How to Create AI Art for Free – Beginners Guide


If you click on a link and make a purchase, I may receive a small commission. As an Amazon affiliate partner, I may earn from qualifying purchases.
Read our disclosure.

Key Takeaways

  • Choose a free AI art generator to create images using artificial intelligence and text prompts.
  • Decide between text-to-image and image-to-image AI art generation methods.
  • Select an AI art style from various AI art generators and models that match your preferences.
  • Be aware of hardware and software requirements if you plan to use Stable Diffusion locally.
  • Craft detailed or simple text prompts to guide the AI art generator, adjusting creative freedom.
  • Understand AI art generator features like inpainting, outpainting, checkpoint models, and techniques like Dreambooth to improve your AI art.

Choose a Free AI Art Generator

Image generated using the Dream Shaper SDXL checkpoint model. Image credits.

To create AI art, you need to choose an AI art generator. AI art generators are software applications that use artificial intelligence and various components, such as machine learning and neural networks, to generate images autonomously.

There are two primary ways to create AI art:

  • Text-to-image: You write a text prompt (words that describe what kind of image you want the generator to create) to the AI art generator.
  • Image-to-image: You upload an image to the AI art generator, write a text prompt, and the AI will generate an image that will take elements from the text and the image to generate a new image.

Best free AI art generators:

Check out: How is AI art made

Choose an AI Art Style

Different AI art models (diffusion models) and AI art generators excel in different AI art styles. Some AI art models and generators are excellent for generating realistic/photographic-style images, while some generators and models are great at producing anime art, for example.

Pick the AI art style you are after and choose an AI art model or an AI art generator based on that decision.

Check out:

Hardware & software requirements for using Stable Diffusion locally

If you choose to use Stable Diffusion (local installation) as your free AI art generator, there are system and software requirements you need to meet.

Minimum system requirements for Stable Diffusion:

  • CPU: Any AMD or Intel processor.
  • RAM: At least 16GB, preferably the latest DDR memory available.
  • GPU: Any GeForce RTX GPU that has at least 8GB memory.
  • Storage: Preferably any SSD drive with at least 200GB of storage space.
  • OS: Mac, Windows, or Linux

Stable Diffusion software requirements

To run Stable Diffusion, you need the following files:

Learn to Write Text Prompts

Text prompts determine what kind of image the AI art generator generates. The more defined, specific, and detailed your prompt is, the better results you can expect from the generator.

The text prompt can be highly detailed and specific, or it can be simple and non-specific. Using wildcards can randomize the output of the AI art generator.

Example of a detailed text prompt and the result

Example image that was generated using a very detailed text prompt. ZavyChromaXL checkpoint model (trained with SDXL base model). Image credits.

Normal text prompt: used

shattered mirror, reflect, girl’s face, cinematic shot + dynamic composition, incredibly detailed, sharpen, details + intricate detail + professional lighting, film lighting + 35mm + anamorphic + lightroom + cinematography + bokeh + lens flare + film grain + HDR10 + 8K + Roger Deakins, ((cinematic))

Negative text prompt used:

((3d, cartoon, anime, sketches)), (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), bad anatomy, out of view, cut off, ugly, deformed, mutated, ((young)), EasyNegative, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans,extra fingers,fewer fingers, (ugly eyes, deformed iris, deformed pupils, fused lips and teeth:1.2), (un-detailed skin, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.2), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck,, Watermark, Text, censored, deformed, bad anatomy, disfigured, poorly drawn face, mutated, extra limb, ugly, poorly drawn hands, missing limb, floating limbs, disconnected limbs, disconnected head, malformed hands, long neck, mutated hands and fingers, bad hands, missing fingers, cropped, worst quality, low quality, mutation, poorly, close up, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, blur, drawn, huge calf, bad hands, fused hand, missing hand, disappearing arms, disappearing thigh, disappearing calf, disappearing legs, missing fingers, fused fingers, abnormal eye proportion, Abnormal hands, abnormal legs, abnormal feet, abnormal fingers

Example of a simple text prompt and the result

Example image of what a simple text prompt can create. Image created with Lexica AI art generator. Image credits.

Normal text prompt used:

A human-mouse rogue in médiéval fantaisie clothes

The fewer words you have in the text prompt, the more creative freedom you give to the AI art generator. The more detailed you are with your text prompt, the less creative freedom the generator has, but at the same time, the more likely it will generate the image you want it to create.

Check out: The best Stable diffusion prompts (can be used with any AI art generator, excluding Midjourney)

Negative text prompts

  • Negative prompts remove objects, items, or things from the image generation.
  • Negative prompts can be used to modify the image for a more accurate result.
  • The first words have the biggest effects, and the later words are for fine-tuning the text prompt.
  • You can emphasize negative text prompts with brackets.

