AI's Artistic Struggle: Capturing the Essence of Dramatic Poses with Flux-dev
- 9 minutes read - 1848 wordsTable of Contents
Dramatic poses are a powerful tool in visual storytelling, conveying emotions, actions, and narratives through the positioning of the human body. These poses often involve dynamic angles, exaggerated movements, and a sense of heightened emotion. In this blog post, we explore the challenges of capturing the essence of dramatic poses using generative AI models. We analyze the results of a model tasked with creating images based on various dramatic scenes, examining its ability to understand scene composition, camera position, and aesthetic. Through this analysis, we gain insights into the strengths and weaknesses of current AI art generation techniques and discuss the potential for future advancements in capturing the nuances of human expression and artistic intent.
Created with: flux-dev
Silhouetted Against the Storm
A lone figure stands defiant on a hilltop, silhouetted against a stormy sky. A lightning bolt strikes in the distance, adding a dramatic and ominous touch to the scene. The image evokes a sense of power, danger, and epic scale.
Prompt
poses dutch-angle: determined, heroic, hopeful ; A lone knight, standing tall on a hilltop overlooking a besieged city; wide shot; heroism; a dramatic, stormy sky with flashes of lightning; cinematic
Characteristic
Shot : A lone figure in a cape stands on a rocky cliff, facing a stormy sky filled with lightning, with a cityscape in the background
Aesthetic Score : 0.7
Mood : epic, dramatic, powerful
Quality
Entropy : 6.41
Noise : 76
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.80
Image errors : The lightning in the sky feels a bit unrealistic and cartoonish, and the cityscape has a low resolution and looks a bit grainy. Some blurriness in the clouds, especially the ones closest to the viewer.
Golden Hour Adventure: Hikers Embrace the Tranquil Sunset
Capture the essence of peace and adventure as four hikers traverse a forest path bathed in the warm glow of a setting sun. The dramatic lighting highlights the beauty of the scene, creating a moment of tranquility and wonder.
Prompt
poses dutch-angle: adventurous, mysterious, awe-inspiring ; A group of explorers, silhouetted against the setting sun, standing at the edge of a vast, unexplored jungle; medium shot; adventure; lush green foliage and towering trees; cinematic
Characteristic
Shot : Four hikers are silhouetted against a sunset, walking along a mountain trail.
Aesthetic Score : 0.6
Mood : tranquil, peaceful, adventurous
Quality
Entropy : 6.47
Noise : 96
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : No visible errors in the image.
Lost in the Glow: Gamer’s Focus Under Neon Lights
A young man, eyes glued to the screen, is completely immersed in his digital world. Vibrant pink and blue lights illuminate the scene, creating a playful and intense atmosphere. This image captures the focused energy of a gamer lost in the thrill of the game.
Prompt
poses dutch-angle: intense, focused, competitive ; A gamer, intensely focused on a screen, fingers flying across a keyboard; close-up; gaming; a brightly lit room with gaming peripherals and posters; cinematic
Characteristic
Shot : A young man wearing a headset sits at a computer desk, lit by pink and blue neon lights. He appears focused on something on the screen.
Aesthetic Score : 0.7
Mood : focused, serious, techy
Quality
Entropy : 6.78
Noise : 68
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has a slight chromatic aberration effect noticeable on the edges of the subject’s head and the computer screens. The overall sharpness could be improved.
A Romantic Moment in Paris: Love Blooms at the Cafe with a View of the Eiffel Tower
Experience the warmth and intimacy of a couple’s romantic rendezvous in a cozy Parisian cafe. As they gaze out the window at the iconic Eiffel Tower, their silhouette against the backdrop creates a dramatic and unforgettable scene, capturing the essence of love and romance.
Prompt
poses dutch-angle: romantic, nostalgic, joyful ; A couple, hand-in-hand, gazing out at the Eiffel Tower from a Parisian cafe; medium shot; tourism; bustling Parisian streets with charming cafes and shops; cinematic
Characteristic
Shot : A couple is sitting at a cafe table next to a window, looking out at the Eiffel Tower in the distance.
Aesthetic Score : 0.6
Mood : romantic, intimate, happy
Quality
Entropy : 6.22
Noise : 69
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.10
Image errors : Some noise is visible in the darker areas, the image is a little blurry.
A Lone Hiker Embraces the Mountain’s Majesty
A solitary figure with a red backpack traverses a snow-capped mountain trail, their journey towards the summit evoking a sense of serenity, adventure, and hope. The vastness of the landscape creates a dramatic perspective, inspiring awe and wonder.
Prompt
poses dutch-angle: free-spirited, adventurous, inspiring ; A backpacker, walking along a winding mountain path, with breathtaking views of snow-capped peaks; medium shot; travel; a rugged mountain landscape with clear blue skies; cinematic
Characteristic
Shot : A lone hiker walks along a trail in the mountains. The mountains are snow-capped and the sky is blue. The scene is serene and inspiring.
