DALLE 2 Tutorial on How to Use all the Editing and Image Features!

1 Mar 202317:12

TLDRThe video script offers a detailed tutorial on using Dolly, an AI art creation tool. It explores the process of inputting prompts to generate images, selecting and refining them through variations, and utilizing editing features. The creator shares mixed results, noting impressive accuracy in some outputs, while pointing out inaccuracies and potential copyright issues in others. The review highlights Dolly's user-friendly interface, quick generation times, and the provision of free credits, but also acknowledges its limitations and the need for further development before it's ready for commercial use.


  • 🎨 The Dolly AI platform generates images from text prompts, catering to both beginners and advanced art creators.
  • πŸ–ΌοΈ Users can input a prompt and receive four image options, selecting the one closest to their vision and further customizing it.
  • πŸ“š Dolly provides variations of the selected image, allowing users to refine their choices and explore more options.
  • πŸ’‘ The platform features an edit tool that enables users to manipulate images, including zooming, panning, and adding new elements.
  • πŸ”„ Dolly's 'generation frame' allows users to combine multiple generated images into a single cohesive piece of art.
  • 🚫 The AI sometimes struggles with accuracy, particularly with complex prompts or specific details like hands.
  • πŸ’° Users receive a monthly allotment of free credits, with the option to purchase more for advanced features or additional image generations.
  • πŸ“Έ Dolly discourages the use of copyrighted art, and its AI learns from existing artworks, which raises potential copyright concerns.
  • 🚫 The platform has limitations, such as restrictions on using celebrity images, which may hinder certain content creation needs.
  • 🌐 Despite its current limitations, Dolly's AI capabilities are impressive, offering quick and user-friendly image generation with potential for future growth.
  • πŸ‘€ The video creator anticipates that as AI art platforms evolve, they may become integral to various professional fields and their business models.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is a comprehensive tutorial on using Dolly, an AI art creation platform.

  • How does the Dolly interface work?

    -The Dolly interface works by prompting users to input a text description, which the AI then uses to generate an image.

  • What kind of image did the user request Dolly to create?

    -The user requested Dolly to create an image of an angry gorilla eating the planet Mars, with a monkey watching in the distance.

  • How does Dolly handle variations of the generated images?

    -Dolly generates four images based on the user's prompt and allows the user to select the closest match to their request. The user can then ask for more variations or edit the chosen image.

  • What are the collection and favorites features in Dolly?

    -The collection feature allows users to organize their images into groups, while the favorites feature lets them mark certain images for easy access in the future.

  • What is the credit system in Dolly?

    -Users are given a monthly allowance of credits to use for free. Each image generation uses a certain number of credits, and users need to purchase more credits if they run out.

  • What are some of the limitations the user noticed when using Dolly?

    -The user noticed that Dolly sometimes neglects parts of the prompt, produces raw or abstract images that don't fully align with the request, and has difficulty with detailed elements like hands.

  • How did the user feel about the accuracy of Dolly's image generation?

    -The user felt that while Dolly was extremely impressive in some cases, it was not always accurate and still needed refinement, especially in understanding specific prompts and handling detailed elements.

  • What is the edit feature in Dolly used for?

    -The edit feature allows users to make adjustments to the generated images, such as moving, zooming, and adding new elements through generation frames.

  • What are some of the pros and cons of using Dolly mentioned in the video?

    -Pros include user-friendliness, speed, and the ability to create realistic images. Cons include occasional inaccuracies, the inability to use celebrity images, and the potential for future cost increases.

  • What is the future outlook for Dolly according to the user?

    -The user believes that Dolly has the potential to become a premier AI art platform, but it is still in its early stages and will likely evolve and improve over time.



🎨 Introduction to Dolly AI Art Creation

The paragraph introduces the audience to the Dolly AI platform, emphasizing its capability to transform text prompts into images. It discusses the user interface, the process of inputting a prompt, and the AI's ability to generate images based on the given text. The creator tests the platform by asking it to create an image of an angry gorilla eating Mars while a monkey watches, and shares the results, highlighting the AI's ability to sometimes produce accurate and other times neglect certain elements of the prompt. The paragraph also touches on the selection and variation features of the platform, allowing users to refine their search and generate more tailored images. Additionally, it explains the concept of credits, which are used to generate images and can be earned for free or purchased if depleted.


πŸ–ŒοΈ Dolly AI's Limitations and Potential Misinterpretations

This paragraph delves into the limitations and occasional misinterpretations by the Dolly AI. The creator provides examples of how the AI sometimes produces raw and unspecific outputs that do not align with the prompts given, such as a sloth playing chess against a rabbit being depicted as a rabbit playing against itself. The paragraph also discusses the AI's struggle with hands and its tendency to borrow elements from copyrighted artworks, raising concerns about potential legal issues. The creator shares their own experiences with the platform, noting that while some prompts yield impressively accurate results, others fall short, particularly when it comes to more complex or specific requests. The paragraph concludes with the creator's opinion that Dolly AI is not yet ready for commercial use, despite its impressive speed and raw capabilities.


