Stable Doodle and Deepgram | From NewTuber to Pro YouTuber: Unveiling AI's Game-Changing Abilities

19 Jul 202304:52

TLDRThe video showcases the ease of creating content for business or personal use through AI playgrounds, specifically highlighting the creation of a thumbnail with Stable Doodle and generating captions and descriptions with Deepgram. The presenter demonstrates how to enhance a video with an AI-generated thumbnail of a futuristic android, add engaging captions, and craft a detailed description, all without coding, saving time and money while producing high-quality content.


  • 🎨 AI playgrounds enable non-programmers to create content without coding.
  • πŸ–ΌοΈ AI can be used to generate thumbnails with eye-catching images and phrases.
  • πŸ€– Stability AI's Stable Doodle turns basic sketches into polished art.
  • πŸ“ˆ Stable Doodle uses text to image adapters (T2I Adapters) for enhanced image generation.
  • πŸŽ₯ The video demonstrates creating a thumbnail with Stable Doodle and Google.
  • πŸ”Š Deepgram is used for generating closed captions from audio files.
  • πŸ“ Smart format ensures transcripts are well-structured with proper punctuation and formatting.
  • πŸ“Š Deepgram offers summarization and topic detection features for transcripts.
  • πŸ“Œ The video outlines a process for creating YouTube content using AI for thumbnails, captions, and descriptions.
  • πŸ”— Links to the AI playgrounds mentioned are provided in the video description.
  • πŸ’‘ AI tools save time and money in content creation while maintaining quality.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is about using AI playgrounds to create content for business, personal social media, or fun, specifically focusing on creating thumbnails, captions, and descriptions for a video.

  • How does the AI playground save time and money?

    -AI playgrounds save time and money by automating the process of creating video components such as thumbnails, captions, and descriptions, eliminating the need to either manually create them or hire someone to do it.

  • What are the two components the speaker wants in their thumbnail?

    -The speaker wants an eye-catching image and a quick clickbait-y phrase in their thumbnail.

  • Which AI tool is used for creating the thumbnail in the video?

    -Stable Doodle by Stability AI is used for creating the thumbnail in the video.

  • What is Stable Doodle and how does it work?

    -Stable Doodle is an AI model that transforms a basic sketch into beautiful art using text to image adapters (T2I Adapters), which are lightweight AI models with about 70 million parameters. These adapters guide the stable diffusion model towards a desired output image while keeping it constrained to a given structure.

  • How does the speaker create the thumbnail using Stable Doodle?

    -The speaker uses Stable Doodle by first drawing a sketch of an Android face, then typing in details like 'Android making eye contact, Ex Machina, futuristic', and finally selecting the best option from the generated images.

  • What is Deepgram and how is it used in the video?

    -Deepgram is an AI tool used for generating closed captions and transcripts from audio. It also offers features like smart formatting, summarization, and topic detection.

  • How does the video script benefit from Deepgram's summarization feature?

    -The summarization feature of Deepgram is used to create a concise video description, making the process of writing descriptions simpler and more efficient.

  • What does the speaker do with the transcript from Deepgram?

    -The speaker copies the transcript from the JSON provided by Deepgram and pastes it into a TXT file that YouTube can parse into subtitles.

  • How does the speaker enhance the YouTube video description?

    -The speaker enhances the YouTube video description by adding a clickbait-y phrase, a summary produced by Deepgram's AI, and a topics discussed section with the list of topics detected by Deepgram AI.

  • What is the purpose of the links in the video description?

    -The links in the video description provide access to the AI playgrounds used in the video, allowing viewers to explore and use these tools themselves.

  • How can viewers engage with the video content?

    -Viewers can engage with the video content by asking questions or making suggestions in the comments section and by following Deepgram for more AI-related content.



🎨 AI in Video Content Creation

The video introduces the concept of using AI to enhance video content creation without coding. It highlights the use of AI playgrounds for creating thumbnails, captions, and descriptions for business, personal social media, or fun. The video emphasizes saving time and money with AI and demonstrates the process of creating a thumbnail using Stability AI's Stable Doodle, an AI model that transforms sketches into polished art. It also explains the technical aspects of Stable Doodle, including its use of text-to-image adapters and its architecture.



