Artful Image Processing and Algorithmic Drawing

Having set up the object detection pipeline, I proceeded to the image processing stage, where the raw visual data and the model’s outputs are transformed into a more artistic representation. My process involved several key steps. First, I applied edge detection algorithms to the video frames. This technique identifies points in a digital image where the brightness changes sharply, effectively outlining the shapes and contours of objects in the scene. Next, I inverted the black and white colour, creating a stark, high-contrast visual style. Finally, I took the bounding boxes generated by the YOLO detection model and redrew them onto this processed image. This layering of machine perception over a stylised version of reality creates a compelling visual dialogue between the actual scene and the AI’s interpretation of it.

Processing Perceptions with YOLO and the COCO Dataset

With the video pipeline established, I turned my attention to processing the visual data using a combination of powerful tools. The core of this stage is the YOLO (You Only Look Once) object detection model. YOLO is a state-of-the-art, real-time object detection system that identifies and classifies objects in a single pass of an image, making it incredibly fast and efficient. For this project, I am intentionally using the model with the pre-trained COCO (Common Objects in Context) dataset. The COCO dataset is a large-scale collection of images depicting common objects in everyday scenes and is a standard benchmark for training and evaluating computer vision models.

My goal is not to achieve flawless object recognition but rather to play with the inherent “mistakes” and misinterpretations the machine makes. The default COCO dataset is perfectly suited for this, as its generalised training can lead to incorrect predictions when applied to novel or ambiguous scenes. To manipulate the image data, which is essentially a collection of pixels, I am using NumPy (Numerical Python). NumPy is a fundamental library for scientific computing in Python that allows for efficient manipulation of large, multi-dimensional arrays and matrices—the very structure that represents digital images.

What is Object Detection?

Object detection is a field of computer vision and image processing concerned with identifying and locating instances of objects within images and videos. Unlike simple image classification, which assigns a single label to an entire image, object detection models draw bounding boxes around each detected object and assign a class label to it, providing more detailed information about the scene.

What are NumPy and the COCO Dataset?

  • NumPy: A Python library that provides support for large, multi-dimensional arrays and matrices, along with a collection of mathematical functions to operate on these arrays. In image processing, an image is treated as a 3D array (height, width, colour channels), making NumPy an indispensable tool for any pixel-level manipulation.
  • COCO Dataset: Standing for “Common Objects in Context,” this is a massive dataset designed for object detection, segmentation, and captioning tasks. It contains hundreds of thousands of images with millions of labelled object instances across 80 “thing” categories and 91 “stuff” categories, providing a rich foundation for training computer vision models.

Objects Detectable by the COCO Dataset:

The COCO dataset can identify 80 common object categories, including:

  • People: person
  • Vehicles: bicycle, car, motorcycle, airplane, bus, train, truck, boat
  • Outdoor: traffic light, fire hydrant, stop sign, parking meter, bench
  • Animals: bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe
  • Accessories: backpack, umbrella, handbag, tie, suitcase
  • Sports: frisbee, skis, snowboard, sports ball, kite, baseball bat, baseball glove, skateboard, surfboard, tennis racket
  • Kitchen: bottle, wine glass, cup, fork, knife, spoon, bowl
  • Food: banana, apple, sandwich, orange, broccoli, carrot, hot dog, pizza, donut, cake
  • Furniture: chair, couch, potted plant, bed, dining table, toilet
  • Electronics: tv, laptop, mouse, remote, keyboard, cell phone
  • Appliances: microwave, oven, toaster, sink, refrigerator
  • Indoor: book, clock, vase, scissors, teddy bear, hair drier, toothbrush

Weaving a World Model with Reinforcement Learning Concepts

With a large dataset of generated policies, the next step is to import them back into the primary software application that displays the 360-degree video. This integration allows the dynamically generated rules to influence the visual output or behaviour of the system in real-time. My use of the term “policy” is a deliberate nod to its origins in the field of Reinforcement Learning (RL), a concept dating back to the 1990s. In RL, a policy is the strategy an agent employs to make decisions and take actions in its environment. It is the core component that dictates the agent’s behaviour as it learns through trial and error to maximise cumulative reward. By generating policies based on visual input, my system is, in a sense, creating its own world model—a simplified, learned representation of its environment and the relationships within it. This process echoes the fundamental principles of how an AI agent learns to react to and make sense of the real world, a topic I have delved into in more detail in some of my earlier writings.