Aesthetic Score : 0.7
Mood : serene, inspiring, adventurous
Quality
Entropy : 6.74
Noise : 89
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
Cheers to Friendship! A Toast to Good Times
A group of friends raise their glasses in a joyous toast, capturing the warmth and celebration of a night out at a cozy restaurant or bar. The festive atmosphere and inviting lighting create a sense of togetherness and shared joy.
Prompt
poses dutch-angle: joyful, celebratory, connected ; A group of friends, laughing and celebrating, raising their glasses in a toast; medium shot; groups; a lively bar or restaurant with warm lighting and festive decorations; cinematic
Characteristic
Shot : A group of friends is toasting with drinks at a table, likely at a bar or restaurant, with a festive atmosphere and warm lighting. There is a lot of bokeh in the background.
Aesthetic Score : 0.7
Mood : happy, festive, celebratory
Quality
Entropy : 6.84
Noise : 85
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible errors, except the camera focus on the glasses is a little bit off.
A Moment of Solitude in the Vastness of Space
An astronaut, silhouetted against the backdrop of Earth, gazes out of a spacecraft window, capturing the essence of solitude and wonder amidst the immensity of space. The dramatic contrast between the lone figure and the vast expanse evokes a sense of isolation and awe.
Prompt
poses dutch-angle: awe-inspiring, contemplative, hopeful ; A lone astronaut, gazing out at the Earth from a space station window; close-up; heroism; the vastness of space with stars and planets in the background; cinematic
Characteristic
Shot : A lone astronaut looks out a porthole window at the Earth, with clouds and the horizon in the distance.
Aesthetic Score : 0.7
Mood : solitude, anticipation, wonder
Quality
Entropy : 6.49
Noise : 94
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.20
Image errors : No noticeable errors or artifacts present.
Conquering the Canyon: Awe-Inspiring Rappel Through Majestic Landscapes
Witness the breathtaking scale of a vast canyon as three climbers descend its steep face. Lush greenery blankets the slopes, while the tiny figures of the adventurers evoke a sense of wonder and adventure.
Prompt
poses dutch-angle: exciting, daring, adventurous ; A group of adventurers, rappelling down a steep cliff face, with a breathtaking view of a valley below; wide shot; adventure; a dramatic mountain landscape with waterfalls and lush vegetation; cinematic
Characteristic
Shot : Three figures on a narrow ledge overlooking a deep valley with a waterfall. The cliff face is rocky and the valley is green.
Aesthetic Score : 0.8
Mood : dramatic, adventurous, awe-inspiring
Quality
Entropy : 6.78
Noise : 104
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly grainy, but otherwise free of visible artifacts.
Triumphant Silhouette: A Moment of Joy Under the Spotlight
A person, bathed in the glow of stage lights, raises a trophy high in the air, their headphones reflecting the moment’s ecstasy. The silhouette against the bright backdrop creates a powerful image of triumph and joy.
Prompt
poses dutch-angle: triumphant, celebratory, exciting ; A gamer, celebrating a victory, holding up a trophy; close-up; gaming; a brightly lit stage with cheering crowds and flashing lights; cinematic
Characteristic
Shot : A person in a concert setting, raising a trophy in the air with their right hand, wearing headphones, with a crowd in the background
Aesthetic Score : 0.6
Mood : excited, triumphant, celebratory
Quality
Entropy : 6.32
Noise : 54
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image has some slight noise and compression artifacts, particularly in the darker areas. The subject’s hand holding the trophy is a bit blurry. The crowd is mostly out of focus.
Silhouettes of Love: A Family’s Sunset Moment
A heartwarming scene of a family of four silhouetted against a vibrant sunset over the ocean. Their peaceful stance and the dramatic effect of the light create a tranquil and memorable moment.
Prompt
poses dutch-angle: peaceful, heartwarming, nostalgic ; A family, standing on a beach, watching the sunset over the ocean; medium shot; travel; a serene beach with golden sand and turquoise waters; cinematic
Characteristic
Shot : A family of four is silhouetted against a sunset on a beach.
Aesthetic Score : 0.7
Mood : tranquil, peaceful, happy
Quality
Entropy : 6.61
Noise : 67
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : There are no visible artifacts or errors in the image.
Conclusion
The results show that the generative AI model performed well in terms of understanding the scene and camera position, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.35, which is below the “good” range of 0.5 to 0.75. This suggests that the model didn’t fully capture the intended camera position described in the prompt.
- Shot Analysis: The model scored 0.515, which falls within the “good” range. This indicates that the model was able to understand the scene described in the prompt reasonably well.
- Aesthetic Analysis: The model scored 0.09, which is significantly higher than the “very good” range of -0.2 to 0.1. This suggests that the generated image’s aesthetic deviated significantly from the expected aesthetic described in the prompt.
Overall, the model demonstrated a good understanding of the scene and shot composition, but struggled to achieve 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://fal.ai/models/fal-ai/flux/dev/api