AI's Artistic Journey: Capturing Poses and Scenes with Freepik
- 9 minutes read - 1794 wordsTable of Contents
In the realm of digital art, AI is making significant strides, particularly in generating images with specific poses and scenes. This ability to translate textual descriptions into visual representations opens up exciting possibilities for artists, designers, and storytellers. However, the accuracy and artistic finesse of AI models are still under development. This blog post explores the results of an experiment that tested the capabilities of a generative AI model in capturing poses and scenes, analyzing its performance in terms of camera position, shot composition, and aesthetic style. By understanding the strengths and weaknesses of AI in this domain, we can better appreciate its potential and limitations in artistic expression.
Created with: freepik
Sunset Showdown: Armored Warriors Clash in Epic Battle
Two heavily armored warriors engage in a fierce duel, their blades clashing against the backdrop of a raging battle. The golden light of the setting sun casts dramatic shadows, highlighting the intensity of the conflict.
Prompt
poses fighting: epic, determined ; A lone warrior; wide shot; heroism; a desolate battlefield with the setting sun in the background; cinematic
Characteristic
Shot : Two warriors in full armor are facing each other in a battlefield, a sunset is in the background and there are other warriors in the background, the image seems to be depicting a duel
Aesthetic Score : 0.7
Mood : epic, dramatic, intense
Quality
Entropy : 6.75
Noise : 58
Prompt Clip Score : 0.26
AI Evaluation
Likelihood of AI : 0.90
Image errors : No visible errors in the image
The Emptiness of Darkness
A stark, black image evokes a sense of emptiness and void. The absence of light and detail creates a mood of nothingness, leaving the viewer with a profound sense of absence.
Prompt
poses fighting: intense, adventurous ; A group of adventurers; medium shot; adventure; a dense jungle with ancient ruins in the distance; cinematic
Characteristic
Shot : A black void, completely empty.
Aesthetic Score : 0
Mood : empty, dark, void
Quality
Entropy : 0.00
Noise : 0
Prompt Clip Score : 0.17
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is just a black void, so there are no artifacts or errors.
Cyberpunk Warrior: Ready for Action
A fierce woman in a futuristic outfit stands amidst the neon glow of a cyberpunk city, radiating power and readiness for battle. The dramatic lighting and pose create a sense of action and intensity, capturing the essence of this futuristic world.
Prompt
poses fighting: dynamic, futuristic ; A player character; close-up; gaming; a neon-lit cityscape with holographic projections; cinematic
Characteristic
Shot : A futuristic cityscape with a woman in a cyberpunk-inspired outfit, standing in a pose of readiness, with a blurred background of people in the city.
Aesthetic Score : 0.75
Mood : futuristic, edgy, intense
Quality
Entropy : 6.86
Noise : 56
Prompt Clip Score : 0.29
AI Evaluation
Likelihood of AI : 0.90
Image errors : Some minor blurring in the background, and the woman’s hand appears slightly distorted.
Clash of Titans: Tension Rises in the Market
Two men lock eyes in a crowded street market, their stances and expressions hinting at a brewing conflict. The air crackles with anticipation, leaving the viewer wondering if a playful rivalry will escalate into something more serious.
Prompt
poses fighting: chaotic, humorous ; Two tourists; medium shot; tourism; a bustling marketplace with colorful stalls and vibrant crowds; cinematic
Characteristic
Shot : Two men are facing each other in a fighting stance in a crowded street market. The background is blurred, and the men are the focus of the image.
Aesthetic Score : 0.5
Mood : intense, playful, confrontational
Quality
Entropy : 6.81
Noise : 81
Prompt Clip Score : 0.34
AI Evaluation
Likelihood of AI : 0.10
Image errors : The image is a little blurry and lacks sharpness, especially in the background. The lighting is uneven.
Lost in the Vastness: A Solitary Figure Conquers the Desert
A lone traveler braves the unforgiving desert, their journey a testament to resilience and the overwhelming power of nature. The sun casts long shadows, emphasizing the vastness of the landscape and the figure’s smallness in comparison. This image evokes a sense of solitude, desolation, and the profound insignificance of human existence in the face of such grandeur.
Prompt
poses fighting: isolated, desperate ; A lone traveler; long shot; travel; a vast desert landscape with a lone sand dune in the foreground; cinematic
Characteristic
Shot : A lone figure walks across a vast, sandy desert. The figure is wearing a robe and is walking in the direction of a distant mountain range. The sun is setting, casting a warm glow over the scene.
Aesthetic Score : 0.7
Mood : serene, isolated, contemplative
Quality
Entropy : 4.86
Noise : 39
Prompt Clip Score : 0.23
AI Evaluation
Likelihood of AI : 0.20
Image errors : There are no visible artifacts or errors in the image.
