skyline; wide shot; heroism; cityscape with skyscrapers; cinematic
Characteristic
Shot : Silhouette of a person jumping from a tall building in a city, overlooking a vast cityscape with a hazy sunset in the background.
Aesthetic Score : 0.6
Mood : dramatic, suspenseful, risky
Quality
Entropy : 5.16
Noise : 81
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.50
Image errors : The image seems to have some blurry edges and the resolution is not very high. The cityscape lacks detail.
Silhouettes of Mystery: Soldiers Emerge into the Unknown
A haunting image of four soldiers in silhouette, walking out of a cave into a dense jungle. The scene is bathed in an ethereal, hazy light, creating a sense of mystery and suspense. The soldiers’ journey into the unknown evokes a feeling of danger and uncertainty, leaving the viewer to wonder what awaits them.
Prompt
silhouette silhouette: suspenseful, adventurous ; A group of explorers silhouetted against the entrance to a dark, mysterious cave; medium shot; adventure; dense jungle foliage; cinematic
Characteristic
Shot : Four figures, silhouetted, walk away from the camera towards a light at the end of a tunnel. The tunnel is a cave with a rocky ceiling and lush foliage framing the entrance.
Aesthetic Score : 0.7
Mood : mysterious, adventurous, hopeful
Quality
Entropy : 5.64
Noise : 117
Prompt Clip Score : 0.33
AI Evaluation
Likelihood of AI : 0.60
Image errors : No obvious image errors, the lighting effect of the tunnel and light is somewhat unrealistic
Cyberpunk Dreams: A Glimpse into the Future of Technology
A dimly lit room, a keyboard bathed in red and blue light, and a figure lost in the digital world. This image captures the essence of cyberpunk, blending mystery, technology, and a hint of the unknown. The low angle and blurred hands create a sense of intrigue, drawing you into the heart of this futuristic scene.
Prompt
silhouette silhouette: intense, focused ; A gamer’s hands silhouetted against a glowing computer screen, typing furiously; close-up; gaming; futuristic, neon-lit gaming room; cinematic
Characteristic
Shot : A close-up shot of a person’s hands typing on a keyboard in a dimly lit room. The screen of a computer is visible in the background, with a colorful, pixelated light shining from it.
Aesthetic Score : 0.6
Mood : mysterious, dark, focused
Quality
Entropy : 6.38
Noise : 113
Prompt Clip Score : 0.19
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image appears slightly blurry, especially on the hands and keyboard. The colors are also slightly overexposed.
Sunset Silhouettes on a Tranquil Beach
A serene scene of three silhouettes standing on a beach at sunset, with a palm tree in the foreground and the ocean in the background. The silhouettes create a sense of mystery and intrigue, evoking a nostalgic and tranquil mood.
Prompt
silhouette silhouette: peaceful, heartwarming ; A family standing on a beach, silhouetted against the setting sun; medium shot; tourism; tropical beach with palm trees; cinematic
Characteristic
Shot : A silhouette of three people standing on a beach at sunset, with a palm tree in the foreground.
Aesthetic Score : 0.7
Mood : serene, peaceful, contemplative
Quality
Entropy : 6.49
Noise : 125
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : Slight graininess, slightly overexposed, some chromatic aberration.
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 0.3, which is considered below average. This suggests that the model didn’t accurately capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.455, which is also below average. This indicates that the model didn’t fully understand the scene described in the prompt and didn’t create an image that accurately reflects it.
- Aesthetic Analysis: The model scored 0.09, which is considered very good. This means that the generated image closely matched the expected aesthetic style.
Overall, the model seems to be better at capturing the desired aesthetic than understanding the scene and camera position. This suggests that the model might need further training to improve its ability to interpret and translate prompts into accurate visual representations.
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://midjourney.com