Create Your Own AI Art In MINUTES | DreamStudio Full Introductory Course (2023 New UI)

Darren Yeo - Reviews, Tech & Tutorials
9 Apr 202363:30

TLDRThe video provides an in-depth walkthrough of using DreamStudio's new user interface and the stable diffusion XL beta model for generating AI art. The host demonstrates various features, including different models, style filters, and prompt options. They explore the ability to generate images in batches without waiting, adjust prompt strength for closer adherence to the input, and manipulate generation steps for more detailed images. The video also touches on advanced settings like negative prompts to avoid unwanted elements and the option to upload personal images for unique effects. The host shares their experience with generating different styles of art, such as anime, sci-fi, and photorealistic landscapes, and discusses the potential of using AI-generated images as reference for traditional art pieces. The summary highlights the ease of creating diverse and compelling artwork with the platform, as well as the creative possibilities it offers to artists and designers.


  • 🎨 The user is exploring the new UI of DreamStudio, an AI art generation platform, which allows for the creation of AI art in minutes.
  • 🔍 DreamStudio has incorporated Stable Diffusion XL beta, enabling users to select different models and adjust parameters for image generation.
  • ⚙️ The platform offers advanced settings such as prompt strength and generation steps, which affect the detail and adherence to the prompt in the generated images.
  • ✅ Users can upload images and apply various styles and filters, creating unique effects and potentially useful for artists looking for inspiration.
  • 🖼️ The generated images can be used as reference photos for artists, especially for complex scenes that are difficult to find or create.
  • ➡️ The user demonstrates the ability to generate different styles of art, including anime, sci-fi, and photorealistic landscapes, by adjusting the prompts and styles in DreamStudio.
  • 🌟 DreamStudio's image generation is fast and allows for simultaneous generation of multiple batches, an improvement over previous versions.
  • 📈 The user highlights the importance of experimenting with different prompt weightings and styles to achieve desired results.
  • 🧩 The platform's ability to generate images from simple text prompts opens up possibilities for creating artwork, designs, and even emojis.
  • 🌍 The user also discusses the generation of cityscapes and landscapes, noting that some locations like Venice seem to produce more accurate and recognizable results.
  • ⚖️ There is a concern about the accuracy and authenticity of the generated scenes, as they may not perfectly reflect real-world locations.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is about using DreamStudio, an AI art creation tool, to generate images with the new user interface and the stable diffusion XL beta model.

  • What are some of the new features in the latest version of DreamStudio mentioned in the video?

    -Some of the new features include the ability to select different models, change parameters for image generation, apply various style filters to prompts, and shuffle prompts for new ideas.

  • How does the user interface of the new DreamStudio version differ from the old one?

    -The new user interface has a different look on the left-hand side console, and it allows for faster image generation, simultaneous processing of multiple image batches, and more control over image parameters.

  • What is the purpose of the 'prompt strength' setting in DreamStudio?

    -The 'prompt strength' setting determines how much the final image will portray the user's prompts, with higher numbers resulting in less extrapolation and a closer resemblance to the input prompts.

  • How does the video creator use DreamStudio for their artwork?

    -The video creator uses DreamStudio to generate ideas for different art pieces to paint, particularly as a watercolor artist, by creating reference photos for landscapes, portraits, and other scenes.

  • What are some of the styles and filters that can be applied in DreamStudio?

    -Some of the styles and filters that can be applied include pen and ink drawing, anime, photographic, low poly, pixel art, comic book, and origami, among others.

  • How does the video demonstrate the process of generating images in DreamStudio?

    -The video demonstrates the process by showing the user interface, selecting different models and styles, inputting prompts, adjusting settings like prompt strength and generation steps, and displaying the resulting images.

  • What is the advantage of being able to generate multiple batches of images simultaneously in DreamStudio?

    -The advantage is that users do not have to wait for one batch of images to finish generating before starting another, which saves time and allows for more efficient use of the tool.

  • How does the video address the issue of generating images with additional or incorrect limbs in previous models?

    -The video mentions that the issue has been improved in the new models, and there is a feature to add negative prompts, which can reduce the likelihood of generating images with additional limbs.

  • What are some of the potential uses for the images generated by DreamStudio?

    -Potential uses for the generated images include creating reference photos for paintings, designing 3D models, generating ideas for sci-fi art, and producing images for personal or commercial projects without worrying about copyright issues.

  • How does the video creator evaluate the quality and realism of the generated images?

    -The video creator evaluates the quality and realism by looking at the details, the handling of light and shadow, the accuracy of the subject matter, and the potential for the images to be used as reference material or in artistic projects.



🎨 Exploring Dream Studio and Stable Diffusion XL Beta

The speaker discusses their experience using the new version of Dream Studio with the Stable Diffusion XL Beta. They highlight the updated user interface, the ability to select different models, and the enhanced parameter customization. The speaker also mentions the faster image generation and the new features like various style filters and the 'Shuffle prompt' button. They demonstrate the process of generating images with different styles and settings, emphasizing the improved user experience and the potential for generating multiple image batches simultaneously.


🖼️ Customizing Image Generation with Advanced Settings

The speaker delves into the advanced settings of the image generation tool, discussing options like prompt strength, which determines how closely the final image resembles the input prompt, and generation steps, which affects the level of detail in the image. They share their experiments with high prompt strength and numerous generation steps, noting the increased detail and the trade-off in credits required. The speaker also talks about applying different filters, like anime and photographic styles, and uploading an image to generate creative effects.