City Lights, City Friends: A Rooftop Moment of Energy and Fun
Four young women stand in a circle on a rooftop, their laughter and energy echoing against the backdrop of a glittering cityscape. The scene captures a moment of friendship and fun, with the dynamic poses of the women adding a sense of excitement to the image.
Prompt
poses fighting: energetic, playful ; A group of friends; medium shot; groups; a rooftop overlooking a city skyline at night; cinematic
Characteristic
Shot : Four women are standing on a rooftop at night, facing each other. They are dressed in athletic wear and appear to be engaged in a conversation or activity. The city skyline is visible in the background, with many lights illuminating the scene.
Aesthetic Score : 0.7
Mood : energetic, confident, playful
Quality
Entropy : 6.77
Noise : 59
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.20
Image errors : There is a slight blurriness in the image, particularly around the edges of the women’s bodies, which could be due to slight camera shake or post-processing. The lighting is a little uneven, with some areas of the image being too bright or too dark.
Knight of Ashes: A Sole Survivor Amidst the Ruins
A lone knight, clad in armor, strides through a village consumed by flames. Smoke billows, casting an ominous glow on his determined face. This powerful image captures the intensity and somber mood of a world ravaged by conflict.
Prompt
poses fighting: tragic, determined ; A lone warrior; close-up; heroism; a burning village with smoke billowing in the air; cinematic
Characteristic
Shot : A lone knight in full armor walks through a burning village. Smoke and flames fill the background.
Aesthetic Score : 0.7
Mood : dark, epic, dramatic
Quality
Entropy : 6.88
Noise : 58
Prompt Clip Score : 0.22
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image has some minor artifacts, such as the slight blurriness of the flames.
Shadows and Secrets: Soldiers Navigate a Mysterious Cave
A haunting image of four soldiers traversing a dark cave, illuminated only by flickering torches. The dramatic lighting creates an atmosphere of mystery and suspense, drawing the viewer into the heart of the unknown.
Prompt
poses fighting: suspenseful, adventurous ; A group of explorers; wide shot; adventure; a dark cave with flickering torches and mysterious shadows; cinematic
Characteristic
Shot : Four soldiers are walking through a cave with torches. The light from the torches illuminates the surrounding rocks, casting long shadows. The cave walls are rough and uneven, creating a sense of danger and mystery.
Aesthetic Score : 0.7
Mood : intense, suspenseful, mysterious
Quality
Entropy : 6.35
Noise : 60
Prompt Clip Score : 0.31
AI Evaluation
Likelihood of AI : 0.10
Image errors : No errors
Lost in the Digital Realm: A Young Man’s Immersive VR Experience
A dimly lit room becomes a portal to another world as a young man, fully engrossed in a virtual reality game, experiences the thrill of digital immersion. The blurred background and focused lighting highlight the transformative power of technology, capturing the intensity and excitement of the virtual realm.
Prompt
poses fighting: immersive, intense ; A gamer; close-up; gaming; a virtual reality headset with a pixelated world projected in the background; cinematic
Characteristic
Shot : A man wearing a VR headset is playing a video game in a dimly lit room. The scene is set in a living room with a television screen in the background.
Aesthetic Score : 0.6
Mood : focused, immersive, futuristic
Quality
Entropy : 6.65
Noise : 46
Prompt Clip Score : 0.27
AI Evaluation
Likelihood of AI : 0.30
Image errors : The image is slightly grainy and the lighting is a bit uneven. There is some slight blurriness around the edges of the subject.
Tension on the Platform: A Moment of Confrontation
A man and a woman stand locked in a tense confrontation on a crowded train platform. The dynamic composition, with strong diagonal lines, amplifies the intensity and suspense of the moment, leaving the viewer wondering what will happen next.
Prompt
poses fighting: fast-paced, chaotic ; Two travelers; medium shot; travel; a crowded train station with people rushing in all directions; cinematic
Characteristic
Shot : A man and a woman are in a tense confrontation on a train platform. The woman is running, and the man is holding her back.
Aesthetic Score : 0.6
Mood : intense, dramatic, suspenseful
Quality
Entropy : 6.81
Noise : 65
Prompt Clip Score : 0.32
AI Evaluation
Likelihood of AI : 0.20
Image errors : The image has some noise and grain, especially in the shadows. The lighting is also a little flat.
Conclusion
The results show that the generative AI model performed well in understanding the camera position and shot composition, but struggled with the aesthetic aspect. Here’s a breakdown:
- Camera Position: The model scored 0.4, 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 0.61, which is considered good. This indicates that the model was able to understand and translate the shot description in the prompt into the generated image.
- Aesthetic Analysis: The model scored 0.13, which is considered very good. This means that the generated image closely matched the expected aesthetic style described in the prompt.
Overall, the model demonstrates a good understanding of shot composition and a strong ability to achieve the desired aesthetic. However, it needs improvement in accurately capturing the intended camera position.
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://www.freepik.com