AI's Artistic Struggle: Capturing the Essence of Poses with Flux-dev
- 9 minutes read - 1867 wordsTable of Contents
In the realm of artificial intelligence, the ability to generate images based on text prompts is a rapidly evolving field. This blog post delves into the fascinating world of AI-generated images, specifically focusing on the challenge of capturing the essence of poses within a scene. We’ll explore the results of an experiment where an AI model was tasked with generating images based on various poses and scene descriptions, highlighting its strengths and weaknesses in translating artistic intent into visual outputs. Dramatic poses, often used in storytelling and visual arts, are designed to convey emotion, action, or a specific character trait. They are frequently employed in photography, film, and even graphic design to create a powerful visual impact. This experiment aimed to assess the AI model’s ability to understand and replicate the dramatic impact of these poses within different scene contexts.
Created with: flux-dev
A Solitary Figure Walks Towards Hope in a Ruined City
A lone figure, cloaked in mystery, walks away from the viewer towards a distant sunset in a ruined cityscape. The silhouette against the vibrant sky creates a sense of intrigue and hope, while the desolate surroundings evoke feelings of loneliness and isolation. This image captures a powerful and evocative moment, leaving the viewer to ponder the figure’s journey and the future that awaits.
Prompt
poses walking-away: Melancholy, yet hopeful ; Lone figure in a tattered cloak; wide shot; Heroism; Ruins of a fallen city bathed in the golden light of a setting sun; cinematic
Characteristic
Shot : A lone figure walks towards the setting sun in a desolate, ancient city. The city is in ruins and the sun is casting a warm glow over everything.
Aesthetic Score : 0.7
Mood : mystical, melancholic, hopeful
Quality
Entropy : 6.51
Noise : 74
Prompt Clip Score : 0.30
AI Evaluation
Likelihood of AI : 0.80
Image errors : The image has some minor artifacts around the figure’s edges, and there is a slight blurriness around the edges of the image.
Tranquil Forest Path Beckons with Sunlit Mystery
A young adventurer strolls through a lush forest, sunlight filtering through the foliage and creating a mesmerizing mist in the distance. The scene evokes a sense of tranquility, contemplation, and the promise of exciting discoveries.
Prompt
poses walking-away: Excited, adventurous ; A young adventurer with a backpack; medium shot; Adventure; Lush jungle with a hidden path leading into the unknown; cinematic
Characteristic
Shot : A young man with a backpack walks on a trail through a lush, green forest, sunlight filters through the trees, creating a misty atmosphere.
Aesthetic Score : 0.7
Mood : serene, peaceful, adventurous
Quality
Entropy : 6.65
Noise : 99
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed, and there is some noise in the shadows.
Lost in the Neon Maze
A solitary figure, shrouded in fog and bathed in the glow of city lights, stands alone in the heart of an urban landscape. The scene evokes a sense of mystery and isolation, leaving the viewer to ponder the character’s thoughts and motivations.
Prompt
poses walking-away: Focused, determined ; A gamer with a headset; close-up; Gaming; Neon-lit cityscape reflected in a computer screen; cinematic
Characteristic
Shot : A young man with headphones on, wearing a jacket and backpack, standing in a city at night with neon lights
Aesthetic Score : 0.6
Mood : urban, futuristic, moody
Quality
Entropy : 6.60
Noise : 60
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are some minor artifacts in the image, but they are not significant enough to detract from the overall aesthetic.
Love Story in the Shadows of a European City
A couple strolls hand-in-hand down a charming cobblestone street, their silhouettes framed against the radiant light at the end. The scene evokes a romantic, whimsical, and nostalgic mood, hinting at a story waiting to unfold.
Prompt
poses walking-away: Romantic, carefree ; A couple holding hands; medium shot; Tourism; Picturesque European street with cobblestone paths and colorful buildings; cinematic
Characteristic
Shot : A couple walks down a narrow alleyway in a European city. The buildings are old and worn, and the alleyway is lined with cobblestones. The couple is dressed casually, and the man is holding a bouquet of flowers.
Aesthetic Score : 0.6
Mood : romantic, intimate, adventurous
Quality
Entropy : 6.83
Noise : 93
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image is slightly overexposed and the colors are a bit muted.
Silhouette of Hope: A Man’s Journey Begins at Sunset
A solitary figure walks towards a departing airplane, his silhouette cast against the fiery hues of a setting sun. The image evokes a sense of loneliness and contemplation, yet also hints at a hopeful new beginning. The man’s journey, like the fading light, promises both uncertainty and possibility.
Prompt
poses walking-away: Nostalgic, bittersweet ; A lone traveler with a suitcase; long shot; Travel; Airport runway with a departing airplane in the distance; cinematic
Characteristic
Shot : A lone traveler walks towards an airplane that has just landed at an airport.
Aesthetic Score : 0.6
Mood : melancholy, hopeful, contemplative
Quality
Entropy : 6.55
Noise : 60
Prompt Clip Score : 0.24
AI Evaluation
Likelihood of AI : 0.30
Image errors : No obvious errors in the image.