Negative prompts help you fine-tune the image to include only things you want to see in the image. Negative text prompts also help modify the image to have a certain style (crisp, clear, purple, etc.) and also to help correct usual mistakes such as disfigured hands, extra fingers, extra hands, ugly eyes, etc.

AI art generators are still in their infancy, and they always make mistakes. While you can get fantastic results by using just the normal text prompt, sometimes the AI adds things to the image that you haven’t specified in the text prompt.

This is the reason why negative text prompts are so effective. These text prompts help you further define what you don’t want to see in the image.

Understand AI Art Generators Features

AI art generators have a lot of features that you might want to get familiar with. Understanding different features will improve the image generation results as well as give you more creative control over AI.


Inpainting is a technique used in Stable Diffusion image editing to restore and edit missing or damaged portions of pictures. Inpainting has been used to reconstruct deteriorated images, eliminating imperfections like cracks, scratches, disfigured limbs, dust spots, or red-eye effects from AI-generated images.

Instead of solely repairing missing portions of a generated image, this technique allows for creating entirely new content within any desired area of an existing picture.


Outpainting is a technique that allows you to expand images beyond their original borders using artificial intelligence (AI) and text prompts.

With outpainting, you can create new elements or scenes outside the original picture by generating content that matches the art style and colors of the existing image. The more of the original image the outpainting frame covers, the better the match will be.

For example, suppose your original image size is 512px x 512px. You can increase the image size with outpainting (to something like 1024px x 512px) and continue generating visuals while keeping the original content in place.

Checkpoint models

Image created with SDXL_Niji_V5.1 checkpoint model. Image credits.

A checkpoint model is a pre-trained Stable Diffusion weight, also known as a checkpoint file (.ckpt). A CKPT file is a checkpoint file created by PyTorch Lightning, a PyTorch research framework. The checkpoint – or .ckpt – format stores and saves models. The .ckpt file contains the entire model, typically several GBs in size.

A Checkpoint model is used to create AI (artificial intelligence) art, and the output depends on the training dataset on which the checkpoint model was trained.

The checkpoint model can’t generate cat images if the training dataset does not include images of a cat or cats. This is why you need to choose an AI art generator specifically for your needs and wants.

Below are the different types of models you can find online:

Dreambooth training

Dreambooth is a technique to fine-tune diffusion models, specifically Stable Diffusion, by incorporating a custom subject into the model.

The core concept of Dreambooth:

  • It uses a unique identifier for the new subject ([V] dog could be named XYK-3), so it does not have a previous meaning inside the model.
  • Corresponding class refers to the subject in hand. In our case, the dog represents the class, so Dreambooth is fine-tuned so that XYK-3 is used while generating an image of a dog (class).

To start the training process, you need the following things:

  • Custom images
  • A unique identifier
  • A class name


If you choose to create AI art with a locally installed AUTOMATIC1111 WebUI, some extensions can improve how you create AI art. Extensions enhance the features and capabilities of the base diffusion model. Useful extensions to try out are Dreambooth, wildcards, and ControlNet.

Improving AI Art Generation

Becoming an AI artist requires you to learn new skills, such as text prompting and English language skills. When you understand how text prompts work and how to write good prompts, it’s also good practice to understand art fundamentals to spot mistakes in AI-generated images.

AI art is by no means perfect and actually quite far from it. AI art looks good, but it has mistakes here and there. Understanding light and shadow, perspective, color theory, etc., helps you improve your AI art, as you can better guide the algorithm with your text prompts.

Studying text prompts and understanding the underlying AI art model helps you create better AI art, and when you are ready, you can train your own AI art model for specific and unique results.

Tools to improve your AI art:

  • ControlNet: If you are using Stable Diffusion, you can use a tool like ControlNet to control the subject poses and even do semantic segmentation.
  • Adobe Creative Cloud: When your image is generated with AI tools, you can further improve and fix the quality of your artwork with tools like Adobe Photoshop and Adobe Illustrator.
  • Kittl: When you are thinking of selling AI art, Kittl is a powerhouse that you can use to create merchandise-ready designs.
  • Install Stability’s Photoshop plugin to further adjust generated images.

Feature image credits.



Digital Artist

I’m a digital artist who is passionate about anime and manga art. My true artist journey pretty much started with CTRL+Z. When I experienced that and the limitless color choices and the number of tools I could use with art software, I was sold. Drawing digital anime art is the thing that makes me happy among eating cheeseburgers in between veggie meals.

More Posts

Thank You!

Thank you for visiting the page! If you want to build your next creative product business, I suggest you check out Kittl!