Tutorial | Become AI Artist in 3 minutes !! | With Stable Diffusion + CivitAI Model | For anyone

Robin's Lab
8 Mar 202303:11

TLDRIn this tutorial, you'll learn how to become an AI artist in just three minutes using Stable Diffusion and the CivitAI model. Start by visiting the GitHub repository via the provided link and run the application on GPU, which will take approximately seven minutes. Once completed, access the web UI through the public URL. Next, download the 'Dolls mix' model from CivitAI, which is one of the presenter's favorites. After downloading, navigate to the 'Text to Image' page, refresh the model, and select 'Dolls mix'. Use the provided random prompt or customize it to your preference. Click 'Generate' to create your first AI art piece, which you can save if desired. To elevate your art, use the 'Image to Image' feature to increase the resolution to 1024x1024 and generate again. This quick and easy process will bring you joy and a sense of accomplishment as an AI artist. Stay tuned for more tutorials by subscribing to the channel.


  • 🎨 Start by visiting the GitHub repository using the provided link and run the application on GPU.
  • ⏱️ Allow approximately seven minutes for the initial setup and processing.
  • 🌐 Open the web user interface by clicking the public URL.
  • πŸ“š Download one of the favorite models from CivitAI, specifically the 'Dolls Mix'.
  • πŸ”„ After downloading, refresh the model on the text-to-image page and select 'Dolls Mix'.
  • πŸ“ Copy and paste the provided prompt or create your own to generate your AI art.
  • πŸ–ΌοΈ Click 'Generate' to produce your first AI art picture.
  • πŸ’Ύ Save your artwork if you are satisfied with the result.
  • πŸ‘©β€πŸŽ¨ To refine your art, use the image-to-image feature and adjust the resolution to 1024x1024.
  • πŸ”„ Generate the image again with the refined settings for a more polished piece.
  • πŸ“ˆ Learn the least to achieve the most joy from creating AI art.
  • πŸ”” Subscribe for more tutorials to continue learning and improving your AI art skills.

Q & A

  • What is the first step to becoming an AI artist using the Stable Diffusion and CivitAI Model?

    -The first step is to visit the GitHub repository using the provided link and click the button to run it on GPU.

  • How long does it take to run the AI model on GPU?

    -It takes about seven minutes to run the AI model on GPU.

  • What should you do after running the model on GPU?

    -You should click the public URL to open the web user interface.

  • Where can you download the Dolls mix model from?

    -You can download the Dolls mix model from CivitAI.

  • What is the purpose of the text-to-image page?

    -The text-to-image page is where you can input a prompt to generate an AI art picture.

  • What is the suggested prompt to use when creating AI art?

    -The prompt provided in the transcript is a random one, but you can type in any text you like to generate your AI art.

  • How do you generate the first AI art picture?

    -After pasting the prompt into the text-to-image page, select the Dolls mix model and click generate.

  • What can you do with the generated AI art picture?

    -You can save the generated AI art picture if you like it.

  • How can you refine the AI art picture to be more like an artist's work?

    -You can refine the AI art by sending it to the image-to-image page and changing its resolution to 1024 by 1024, then click generate again.

  • What is the benefit of learning the least thing mentioned in the transcript?

    -The least thing to learn mentioned in the transcript will bring you the most joy.

  • How can you stay updated with future tutorials?

    -You can subscribe to receive updates on future tutorials.

  • What is the role of the music in the transcript?

    -The music in the transcript serves as an audio backdrop to the tutorial, enhancing the overall experience.



🎨 Becoming an AI Artist in 3 Minutes

The video instructs viewers to become AI artists by accessing a GitHub repository and executing a specific button to run the process on a GPU, which is estimated to take around seven minutes. Afterward, the viewer is guided to open a web UI and download a preferred AI model from Civet AI. The model 'Dos Mix' is recommended. Once downloaded, the user is directed to the 'text to image' page, where they should refresh the model, paste a provided prompt, and then generate their first AI art picture. The process concludes with an option to save the artwork and further refine it by using an 'image to image' feature to adjust the resolution to 1024 by 1024 and generate the image again. The video ends with an encouragement to subscribe for future tutorials.