Silhouettes of Joy: A Sunset Stroll on the Beach
Capture the essence of carefree summer evenings with this stunning image. Four young adults walk along a sandy beach, their silhouettes stark against the vibrant orange sunset. The peaceful mood and dramatic lighting create a sense of depth and mystery, making this a perfect choice for evoking feelings of joy and tranquility.
Prompt
poses walking-away: Joyful, carefree ; A group of friends laughing; wide shot; Groups; Beach at sunset with the ocean waves crashing in the background; cinematic
Characteristic
Shot : Four friends are walking along a beach at sunset, silhouetted against the golden sky.
Aesthetic Score : 0.7
Mood : happy, carefree, friendship
Quality
Entropy : 6.50
Noise : 66
Prompt Clip Score : 0.28
AI Evaluation
Likelihood of AI : 0.20
Image errors : No visible errors.
A Shadow in the Mist: A Lone Figure Walks Towards the Unknown
A solitary figure, cloaked in darkness and wielding two swords, traverses a fog-shrouded path. The light at the end, a beacon of hope or a harbinger of danger, draws them forward. This mysterious scene evokes a sense of suspense and intrigue, leaving the viewer to wonder what lies ahead.
Prompt
poses walking-away: Determined, resolute ; A lone warrior with a sword; medium shot; Heroism; Dark forest with a path leading into the shadows; cinematic
Characteristic
Shot : A lone figure walks down a path in a dense, foggy forest carrying two swords.
Aesthetic Score : 0.7
Mood : mysterious, eerie, suspenseful
Quality
Entropy : 6.52
Noise : 88
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.90
Image errors : The image appears to be slightly blurry and the lighting is uneven.
Shadows and Secrets: A Journey Through Ancient Stone
Four figures walk towards a warm, inviting light at the end of a mysterious stone corridor. The backlighting creates an atmosphere of intrigue and hope, promising adventure around every corner.
Prompt
poses walking-away: Curious, excited ; A group of explorers with maps; wide shot; Adventure; Ancient ruins with a mysterious entrance; cinematic
Characteristic
Shot : Four people, likely friends or family, are walking in a narrow alleyway between tall stone walls with an opening at the end of the alleyway, leading to a bright light. The sun is shining brightly, and there are shadows cast by the walls.
Aesthetic Score : 0.6
Mood : mysterious, adventurous, hopeful
Quality
Entropy : 6.70
Noise : 99
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is slightly overexposed, especially in the background. There is also some chromatic aberration.
Immersed in the Future: A Vibrant Techscape
A young woman stands in a futuristic room bathed in blue and purple neon, her VR headset and controller hinting at a world of immersive possibilities. The vibrant colors and lighting create a sense of energy and excitement, showcasing the power of technology to transport us to new realities.
Prompt
poses walking-away: Immersed, excited ; A gamer with a controller; close-up; Gaming; Virtual reality headset with a fantastical world displayed; cinematic
Characteristic
Shot : A young woman wearing a VR headset, standing in a brightly lit room. She is holding a game controller and appears to be playing a game.
Aesthetic Score : 0.6
Mood : futuristic, playful, engaging
Quality
Entropy : 6.85
Noise : 61
Prompt Clip Score : 0.25
AI Evaluation
Likelihood of AI : 0.10
Image errors : No noticeable artifacts or errors present.
A Family’s Journey Begins
A tranquil scene of a family of three walking away from the camera on a sunny train station platform. The father pulls a rolling suitcase, their shadows stretching across the floor, hinting at a hopeful departure. The image evokes a sense of longing and the promise of new beginnings.
Prompt
poses walking-away: Emotional, bittersweet ; A family with luggage; long shot; Travel; Train station platform with a departing train in the distance; cinematic
Characteristic
Shot : A family of three, a father and two daughters, are walking away from the camera on a train platform. They are walking towards a train that is leaving the station. The father is carrying a suitcase.
Aesthetic Score : 0.6
Mood : tranquil, bittersweet, farewell
Quality
Entropy : 6.36
Noise : 69
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is some noise in the image and the edges of the figures are slightly blurry.
Conclusion
The results show that the generative AI model performed well in terms of camera position and shot analysis, but struggled with aesthetic analysis. Here’s a breakdown:
Camera Position:
- Score: 0.45
- Interpretation: This score falls below the “good” range of 0.5 to 0.75. It suggests that the model didn’t perfectly capture the intended camera positions described in the prompt.
Shot Analysis:
- Score: 0.6
- Interpretation: This score falls within the “good” range of 0.5 to 0.75. It indicates that the model was able to understand and translate the scene description from the prompt into the generated image fairly well.
Aesthetic Analysis:
- Score: 0.12
- Interpretation: This score is significantly higher than the “very good” range of -0.2 to 0.1. It suggests that the generated image’s aesthetic deviated considerably from the expected aesthetic described in the prompt.
Overall:
The model demonstrates a good understanding of shot composition and scene description, but struggles to accurately capture the desired aesthetic. This suggests that the model might need further training to better understand and translate aesthetic preferences into visual outputs.
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