Generating AI Policies from Object Proximity

In a more experimental turn, I developed a separate piece of software to explore the concept of emergent behaviour based on the object detection output. This program uses a Large Language Model (LLM) to generate “policies” when objects from the COCO dataset are detected in close proximity on the screen. The system calculates the normalised distance between the bounding boxes of detected objects. This distance value is then fed to the LLM, which has been prompted to generate a policy or rule based on the perceived danger or interaction potential of the objects being close together. For instance, if a “person” and a “car” are detected very close to each other, the LLM might generate a high-alert policy, whereas a “cup” and a “dining table” would result in a benign, functional policy. This creates a dynamic system where the AI is not just identifying objects, but also creating a narrative or a set of rules about their relationships in the environment.

Setting the software with 360-Degree Vision

The initial phase of this project involved tackling the technical groundwork required to process 360-degree video. I began by using OpenCV, a powerful open-source computer vision library, to stitch together the two separate video feeds from my 360-degree camera. OpenCV is an essential tool for real-time image and video processing, providing the necessary functions to merge the hemispheric views into a single, equirectangular frame. After successfully connecting the camera to my computer, I set up a basic Python workspace within my integrated development environment (IDE). The next step was to write a script that could access the camera’s video stream and display it in a new window, confirming that the foundational hardware and software were communicating correctly. This setup provides the visual canvas upon which the subsequent layers of AI-driven interpretation will be built.

Embracing the Algorithmic Uncanny

I am revisiting a creative process that has captivated my interest for some time: enabling an agent to perceive and learn about its environment through the lens of a computer vision model. In a previous exploration, I experimented with CLIP (Contrastive Language-Image Pre-Training), which led to the whimsical creation of a sphere composed of text, a visual representation of the model’s understanding. This time, however, my focus shifts to the YOLO (You Only Look Once) model. My prior experiences with YOLO, using the default COCO dataset, often yielded amusingly incorrect object detections—a lamp mistaken for a toilet, or a cup identified as a person’s head. Instead of striving for perfect accuracy, I intend to embrace these algorithmic errors. This project will be a playful exploration of the incorrectness and the fascinating illusions generated by an AI model, turning its faults into a source of creative inspiration.

* visualization using CLIP and Blender for artwork “Golem Wander in Crossroads”

Ultralytics YOLO

https://docs.ultralytics.com

Ultralytics YOLO is a family of real-time object detection models renowned for their speed and efficiency. Unlike traditional models that require multiple passes over an image, YOLO processes the entire image in a single pass to identify and locate objects, making it ideal for applications like autonomous driving and video surveillance. The architecture divides an image into a grid, and each grid cell is responsible for predicting bounding boxes and class probabilities for objects centered within it. Over the years, YOLO has evolved through numerous versions, each improving on the speed and accuracy of its predecessors.
(Text from Gemini-2.5-Pro and edited by artist)

CLIP

https://github.com/openai/CLIP

CLIP (Contrastive Language-Image Pre-Training), developed by OpenAI, is a neural network that learns visual concepts from natural language descriptions. It consists of two main components: an image encoder and a text encoder, which are trained jointly on a massive dataset of 400 million image-text pairs from the internet. This allows CLIP to create a shared embedding space where similar images and text descriptions are located close to one another. A key capability of CLIP is “zero-shot” classification, meaning it can classify images into categories it wasn’t explicitly trained on, simply by providing text descriptions of those categories.

(Text from Gemini-2.5-Pro and edited by artist)

COCO

https://cocodataset.org/#home

https://docs.ultralytics.com/datasets/detect/coco

COCO (Common Objects in Context), is a large-scale object detection, segmentation, and captioning dataset. It is designed to encourage research on a wide variety of object categories and is commonly used for benchmarking computer vision models. It is an essential dataset for researchers and developers working on object detection, segmentation, and pose estimation tasks.

(Text from Ultralytics YOLO Docs)

REST without AI

This week, Hong Kong was battered by heavy rain, and I took the chance to take a breather and recharge. The last few weeks have been manic. I’ve been working on three software projects at once. The non-stop pace had left me totally overloaded, so this rain break was just what I needed. I decided to visit my wife home village, a recharging place in the middle of the city’s forests. The air smelt of earth, and the quiet beauty of the landscape was a nice change. I could feel the tension of my tightly wound days begin to unravel, replaced by a sense of calm that felt long overdue. The mountains were like silent guards, making me think about the balance between creativity and rest.

