Microsoft Copilot + Designer ✨​ Get Creative: Starting Out with Text to Image & DALL·E 3

AI Unplugged
26 Mar 202417:19

TLDRThe video script showcases the capabilities of Microsoft co-pilot, utilizing Open AI's Dolly 3 for text-to-image creation. The speaker, admitting to a lack of natural creativity, explores various prompts to generate images, emphasizing the importance of descriptive language and experimentation. The video highlights the transformation of simple text prompts into diverse and intricate images, demonstrating the potential of AI in the creative process and inspiring users to explore the possibilities of AI-assisted content creation.


  • 🌐 The speaker is using Microsoft Windows with Edge browser on to discuss text-to-image AI capabilities.
  • 🎨 AI, through Microsoft co-pilot and OpenAI's Dolly 3, enables creation of images from text inputs, aiding those who lack inherent creativity.
  • 📌 For effective text-to-image creation, one must be descriptive and specific to allow AI to better interpret and realize the envisioned concept.
  • 🎭 Referencing artists, styles, and art movements can guide the AI in generating the desired output.
  • 🧪 Experimentation is crucial; combining unusual elements can lead to surprising and innovative results.
  • 🖼️ Microsoft co-pilot offers various filters like pixel art, watercolor, block print, etc., to refine and personalize the images.
  • 🌟 The speaker emphasizes the importance of selecting 'gp4 creative' for creative content, as other options may not facilitate image creation.
  • 💡 AI's interpretation of spatial relationships and impossible forms showcases its advanced understanding and adaptability.
  • 🚀 The technology allows for the creation of custom, inspiring images beyond the limitations of traditional search engines.
  • 🌈 The session demonstrates the potential of AI in unlocking creative possibilities, even for those who consider themselves non-creative.

Q & A

  • What is the main topic of the video transcript?

    -The main topic of the video transcript is the exploration of text-to-image AI capabilities, specifically using Microsoft co-pilot and Open AI's Dolly 3 to create images from text descriptions.

  • Which platform is the speaker using to demonstrate text-to-image AI?

    -The speaker is using Microsoft Windows with the Edge browser to demonstrate text-to-image AI capabilities.

  • What is the significance of selecting 'gp4 creative' in Microsoft co-pilot for text-to-image creation?

    -Selecting 'gp4 creative' in Microsoft co-pilot is important for text-to-image creation because it allows the AI to generate images from text descriptions. The other options like 'fast', 'balanced', or 'precise' do not support image creation.

  • How does the speaker describe their own creative abilities?

    -The speaker describes themselves as not very creative, mentioning that they have tried various creative pursuits like drawing, painting, and playing musical instruments but found creativity to be outside their reach.

  • What is the speaker's advice for creating better images with text-to-image AI?

    -The speaker advises being descriptive with the language used in text prompts, as the more specific the language, the better the AI can interpret and create the desired image. They also suggest experimenting with unusual combinations of elements and referencing artists, styles, and artistic movements.

  • What is the role of Microsoft Designer in the text-to-image process?

    -Microsoft Designer is a brand that bundles creative features, including text-to-image capabilities, under the co-pilot umbrella. It provides a platform for creating, editing, and sharing images generated by AI.

  • What are some of the image filters or styles available in Microsoft Designer?

    -Some of the image filters or styles available in Microsoft Designer include original, pixel art, watercolor, block print, steampunk, claymation, Art Deco, low poly, and origami.

  • How does the speaker demonstrate the use of text-to-image AI in the video?

    -The speaker demonstrates the use of text-to-image AI by providing various prompts, such as 'a closeup photo of a butterfly with iridescent wings perched on a vibrantly colored wild flower' and 'a photorealistic portrait of an elderly woman with kind eyes', and then showcasing the images created by the AI based on these prompts.

  • What is the speaker's reaction to the images created by the AI?

    -The speaker is amazed and impressed by the images created by the AI, expressing excitement about the possibilities and potential of text-to-image AI technology.

  • What is the speaker's final takeaway or message about text-to-image AI?

    -The speaker's final takeaway is that text-to-image AI is a powerful and inspiring tool that can be used to create custom, beautiful, and creative images from just a few descriptive words, offering potential for both personal and professional use.



🎨 Introduction to Text-to-Image AI

The speaker introduces the topic of text-to-image AI, sharing their lack of natural creativity and excitement about the capabilities of AI in this field. They mention using Microsoft co-pilot with Open AI's Dolly 3 to create images and emphasize the importance of selecting the 'gp4 creative' option for generating images. The speaker also shares their initial experiences with text-to-image tools and provides tips for effective usage, such as being descriptive and experimental with language to better convey the desired image to the AI.