🌌 Generating Sci-Fi and Fantasy Artwork

The speaker explores the capabilities of the tool in generating sci-fi and fantasy-themed artwork. They mention using different styles like 'low poly', 'origami', and 'fantasy art' to create unique designs. The speaker appreciates the tool's ability to generate images that could be used as reference photos for painting, especially noting the value in the shadows and scenery details for creating art pieces.


🎭 Experimenting with Styles and Generating Realistic Images

The speaker continues to experiment with various styles, including 'analog film' and 'neon Punk', to generate a diverse set of images. They discuss the tool's ability to create images with a cyberpunk aesthetic and its handling of light and color. The speaker also attempts to generate images of famous landmarks like Venice and the Charles Bridge in Prague, noting the need for accuracy and the potential for using these images as artistic references.


🌃 Generating Cityscapes and Landscapes

The speaker focuses on generating cityscapes and landscapes, mentioning the desire to create reference photos for personal artwork. They experiment with prompts like 'Venice photo realistic' and discuss the impressive results, including the detailed reflections and shadows. The speaker also attempts to generate images with different orientations and styles, highlighting the potential for customization and the challenges in achieving accurate representations.


🤖 Creating Sci-Fi and Anime-Style Images

The speaker experiments with generating sci-fi and anime-style images, using prompts like 'Blade Runner City' and various styles to achieve different aesthetics. They discuss the potential for using these images in artistic projects and the importance of refining prompts for better results. The speaker also shares their experience with uploading personal images and applying filters to create unique versions of themselves in different styles.


🌐 Using Lexicon for Inspiration and Building Prompts

The speaker introduces another website, Lexicon, as a tool for finding inspiration and building prompts for image generation. They demonstrate how to use Lexicon to generate a variety of images, including landscapes, portraits, and abstract art. The speaker emphasizes the importance of experimenting with different prompts and styles to spark creativity and find the desired outcome. They also provide links in the video description for further resources on prompt building.




DreamStudio is an AI art creation platform that allows users to generate images based on textual prompts. In the video, the user discusses their experience with the new user interface and features of DreamStudio, highlighting its ability to adjust parameters and generate images quickly, which is central to the video's theme of exploring AI art generation.

💡Stable Diffusion

Stable Diffusion refers to a set of AI models used in DreamStudio for generating images. The video mentions different versions of Stable Diffusion, such as 2.1 and 1.5, and the XL beta version, which are significant as they determine the style and quality of the generated images. The user compares these models to demonstrate their capabilities in creating various art styles.

💡Prompt Strength

Prompt strength is a parameter in DreamStudio that determines how closely the final image will adhere to the user's textual prompt. A higher prompt strength means the generated image will more closely resemble the prompt, with less extrapolation. The user discusses adjusting prompt strength to achieve different levels of detail and adherence to their input.

💡Generation Steps

Generation steps refer to the number of times an image is sampled during the AI's image creation process. More steps can lead to more accurate and detailed images, but they also consume more credits within the DreamStudio system. The user experiments with varying the number of generation steps to observe its impact on image quality.

💡Filters and Styles

Filters and styles are options within DreamStudio that allow users to apply specific visual effects or themes to their generated images. The user explores various filters and styles, such as 'anime', 'photorealistic', and 'low poly', to create different types of art, demonstrating the versatility of AI in mimicking various artistic styles.

💡Negative Prompt

A negative prompt is a feature in DreamStudio that enables users to specify elements they do not want in the generated image. This tool helps refine the AI's output by reducing unwanted features, such as additional limbs or certain objects. The user mentions using negative prompts to improve the accuracy of the generated images.

💡Image Orientation

Image orientation refers to the layout or positioning of elements within the generated image. The user discusses the ability to change the orientation in some versions of Stable Diffusion, which is important for creating images that fit specific compositional requirements, such as landscape or portrait formats.


Credits are the virtual currency used within DreamStudio to generate images. They are consumed based on the complexity of the image generation process, such as the number of generation steps or the use of certain filters. The user mentions the cost of credits in relation to the number of images they can generate.

💡AI Art

AI art is the broader term for artwork created or influenced by artificial intelligence. The video is centered around the creation of AI art using DreamStudio, showcasing the capabilities of AI in generating images that can be used as references for traditional art or as standalone digital art pieces.


Lexica is another AI art tool mentioned in the video that the user employs to generate images with specific styles and themes. It serves as an example of how different AI platforms can be used to create a variety of artistic outputs, contributing to the video's exploration of AI's role in the art creation process.


Introduction to the new user interface of DreamStudio with the stable diffusion XL beta.

Capability to select different models in DreamStudio for varied image generation styles.

Faster image generation and parameter adjustments in the new DreamStudio version.

New style filters and prompt options for more creative control.

Shuffle prompt feature for quick generation of diverse prompts.

Simultaneous image generation without waiting for the previous batch to finish.

Advanced settings like prompt strength and generation steps for detailed image control.

Option to upload an image and apply various prompts for unique effects.

Use of DreamStudio for generating art piece ideas and reference photos.

Negative prompt feature to avoid unwanted elements in the generated images.

Different styles demonstrated, including anime, neon Punk, and analog film.

Generating photorealistic, low-poly, and pixel art styles with ease.

The ability to refine and adjust prompts for better results in stable diffusion.

Creating images with a digital art style that have intricate details and a futuristic touch.

Experimenting with the photographic style to generate realistic and detailed images.

Using DreamStudio to generate complex cityscapes and landscapes for artistic reference.

The potential use of generated images as stock photographs with minor post-processing.

DreamStudio's ability to generate images across various artistic styles, including origami and fantasy art.

The convenience of generating images with specific themes like Blade Runner-style cities.