The Question: 11AUG2025

The modern AI, most prominently represented by the Large Language Models (LLMs), prompts a fundamental question: Does it contain consciousness? To pose the question another way, the original wellspring of the AI concept is found where brain scientists, computer scientists and mathematicians began to explore if consciousness itself could be understood as a mathematical or computational process, as a system. This inquiry delves into whether today’s advanced automation is merely sophisticated mimicry or a genuine step towards the sentient machines envisioned by pioneers of the field. As Noam Chomsky openly criticises the GPT model as a fake intelligence, a copycat only. Or is there an even deeper question: is there any form of computing that can capture the differences between intelligence, awareness and consciousness? Or we simply don’t understand our kind. Those three words are just a game of our language, a misconception; they never exist.

Catastrophic Forgetting

The contemporary world is becoming increasingly influenced by artificial intelligence (AI) models, some of which are known as ‘world models’. While these concepts gained significant attention in 2025, their origins can be traced much further back. Jürgen Schmidhuber introduced the foundational architecture for planning and reinforcement learning (RL) involving interacting recurrent neural networks (RNNs)—including a controller and a world model—in 1990. In this framework, the world model serves as an internal, differentiable simulation of the environment, learning to predict the outcomes of the controller’s actions. By simulating these action-consequence chains internally, the agent can plan and optimise its decisions. This approach is now commonly used in video prediction and simulations within game engines, yet it remains closely related to cameras and image processing.

Despite the advancements made, a fundamental limitation first identified in 1990 continues to challenge the progress: the problem of instability and catastrophic forgetting. As the controller guides the agent into new areas of experience, there is a risk that the network will overwrite previously learned knowledge. This leads to fragile, non-lifelong learning, where new information erases older representations. Furthermore, Prof. Yann LeCun mentioned in his presentation ‘The Shape of AI to Come’ at the AI Action Summit’s Science Days at the Institut Polytechnique de Paris (IP Paris) that the volume of data that a large language model contains remains minimal compared to that of a four-year-old child’s data volume, as 1.1E14 bytes. One of the titles of his slides that has stayed in my mind is “Auto-Regressive Generative Models Suck!” In the area of reinforcement learning, the AI’s policies often remain static, unable to adapt to the unforeseen complexities of the real world — in other words, the AI does not learn after the training process. Recently, emerging paradigms like Liquid Neural Networks (Ramin Hasani) and Dynamic Deep Learning (Richard Sutton) attempt to address this rigidity. However, those approaches are still highly reliant on randomly selecting and cleaning a neural network inside, to maintain the learning dynamic and potentially improve real-time reaction and long-term learning. Nevertheless, they are still facing challenges in solving the problem of AI’s hallucinations. A fundamental paradigm shift for AI is needed in our time, but it takes time, and before that, this paradigm may already be overwhelming for both machines and humans.

Meet the artists: Vital Capacities residency, August 2025

A collage of three pictures showing the resident artists with Lazarus Chan on the left wearing a white button down shirt, Leah Clements in the centre wearing black kneeling before a painting, and on the right is Elora Kadir with long dark hair and red top.
Resident artists, August 2025 from left to right: Lazarus Chan, Leah Clements, Elora Kadir

For the 11th Vital Capacities residency, we partner with Film London Artists’ Moving Image Network and Wysing Arts Centre to work with artists from the UK and Hong Kong. From 1 August, artists Chan Long Fung, Lazarus, Leah Clements, and Elora Kadir will join Vital Capacities to undertake research and develop new work. Over the month-long online residency, the artists will explore new ideas, connect across disciplines and geographies, and experiment within their digital studio spaces.

The artists for August 2025’s residency are:

Chan Long Fung, Lazarus, a new media artist from Hong Kong, fuses science, technology, and art to create visual experiences through sound, generative art, and data visualisations. His art interrogates the essence of natural and cultural phenomena, drawing on deep technological insight. During the residency, he will continue developing his series Stochastic Camera, delving into AI and the nature of creativity, consciousness, and automated seeing.

Leah Clements is an artist from and based in East London. Her work thinks about transcendence, affect, illness, and the other-worldly. It spans film, photography, performance, installation, sound, and other media. For this residency, she will be developing a new moving image work that draws on symbols from across time – ancient, medieval, and modern – reflecting her ongoing interest in moments of epiphany, transformation, and meaning-making through the lens of chronic illness and collective experience.

Elora Kadir is an artist based in London whose practice spans installation, drawing, photography, video, and found objects. Her work explores lived experiences of disability and how these intersect with the outside world – whether through navigating physical spaces, engaging with bureaucratic systems, or encountering subtle tensions and mismatches within an able-bodied society. During the residency, she will explore those small moments of friction where body and environment fail to align, experimenting with materials and language to make these dissonances visible.

