How To Get Started Creating Images With AI

5 min readMar 18, 2023

To learn how to use AI art generators, you need to consider your current level of knowledge and experience in both art and technology. Below are general steps to follow:

Research: Read articles and watch videos that explain the technology behind AI art generators to understand how they work and what they’re capable of.

Choose a tool: Pick an AI art generator that appeals to you and start experimenting with it.

Start small: Begin by creating simple images with the AI art generator to understand the tool’s basic features and how to use them effectively.

Practice: The more you practice, the more comfortable you’ll become with the tool. Experiment with different images and settings until you’re confident in your ability to use the generator.

Join online communities: Join online communities where artists and technologists discuss AI art generators and share their work for valuable insights and feedback.

Attend workshops: If possible, attend workshops or conferences where you can learn more about AI art generators from experts in the field.

Remember, learning how to use AI art generators is an ongoing process. Keep experimenting, practicing, and exploring new ideas to continually improve your skills.

There are several popular AI art generators that have gained popularity in recent years. Here are a few:

Deep Dream Generator — Deep Dream Generator allows users to upload their own images and apply various styles and filters to create AI-generated art. It is one of the most popular AI art platforms available.

ArtBreeder — ArtBreeder uses AI to create new art by mixing different images and styles. Users can upload their own images or use the ones provided by the platform to create unique artworks.

RunwayML — RunwayML is a platform that allows users to experiment with various AI models to create unique art and designs. It offers a wide range of tools and models for users to explore.

Here are the three most popular based on my experience…

Mid-journey, Jasper, and DALL-E. They are all language models developed by OpenAI, but they have different capabilities and purposes.

Mid-journey is a language model that can generate coherent and meaningful text from a given prompt. It was specifically designed to generate creative and engaging product descriptions for e-commerce websites.

Jasper is a language model that can answer questions and provide explanations on a wide range of topics. It was designed to understand natural language queries and provide accurate answers in a conversational manner.

DALL-E is a language model that can generate images from textual descriptions. It was designed to create novel and diverse images based on textual inputs, such as “an armchair in the shape of an avocado.”

While all three models use natural language processing, they have different strengths and purposes. Mid-journey is optimized for generating product descriptions, Jasper for answering questions, and DALL-E for generating images.

My advice is to start with DALL-E. It’s free and relatively easy to use. And don’t let that fool you. DALL-E is a powerful AI tool that can generate highly detailed and realistic images from textual descriptions. To learn how to create art images using DALL-E, you can follow these steps:

*Familiarize yourself with the DALL-E interface and capabilities. You can read the original research paper or explore DALL-E demos online to get a sense of how the system works. (

*Identify the type of art images you want to create. DALL-E can generate a wide range of images, from surreal landscapes to detailed objects and animals. It’s helpful to have a clear idea of the type of image you want to generate before starting.

*Write a textual description of the image you want to create. DALL-E works by generating images from textual prompts, so you’ll need to write a detailed description of the image you want to create. The more specific and detailed your description is, the better the resulting image will be.

*Use a DALL-E interface to generate your image. There are several online tools that allow you to generate DALL-E images, such as GPT-3-based text editors or pre-built interfaces. You can also build your own interface using the DALL-E API.

*Iterate and experiment. Generating DALL-E images can be an iterative process, as the system may not always generate the exact image you want on the first try. Experiment with different textual prompts and parameters to fine-tune your results.

*Spend time practicing. Like any skill, generating DALL-E images takes practice and experimentation. Keep generating images and refining your techniques to develop your skills and produce high-quality art images.

Here’s a prompt template for generating art images using DALL-E AI and an example:

Choose a concept or theme: Start by choosing a concept or theme for your art piece. This could be anything from a specific object or animal to a mood or feeling.

Define the parameters: Next, define the parameters for your image. This could include the size of the image, the color scheme, and any specific details or elements you want to include.

Write your prompt: Write a prompt that describes your concept or theme, along with any specific parameters you’ve defined. Make sure your prompt is clear and concise, so that the DALL-E AI can accurately interpret your request.

Generate your image: Use the DALL-E AI to generate your art piece based on the prompt you’ve provided. You may need to experiment with different prompts or adjust your parameters to get the desired result.

Example Prompt Template

Concept: A surreal landscape with floating houses


Size: 1920x1080 pixels
Color scheme: muted blues and greens with pops of pink and orange
Houses: 5–7 small, cottage-style houses that appear to be floating in the air
Landscape: Rolling hills and trees in the background
Prompt: “Create a surreal landscape with floating houses, using a muted color scheme of blues and greens with pops of pink and orange. Include 5–7 small cottage-style houses that appear to be floating in the air, set against a backdrop of rolling hills and trees.”

Here’s a set of possible results based on the aforementioned prompts, just for illustration purposes.


I have spent months practicing with this technology and still feel like I’ve only taken the first step on a journey of 1000 steps. I am often happy with what I create but at first I almost gave up because I didn’t feel like I was getting anywhere.

You can use this tech to mash up your existing photos, to create backgrounds, for compositing or just for compositional ideas (think of it as a sketch pad.) Really, however you want to use it just give it a try. Don’t be afraid of it. If I can do it anyone can do it.

I am rooting for you.

For a list of my toy photo gear and props go to:

Follow me on Instagram:




I'm a toy photographer. I'm also delving into AI Art. I also help people get the most out of their Fuji X100 series cameras. (C) 2023