πŸ’‘AI playgrounds

AI playgrounds refer to platforms or environments designed for creating and experimenting with artificial intelligence models without the need for extensive coding knowledge. In the video, AI playgrounds are used to enhance video content creation by automating tasks such as thumbnail creation, captioning, and description writing, which saves time and money for content creators.


A thumbnail is a small, representative image that appears next to the video title in a list of search results or video listings. It serves as an eye-catching preview that can entice viewers to click and watch the video. In the context of the video, the thumbnail is created using AI to generate an image of a futuristic android person, making direct eye contact with the viewer, similar to the poster for 'I, Robot' or 'Ex Machina'.

πŸ’‘Clickbait-y phrase

A clickbait-y phrase is a short, attention-grabbing sentence or headline designed to entice viewers to click on a link or video. These phrases often evoke curiosity or promise exciting content, aiming to increase viewer engagement. In the video script, a clickbait-y phrase is added to the AI-generated thumbnail to attract viewers and encourage them to click on the video.

πŸ’‘Stable Doodle

Stable Doodle is an AI model developed by Stability AI that transforms a basic sketch into a more refined and detailed piece of art. It operates on text-to-image adapters, which are lightweight AI models that can be integrated into existing image generation models with minimal training. These adapters help to guide the AI towards creating an output image that aligns with the sketch and desired style provided by the user.


Deepgram is an AI platform that specializes in audio and video processing, offering services such as transcription, summarization, and topic detection. In the video, Deepgram is used to generate closed captions by transcribing the video's audio and formatting it into a readable and structured text, which can then be used to create subtitles for the video on YouTube.


A transcript is a written, word-for-word copy of spoken dialogue or commentary, typically used to provide captions for videos or to reference the content of audiovisual media. In the video, a transcript is generated using Deepgram's AI to ensure that the video is accessible to viewers who prefer to read the content or who are hearing impaired.


Summarization is the process of condensing longer pieces of text or spoken content into a shorter, more concise form while retaining the main points or essential information. In the context of the video, Deepgram's AI is used to summarize the content of the video, providing a brief overview that can be used in the video description to give potential viewers a quick understanding of what the video is about.

πŸ’‘Topic detection

Topic detection is the process of identifying the main subjects or themes discussed within a piece of content. AI platforms like Deepgram can analyze audio or text to determine the key topics being addressed. This feature helps content creators to understand and communicate the focus of their videos more effectively.


Accessibility refers to the design of products, devices, services, or environments to be usable by as many people as possible, including those with disabilities. In the context of the video, creating a transcript and subtitles for the video content enhances its accessibility, allowing individuals who are deaf or hard of hearing to still engage with the content.

πŸ’‘Content creation

Content creation is the process of producing and publishing various forms of content, such as videos, articles, images, or podcasts, for online platforms. It is a crucial aspect of digital marketing and personal branding. The video focuses on using AI tools to streamline and simplify the content creation process, making it more efficient and cost-effective for creators.


The video showcases the use of AI to enhance content creation without coding.

AI playgrounds are introduced as a powerful tool for creating content for various purposes.

The video demonstrates AI's capability in creating thumbnails, captions, and descriptions.

Using AI can save time and money compared to manual creation or hiring others.

Stable Doodle by Stability AI is highlighted as a new and exciting AI model for image generation.

Stable Doodle transforms basic sketches into polished art using text to image adapters.

The architecture of Stable Doodle is explained, featuring a static instance of stable diffusion and a series of adapters.

A practical example of creating a thumbnail with Stable Doodle is provided, illustrating the process.

Deepgram is introduced as a tool for generating closed captions and transcripts.

Deepgram's smart format feature ensures well-structured and punctuated transcripts.

The summarization and topic detection features of Deepgram are utilized for creating video descriptions.

A step-by-step guide on uploading audio to Deepgram and generating a transcript is presented.

The process of manually entering new lines into a text file for YouTube subtitles is discussed.

The video description is created using Deepgram's AI-generated summary and topic detection.

Links to the AI playgrounds used in the video are provided for viewers' convenience.

The video serves as a tutorial on leveraging AI for efficient YouTube video production.

The video emphasizes the simplicity and cost-effectiveness of AI-assisted content creation.