An online exhibition showcasing work developed during the residency will be presented on vitalcapacities.com in September 2025.

Residency launches on 1 August 2025 – find out what the artists are up to by following their progress at: vitalcapacities.com and on Instagram: @vitalcapacities

Vital Capacities is an accessible, purpose-built digital residency space, that supports artists’ practice while engaging audiences with their work.

Vital Capacities has been created by videoclub in consultation with artists, digital inclusion specialist Sarah Pickthall and website designer Oli Pyle.

Vital Capacities 2025 residency is supported by Arts Council England.

Leveraging ChatGPT Prompt Engineering for Artists

Prompt engineering can be a powerful tool for artists to enhance their creative process, generate new ideas, and refine their work. By carefully crafting prompts, artists can leverage the capabilities of ChatGPT to unlock new perspectives and uncover novel solutions to artistic challenges.

Task

Clearly Define Objectives

Identify the specific goals or activities you want to accomplish using ChatGPT, such as generating ideas, exploring color palettes, or refining compositions.

Consider Your Artistic Needs

Reflect on the unique challenges or areas of focus in your artistic practice, and tailor your prompts accordingly.

Experiment with Prompts

Try different prompt structures and see how they impact the output to find the most effective approach for your needs.

Context

Provide Background

Share relevant information about your artistic style, medium, or the specific project you’re working on to help ChatGPT understand the context.

Describe Your Challenges

Openly communicate any obstacles or barriers you’re facing in your creative process, as this can guide ChatGPT’s responses.

Establish Constraints

Outline any limitations, such as technical requirements or stylistic preferences, to ensure the output aligns with your artistic vision.

Exemplar

Color Inspiration

Provide examples of artworks that capture the mood or aesthetic you’re aiming for, such as this abstract painting with a bold, vibrant color palette.

Conceptual Inspiration

Share images of artwork that exemplify the conceptual or thematic direction you’re exploring, like this surreal digital illustration.

Stylistic Inspiration

Provide examples of artistic styles or techniques you’re interested in experimenting with, such as this landscape painting with a soft, muted color palette.

Personal

Artistic Preferences

Communicate your unique artistic sensibilities, such as preferred color schemes, subject matter, or emotional tones, to guide ChatGPT’s responses.

Creative Challenges

Openly share any creative blocks or areas of growth you’re looking to address, so ChatGPT can provide tailored suggestions.

Artistic Identity

Reflect on your artistic identity and how you want to express it through your work, as this can inform the direction of your prompts.

Unique Perspective

Highlight your distinctive artistic perspective, experiences, or influences to help ChatGPT understand your unique creative voice.

Format

Structured Responses

Consider requesting the output in a specific format, such as a list, a step-by-step guide, or a series of paragraphs, to best suit your needs.

Visualizations

Incorporate visual elements like diagrams, illustrations, or color palettes to complement the textual output.

Customized Layout

Specify the desired structure or layout of the response to align with your artistic preferences or project requirements.

Tone

Formal

For technical, academic, or professional applications.

Casual

For more relaxed, conversational, or exploratory prompts.

Inspirational

To foster creativity, motivation, and a positive mindset.

Analytical

For prompts that require in-depth research or problem-solving.

Putting It All Together

Here’s how you might combine all these elements into a single prompt:

Prompt Example: “I am an abstract painter focusing on the interplay between light and shadow (context). I struggle with conveying emotions through my art (personal). Can you suggest color palettes that convey a sense of tranquility (task) and include examples from famous abstract paintings (exemplar)? Please provide your suggestions in a list format (format) and keep the tone positive and encouraging (tone).”

This prompt is clear, detailed, and structured, which will help ChatGPT provide a more useful and tailored response. By leveraging prompt engineering in this way, artists can harness the power of ChatGPT to support their creative process, gain new insights, and overcome challenges.