🌟 Exploring Microsoft Co-Pilot's Image Creation

The speaker dives into the process of creating images using Microsoft co-pilot, highlighting the animation and interactivity of the platform. They demonstrate how to apply different filters like low poly, origami, and steampunk to the images, and discuss the ability to edit and enhance the AI-generated content. The speaker expresses their admiration for the technology and its potential, showcasing the impressive results of creating photorealistic portraits and pixel art landscapes.


💡 Experimenting with Various Styles and Concepts

The speaker continues to experiment with text-to-image AI by creating images based on various styles and conceptual ideas. They explore creating a blueprint sketch of an impossible machine and a sculpture made entirely of clouds, emphasizing the AI's ability to understand and visualize complex and impossible forms. The speaker discusses the process of refining voice inputs for better results and the excitement of seeing the AI's interpretations of their prompts.


🚀 Final Thoughts on AI and Creativity

In the conclusion, the speaker reflects on the transformative potential of AI in the realm of creativity, expressing a sense of awe and excitement for the possibilities that text-to-image AI offers. They encourage viewers to explore and experiment with AI tools like Microsoft co-pilot to create custom and inspiring images for personal or professional use, highlighting the shift from searching for images to creating them through simple prompts.



💡text to image

The process of converting textual descriptions into visual images using AI technology. In the video, the speaker discusses their experience with text to image AI, specifically mentioning Microsoft co-pilot and its ability to generate images based on descriptive input.

💡Microsoft co-pilot

A tool developed by Microsoft that utilizes AI to assist users in various tasks, including text to image creation. The video emphasizes its use of OpenAI's Dolly 3 for generating images from text descriptions.

💡Dolly 3

An AI model from OpenAI that specializes in generating images from text descriptions. It is noted in the video as the underlying technology used by Microsoft co-pilot for its text to image functionality.


The use of imagination or original ideas to create something new. In the context of the video, the speaker expresses their lack of inherent creativity and explores how AI tools like text to image can help individuals overcome this limitation.

💡Google Imagine

A reference to Google's AI technology that also deals with generating images from text descriptions. The speaker mentions it as one of the other platforms they have experimented with for creating images.

💡image filters

Digital tools or effects that can be applied to images to alter their appearance in various ways, such as pixel art, watercolor, or steampunk styles. In the video, the speaker uses different filters provided by Microsoft co-pilot to modify the generated images.


The process of trying out new methods or ideas to see what works or to discover new possibilities. In the video, the speaker encourages viewers to experiment with different prompts and settings in Microsoft co-pilot to explore the potential of text to image AI.


A detailed account or representation of something in words. In the context of the video, a description refers to the textual input provided to the AI to generate a specific image.


A form of visual art that creates the illusion of motion through a sequence of images. In the video, the speaker appreciates the animation of the image creation process in Microsoft co-pilot, which visually represents the AI generating the image.


The act of modifying or adapting something to individual needs or preferences. In the video, the speaker discusses the ability of AI tools like Microsoft co-pilot to create customized images based on user-provided text descriptions.

💡impossible forms

Shapes or structures that defy the laws of physics or logic as we understand them. In the video, the speaker explores the AI's ability to conceptualize and visualize impossible forms, such as a sculpture made entirely of clouds.


The speaker is exploring text to image capabilities on Microsoft Windows using Edge and as a platform.

The speaker admits to not being very creative and shares their childhood attempts at various creative endeavors.

AI is enabling new capabilities in text to image conversion, which the speaker finds exciting and accessible despite their perceived lack of creativity.

Microsoft co-pilot utilizes Open AI's Dolly 3 for text to image creation, which the speaker finds incredible.

When using co-pilot for creative content, it is important to select the 'gp4 creative' option for the best results.

The speaker emphasizes the importance of being descriptive in language when providing text inputs for AI to interpret visions accurately.

Referencing artists, styles, and movements can help guide the output of the AI in creating images.

Experimentation with unusual elements is encouraged when working with text to image AI.

The speaker uses voice input to instruct Microsoft co-pilot to create an image of a butterfly on a wildflower, demonstrating the process.

Microsoft Designer is a brand that bundles creative features, including image filters like pixel art, watercolor, and origami.

The speaker expresses amazement at the creation of a photorealistic portrait of an elderly woman, showcasing the AI's ability to generate detailed and expressive images.

The AI's capacity to understand spatial relationships and create impossible forms is highlighted when the speaker asks for an image of a sculpture made of clouds.

The speaker is impressed by the variety of images generated, including pixel art, blueprint sketches, and steampunk renditions.

The potential of text to image AI for creating custom, creative content is discussed, offering possibilities beyond standard image searches.

The speaker shares their excitement for the future of using co-pilot and text to image for personal and professional purposes.

The transcript concludes with an encouragement for others to experiment with chatbots and text to image tools to unlock their own creativity.