πŸ› οΈ Exploring Dolly AI's Editing and Frame Features

The paragraph focuses on the editing and frame features within the Dolly AI platform. The creator demonstrates how to use the pan, zoom, and generation frame tools to manipulate and combine images. They show how the AI can fuse different images together to create a single cohesive piece of art, and how the eraser tool can be used to edit parts of an image. The creator also shares their nostalgia for the way the platform allows for the combination of AI-generated and real-life captured images, drawing parallels with their grandfather's stamp collections. They highlight the user-friendly nature of Dolly AI, its speed, and its potential for both personal and commercial use, while also noting the platform's current affordability and the availability of free credits.


πŸš€ Conclusion and Future Prospects of Dolly AI

In the final paragraph, the creator summarizes their thoughts on Dolly AI, acknowledging its current limitations but also recognizing its potential for future growth. They mention the platform's restrictions on using celebrity images and express their frustration with this policy, especially considering the importance of famous figures in content creation. The creator encourages viewers to keep an eye on the platform's development, as they believe it could become a leading AI art platform. They conclude by expressing their anticipation for future tutorials on various AI software platforms and remind viewers to stay tuned for more content, emphasizing the evolving nature of AI technology and its potential impact on various industries.




Dolly is an AI platform that generates images based on text prompts provided by users. It is the central focus of the video, demonstrating its capabilities in creating and editing images. The video showcases how Dolly interprets various prompts, such as creating an image of an 'angry gorilla eating Mars' and how it sometimes fails to meet the exact requirements of the prompt, like neglecting to include a 'monkey watching in the distance'.

πŸ’‘AI brain

The term 'AI brain' refers to the artificial intelligence algorithms and computational processes that Dolly uses to interpret text prompts and generate corresponding images. It symbolizes the intelligence and decision-making capabilities of the AI, which are crucial to the creative output.


Variations in the context of the video refer to the different iterations or modifications of an initially generated image that Dolly can produce based on user selection and further input. This feature allows users to refine their requests and explore different creative possibilities.

πŸ’‘Collections and Favorites

Collections and Favorites are organizational features within Dolly that enable users to categorize, save, and easily access their previously generated images. Collections could be thematic groupings of images, while Favorites would be a way to mark and quickly return to particularly important or appealing images.


In the context of Dolly, credits are a form of virtual currency that users consume to generate images. The number of free credits provided per month limits the amount of usage, and once depleted, users must purchase additional credits to continue using the service.

πŸ’‘Copyrighted Art

Copyrighted Art refers to creative works that are legally protected by copyright laws, which means they cannot be used without permission from the copyright holder. The video raises concerns about Dolly potentially using elements from copyrighted artworks in its generated images, which could lead to legal issues.

πŸ’‘Realistic Imagery

Realistic Imagery refers to the creation of images that closely resemble real-life objects, scenes, or people. In the context of the video, it highlights the capability of Dolly to generate images that look like they could have been taken by a camera or closely imitate a specific artistic style.


Inaccuracy in the video refers to the instances where Dolly's generated images do not align with the user's prompt or intended concept. This could manifest in various ways, such as incorrect depictions of subjects or misinterpretations of the requested theme.

πŸ’‘Edit Feature

The Edit Feature in Dolly is a tool that allows users to modify their generated images after they have been created. This includes functions like adding new elements, adjusting the composition, and using an eraser tool to remove or alter parts of the image.


User-Friendliness refers to the ease with which users can navigate and use a software or platform. In the context of the video, it highlights Dolly's accessible interface and straightforward processes for generating and editing images, making it suitable for a wide range of users, from beginners to experienced content creators.

πŸ’‘Content Creation

Content Creation involves the production of various forms of digital content, such as images, videos, and text, for the purpose of communication, marketing, or artistic expression. The video discusses how Dolly can be utilized in content creation, despite some of its limitations.


The tutorial covers the comprehensive use of Dolly, an AI art creation tool, accessible to both beginners and advanced users.

Dolly generates images from text prompts, using its AI to visualize the input.

An example prompt of an 'angry gorilla eating Mars' demonstrates the AI's ability to create unique images based on user input.

Dolly's interface allows users to select the most accurate image from a set of four generated by the AI.

The 'variations' feature enables users to refine their image selection by generating additional images based on the chosen one.

Users can create collections and favorites for easy access to frequently used or significant images.

The 'credits' system allows users to generate images for free up to a monthly limit, after which users must purchase more credits.

Dolly sometimes produces raw or inaccurate images that do not fully align with the user's request.

The AI's ability to generate realistic images, like a Picasso painting of a homeless man, is impressive and appreciated.

Dolly's struggle with accurately depicting hands and its tendency to add extra fingers or thumbs is noted.

The 'edit' feature allows users to modify images, including the use of tools like pan, zoom, and content-aware fill.

The 'generation frame' feature enables users to add new elements to an image, such as a Dilophosaurus at an EDM concert.

Dolly's capacity to fuse multiple images together seamlessly is showcased.

The platform's potential for commercial use is discussed, with considerations of its current limitations and future potential.

Dolly's user-friendly interface, accuracy, and speed are praised, but its limitations in editing and accuracy are also acknowledged.

The inability to use celebrity images due to policy restrictions is seen as a drawback for content creators.

The video creator expresses optimism for Dolly's future development and its potential to become a leading AI art platform.