Reference

https://learnprompting.org/docs/intermediate/

Example Conversation with ChatGPT

you are a visual artistic, you would like to have 10 color theme of summer

ChatGPT:

Sure! Here are 10 summer color themes with their corresponding hex codes:

1. Tropical Sunset

  • #FF4500 (Orange Red)
  • #FF6347 (Tomato)
  • #FFD700 (Gold)
  • #FF69B4 (Hot Pink)
  • #FF1493 (Deep Pink)

2. Ocean Breeze

  • #00CED1 (Dark Turquoise)
  • #20B2AA (Light Sea Green)
  • #87CEEB (Sky Blue)
  • #4682B4 (Steel Blue)
  • #5F9EA0 (Cadet Blue)

3. Lemonade Stand

  • #FFFACD (Lemon Chiffon)
  • #FFD700 (Gold)
  • #FFDEAD (Navajo White)
  • #F4A460 (Sandy Brown)
  • #FFA07A (Light Salmon)

4. Coral Reef

  • #FF7F50 (Coral)
  • #FF6347 (Tomato)
  • #FF4500 (Orange Red)
  • #FF8C00 (Dark Orange)
  • #FFD700 (Gold)

5. Fresh Fruit

  • #FF6347 (Tomato)
  • #FF4500 (Orange Red)
  • #FFD700 (Gold)
  • #98FB98 (Pale Green)
  • #ADFF2F (Green Yellow)

6. Sandy Beach

  • #FFF8DC (Cornsilk)
  • #F5DEB3 (Wheat)
  • #DEB887 (Burly Wood)
  • #D2B48C (Tan)
  • #B8860B (Dark Goldenrod)

7. Summer Garden

  • #32CD32 (Lime Green)
  • #98FB98 (Pale Green)
  • #00FA9A (Medium Spring Green)
  • #3CB371 (Medium Sea Green)
  • #2E8B57 (Sea Green)

8. Ice Cream Parlor

  • #FFB6C1 (Light Pink)
  • #FF69B4 (Hot Pink)
  • #FFA07A (Light Salmon)
  • #FA8072 (Salmon)
  • #E9967A (Dark Salmon)

9. Picnic Blanket

  • #FA8072 (Salmon)
  • #FF6347 (Tomato)
  • #FFD700 (Gold)
  • #98FB98 (Pale Green)
  • #87CEFA (Light Sky Blue)

10. Wildflowers

  • #FF69B4 (Hot Pink)
  • #FF1493 (Deep Pink)
  • #FFA500 (Orange)
  • #FFD700 (Gold)
  • #ADFF2F (Green Yellow)

Each of these color themes captures a different aspect of summer, from the vibrant sunsets and clear ocean waters to the fresh fruits and sandy beaches.

following topic give me 3 visual elementChatGPT

Absolutely! Here are three visual elements for each of the summer color themes:

1. Tropical Sunset

  • Palm Trees Silhouettes: Against a vibrant sunset background, black or dark silhouettes of palm trees create a striking contrast.
  • Gradient Sky: Blending from deep pink to orange and yellow, representing the colors of a tropical sunset.
  • Sunset Over Water: Reflections of the sunset colors on the ocean or a lake, enhancing the warm and peaceful feeling.

2. Ocean Breeze

  • Waves and Seafoam: Gentle rolling waves with seafoam details, using shades of turquoise and blue.
  • Seashells and Starfish: Scattered along the beach in soft blue and sea green tones.
  • Beach Umbrellas: In light sea green and sky blue, providing a refreshing visual of a breezy beach day.

3. Lemonade Stand

  • Glass Jars with Lemonade: Filled with bright yellow lemonade and slices of lemon.
  • Striped Canopies: Using yellow and white stripes reminiscent of a classic lemonade stand.
  • Citrus Fruits: Lemons and oranges arranged in a basket or scattered, adding a fresh and zesty feel.

4. Coral Reef

  • Colorful Corals: Various shapes and sizes in vibrant coral and orange-red hues.
  • Tropical Fish: Brightly colored fish swimming among the corals.
  • Sea Anemones: In shades of pink and orange, adding movement and life to the scene.

5. Fresh Fruit

  • Assorted Fruits: Arrangements of tomatoes, oranges, lemons, and green apples.
  • Fruit Slices: Close-up views of sliced fruits showing their juicy interiors.
  • Fruit Baskets: Filled with an assortment of colorful fruits.

6. Sandy Beach

  • Footprints in the Sand: Trails of footprints leading towards the water.
  • Beach Towels and Mats: Laid out on the sand, using shades of tan and sandy brown.
  • Sandcastles: Detailed sandcastle sculptures with golden-brown hues.

7. Summer Garden

  • Lush Green Plants: Various shades of green foliage, from lime to dark green.
  • Flower Beds: Filled with blooming flowers in pale green and medium sea green.
  • Garden Pathways: Stone paths winding through the garden, bordered by vibrant greenery.