πŸ’‘AI Artist

An AI Artist refers to an individual who uses artificial intelligence to create art. In the context of the video, it is someone who utilizes AI models to generate artwork, such as images or designs, without the need for traditional artistic skills. The video aims to teach viewers how to become AI Artists by using specific tools and models.

πŸ’‘Stable Diffusion

Stable Diffusion is a term in the video that likely refers to a type of AI model or technology used for generating images from textual descriptions. It is a core component in the process of creating AI art, as it enables the transformation of text prompts into visual art pieces, which is central to the video's tutorial.

πŸ’‘CivitAI Model

CivitAI Model is a specific AI model mentioned in the video that is used for creating images from text prompts. It is one of the tools that the video instructs the audience to download and use in order to generate AI art. The model is part of the process that turns textual descriptions into AI-generated images.

πŸ’‘GitHub Repo

GitHub Repo stands for a repository on GitHub, which is a platform for version control and collaboration that allows developers to work on projects together. In the video, the GitHub repo is the source from which viewers are instructed to access and run a certain application or script to begin the AI art creation process.


GPU stands for Graphics Processing Unit, which is a type of processor designed for handling complex mathematical and geometric calculations involved in rendering images, videos, and animations. In the context of the video, running an application on GPU implies that it will be processed more efficiently, which is crucial for the intensive computations required by AI art generation.

πŸ’‘Web UI

Web UI stands for Web User Interface, which is the visual and interactive part of a web application that allows users to interact with the software. In the video, the public URL is clicked to open the Web UI where users can input their text prompts and generate AI art.

πŸ’‘Text to Image

Text to Image is a process where AI takes a text description and generates an image that represents the description. It's a key concept in the video as it describes the primary function of the AI model being used. The viewer is guided to use this feature to create their first piece of AI art.


In the context of AI art generation, a Prompt is a text input that guides the AI in creating a specific image. The video provides a prepared prompt for the viewers to use, but it also encourages them to create their own prompts, allowing for a wide range of creative possibilities.


Generate in this context refers to the action of creating or producing something, particularly an image, using the AI model. The viewer is instructed to 'click generate' after inputting their prompt to produce the AI art, which is a fundamental step in the process.


Resolution is the measure of the amount of detail an image can show, typically measured in pixels. In the video, the resolution is set to 1024 by 1024, which means the generated image will have 1024 pixels in both width and height. This step is part of refining the AI art to make it more detailed.

πŸ’‘Image to Image

Image to Image is a process where an existing image is used as input to generate a new, transformed image. In the video, this process is suggested for refining the AI art by changing its resolution and regenerating it, which can enhance the quality and appearance of the final artwork.


Become an AI artist in just three minutes using Stable Diffusion and CivitAI Model.

Access the GitHub repository through the provided link.

Run the AI model on GPU for an approximate seven-minute processing time.

Open the web UI by clicking the public URL.

Download the 'Dolls mix' model from CivitAI, a favorite among AI artists.

Refresh the text to image page after the model has been downloaded.

Select the 'Dolls mix' model for your AI art creation.

Craft a unique prompt to generate your first AI art picture.

Generate your AI art by clicking the 'Generate' button.

Save your AI art if you are satisfied with the result.

Refine your AI art by using the image to image feature.

Change the resolution to 1024 by 1024 for higher quality output.

Generate the refined AI art for a more polished look.

Learn the least to gain the most joy from AI art creation.

Subscribe for future tutorials to stay updated with the latest in AI art.

The tutorial is designed for anyone interested in AI art creation.

The process includes both text to image and image to image transformations.

The tutorial provides a step-by-step guide for beginners to create AI art.

The use of the 'Dolls mix' model is highlighted for its creative potential.

The final AI art can be saved and further refined for professional quality.