8. Ice Cream Parlor

  • Ice Cream Cones: With scoops in light pink, hot pink, and light salmon colors.
  • Parlor Signs: Retro-style signs in soft pastel hues advertising ice cream flavors.
  • Candy Sprinkles: Brightly colored sprinkles in shades of pink and salmon on top of ice cream.

9. Picnic Blanket

  • Checkered Blanket: A classic picnic blanket in red, gold, and light blue checks.
  • Picnic Basket: Filled with fruits, sandwiches, and a bottle of lemonade.
  • Outdoor Setting: A grassy field with a clear sky and scattered wildflowers.

10. Wildflowers

  • Flower Fields: Expansive fields filled with vibrant wildflowers in pink, orange, and yellow.
  • Close-up Blooms: Detailed close-ups of individual flowers showing their bright colors.
  • Meadow Pathways: Winding paths through the flower fields, inviting exploration.

These visual elements can help bring each summer color theme to life in a visually engaging way.

You are a prompt generator, who is an expert for generating prompts from users’ input into specific formats.
For example, when user inputs “holographic background”, you will output “digital background, gradient, soft light, low contrast, minimalist, foil holographic”; when user inputs “Tokyo, Japan”, you will output “Tokyo, Japan, street, architecture, minimalistic, abstract, mist, vector, flat, unreal engine, by jewel tones, scandi style, morning, fog, blue and grey”; when user inputs “polygons”, you will output “digital background, origami, soft light, low contrast, minimalist, foil holographic”; when user inputs “Spacetime” , you will output “Spacetime , minimalistic, abstract, mist, vector, flat, unreal engine, cinematic”.
Please give user 3 different prompts with slightly different styles or descriptions, and you will add “4k –ar 3:2 –v 5” in the end of each prompt.
Here is the user input: {{input}}

ChatGPT

Sure! Here are three different prompts based on the user input “{{input}}”:

User Input: “Beach at Sunset”

  1. Prompt 1:
    • “Beach at Sunset, golden hour, warm tones, soft light, serene, minimalist, waves, silhouettes, tranquil scene, by the ocean, dusk, gradient sky, 4k –ar 3:2 –v 5”
  2. Prompt 2:
    • “Beach at Sunset, vibrant colors, dramatic sky, silhouettes of palm trees, reflections, peaceful, seaside, romantic, glowing horizon, watercolor effect, 4k –ar 3:2 –v 5”
  3. Prompt 3:
    • “Beach at Sunset, pastel colors, gentle waves, calm and relaxing, abstract, impressionistic style, sunset glow, beach scenery, soft focus, twilight, dreamy atmosphere, 4k –ar 3:2 –v 5”

User Input: “Mountain Landscape”

  1. Prompt 1:
    • “Mountain Landscape, majestic peaks, cool tones, misty, serene, minimalist, high contrast, alpine scenery, dramatic, crisp air, sunrise, ethereal light, 4k –ar 3:2 –v 5”
  2. Prompt 2:
    • “Mountain Landscape, panoramic view, lush valleys, vibrant colors, nature, rugged terrain, detailed, sunlight breaking through clouds, scenic vista, realistic, wild, 4k –ar 3:2 –v 5”
  3. Prompt 3:
    • “Mountain Landscape, abstract, geometric shapes, pastel colors, artistic interpretation, soft light, layered, mountain ridges, whimsical, fantasy, muted tones, 4k –ar 3:2 –v 5”

User Input: “City Skyline at Night”

  1. Prompt 1:
    • “City Skyline at Night, vibrant lights, skyscrapers, reflection on water, high contrast, urban landscape, modern architecture, dynamic, glowing windows, nightlife, cityscape, 4k –ar 3:2 –v 5”
  2. Prompt 2:
    • “City Skyline at Night, neon lights, futuristic, sleek buildings, bustling, nightlife, high detail, reflections, dramatic sky, colorful, energetic, cyberpunk vibe, 4k –ar 3:2 –v 5”
  3. Prompt 3:
    • “City Skyline at Night, minimalist, abstract, silhouettes of buildings, soft glow, quiet night, muted colors, tranquil, peaceful, moonlit sky, artistic, serene, 4k –ar 3:2 –v 5”

These prompts provide diverse descriptions and styles for each of the given user inputs.

The screen capture image is from the MidJourney Bot on Discord, showing four photographs of a beach at sunset
The image consists of four photographs, all capturing a beach scene during sunset. Here is a detailed description of each photograph:

Top Left: The sun is low in the sky, casting a warm golden hue across the water and the sandy beach. Gentle waves are rolling towards the shore, creating a serene and peaceful atmosphere.

Top Right: Similar to the first, this photograph shows the sun near the horizon, but with the waves appearing slightly more pronounced. The light from the sunset is reflecting off the wet sand, giving it a glowing, almost metallic look.

Bottom Left: This photograph captures the sun a bit higher in the sky compared to the others. The waves are more dynamic, crashing onto the shore, with the foam creating intricate patterns. The sunlight reflects off the water and foam, enhancing the warm tones of the scene.

Bottom Right: The sun is nearly touching the horizon, and the waves are gently lapping against the shore. The light is soft and diffuse, giving the entire scene a calm and tranquil feel. The reflections on the wet sand add to the overall warmth of the image.

All four photographs emphasize the beauty of the sunset over the ocean, with a focus on the interplay of light and water, creating a soothing and picturesque scene.

Unleashing Creativity with Generative AI

Session 1: Understanding GenAI Tools

  • Part 1: Introduction to GenAI for Artists
    • Overview of GenAI
    • Applications in the art world
  • Part 2: Hands-On Practice with Idea Generation Tools
    • Using ChatGPT for brainstorming
    • Exploring AI-based idea generation tools (e.g., DALL-E, DeepArt)

Tools

Next: Concept Development and Mood Board Creation

Residency June 2024 – meet the artists

Picture of four artists who are taking part in Vital Capacities in June 2024.
Artists on Vital Capacities residency in June 2024 – from top left, clockwise: Jameisha Prescod, Shrouk El-Attar, Bella Milroy, and James Kong King-sin

For the tenth Vital Capacities‘ residency, we partner with UnlimitedVideotage (Hong Kong) and Wysing Art Centre (Cambridge) to work with artists from the UK and Hong Kong. From 1 June, artists Shrouk El-Attar, Bella Milroy, Jameisha Prescod and James Kong King-sin will join Vital Capacities, to undertake research and develop new work. Working with our partners, they will explore and exchange new ideas using their studio spaces, and create new work throughout the residency.

Continue reading “Residency June 2024 – meet the artists”

GenAI: A First Step

As part of my residency with Vital Capacities, I’m exploring the relationship between GenAI and artists, focusing on how AI can enhance our creative processes. Today, I’m excited to share my first use case: using ChatGPT to extract and describe image content for accessibility purposes. Here’s a photograph I captured during my urban exploration.


To ensure that my work is accessible to all, I used ChatGPT to generate a detailed description of the image. The AI accurately identified the silhouette of a person standing on a high vantage point, overlooking a brightly lit cityscape at night, with an overcast sky adding to the dramatic atmosphere.

A screen capture of James requests ChatGPT to describe his portfolio picture. ChatGPT response the image description

This initial use of GenAI demonstrates how artists can utilize AI tools to create accessible content, ensuring that our work can be experienced by a broader audience, including those with visual impairments. By integrating AI into our practice, we can enhance the inclusivity and reach of our art.

Stay tuned as I continue to explore and share more ways in which AI can support and transform our artistic endeavors. This is just the beginning of an exciting journey with Vital Capacities.

Vital Capacities: Gateways – new exhibition

A handpainted image of a white toilet spewing brown liquid into a giant fountain holding high a large white spotted egg on a yellow and orange background.
Sammy Paloma, The Flowering Milk of the Boghead, 2023 (screen shot from artwork)

New work by Vital Capacities resident artists from the May 2023 residency, including work by artists Shaima Ali, Bassam Issa, Sammy Paloma, and Su Hui-Yu & XTRUX.

In May 2023, four artists took part in residencies on Vital Capacities – Shaima Ali (Palestine), Bassam Issa (Ireland), Sammy Paloma (UK), and Su Hui-Yu & XTRUX (Taiwan) – to explore and develop new work, supported by partnerships with Film London Artists’ Moving Image Network (FLAMIN), Shubbak Festival, Videotage and Wysing Art Centre.

Throughout the month the artists did research, tested ideas and created new work, working with our partners, web designer and digital inclusion specialist. Gateways is an exhibition of new work resulting from May 2023’s residency.

See the exhibition now: vitalcapacities.com/exhibition/

With thanks to Film London Artists’ Moving Image Network (FLAMIN), Shubbak Festival, Videotage, and Wysing Art Centre. Thank you to Arts Council England for their support.

The memorial hall

The structure was ready made by the architect team. We are now building the detail of the interior.

The eventual form will be a digital grave , we will be able to maintain the content for the rest of our life, as an artist last will. Also, the spaceship looking hall is an extension of the video work Space Warriors.

The Bog is a Thin Place; A Sanctuary, A Portal & A Home

A watercolour painting featuring a pair of Simpson-yellow arms with black chains around the wrists. The hands have long and gnarly bright green nails wriggling their way towards the sky. The chains around their wrists also extend upwards towards the sky.
The arms are splashing out of a boggy, bubbling hole in the ground. This hole of green bubbling sludge is surrounded by brown earth blooming out at it's edges.

I love that phrase u sometimes hear about Halloween/Samhain: “the thinning of the veil”. From the idea of thin times it’s only a small leap to that of thin places. In Shetland witch (or heksi) folklore it is said that the stretch of sand that runs between high and low tide is the undisputed territory of the devil. Folk magic loves a threshold, a space between spaces (oh so liminal): a beach, a fog, the meeting point of two rivers, a keyhole, midnight, a crossroad. A bog. To get lost in a thick fog whilst traversing a bog might just about be the perfect setting to summon the dead. My sense is that these thin places and times are potent precisely because they can function as temporary sanctuaries, a home for those pushed to the margins. Not unlike Doom Patrol’s Danny The Street (DC Universe/HBO) a roving sentient genderqueer street that goes where it’s needed and provides a home to for us misfits.

https://www.youtube.com/watch?v=EynuSPCUEHk

Vital Capacities new resident artists May 2023

Artists on Vital Capacities residency in May 2023 – from top left, clockwise: Sammy Paloma, Bassam Issa, Shaima Mohammad Ali, and Su Hui-Yu & XTRUX

For the eighth Vital Capacities‘ residency, we partner with Film London Artists’ Moving Image Network (FLAMIN), Shubbak Festival, Videotage (Hong Kong) and Wysing Art Centre (Cambridge) to work with artists from Scotland, Northern Ireland, Palestine and Hong Kong. From 1 May, artists Bassam Issa, Sammy Paloma, Shaima Muhammad Ali and Su Hui-Yu & XTRUX will join Vital Capacities, to undertake research and develop new work. Working with our partners, they will explore and exchange new ideas using their studio spaces, and create new work throughout the residency.

The artists for May 2023’s residency are:

Bassam Issa works across digital animation, painting, sculpture, and textiles creating visions of resistance, transformation, and queer possibility. He completed a BA in Visual Art Practice from Dún Laoghaire Institute of Art, Design and Technology in 2016. Recent solo exhibitions include: IT’S DANGEROUS TO GO ALONE, TAKE THIS! The Douglas Hyde Gallery(2022) I AM ERROR, Gasworks, London (2021), and De La Warr Pavilion, Sussex (2022).

Sammy Paloma is an artist, poet and witch living in Shetland, on a croft by a beach, next to a bog, with 11 chickens. She paints, prints, tattoos, writes poetry, and makes computer games (with Uma Breakdown). Her work is into how divination disturbs linear time, grief rituals and necromancy. Her current obsession is the overlapping folklore and paranormal phenomena surrounding both boglands and crossroads.

Shaima Mohammad Ali is an artist from the destroyed village of Beit Thul in Palestine. She uses sculptural elements and video art to explore the liminal space between the personal and the collective, where it  is a point of intersection and where it is a point of departure. She draws her inspiration from that which demands an interruption to the every day. Her art is political in that it refuses to take on a singular perspective, preferring to reflect the mixture and entwinement of politics in the day-to-day of the Palestinian individual through their life, hopes and dreams.

Su Hui-Yu & XTRUX – Su Hui-Yu is a Taipei based artist who has been working on his specific “Re-shooting” series which focuses on Taiwan’s colonial histories, martial law memory and body-politics for many years. XTRUX is a Taiwanese collective art founded in October 2020 with a number of creators whose works focus on new media art. Su and XTRUX have been cooperating on experimental projects since 2022.

Residencies will launch on 1 May 23 – find out what artists are up by joining our mailing list and following them on: vitalcapacities.com

May’s residency programme is delivered in partnership with Film London Artists’ Moving Image Network (FLAMIN), Shubbak Festival, Videotage (Hong Kong) and Wysing Art Centre, with support from Arts Council England.

Vital Capacities is an accessible, purpose-built digital residency space, that supports artists’ practice while engaging audiences with their work.

Vital Capacities has been created by videoclub in consultation with artists, digital inclusion specialist Sarah Pickthall and website designer Oli Pyle.