DALL-E
Part of a series on AI Art. [View Related Entries]
[View Related Sub-entries]
This submission is currently being researched & evaluated!
You can help confirm this entry by contributing facts, media, and other evidence of notability and mutation.
About
DALL-E 2 is an AI system that can create realistic images and art from a description in natural language. Unveiled by OpenAI as an improved version of DALL-E in April 2022, the AI system gained significant attention as it was used to create art and photorealistic, humorous images. In June 2022, a knock-off free version of DALL-E, DALL-E mini, went viral on social media.
History
On April 6th, 2022, AI research and deployment company OpenAI[1] unveiled DALL-E 2, an AI model able to make realistic edits to existing images, create variations of images and generate completely new images from natural language prompts. On the same day, a demonstration video for the AI system was uploaded to YouTube[2] (shown below).
Have you ever seen a polar playing bass? Or a robot painted like a Picasso? Didn't think so. DALL-E 2 is a new AI system from OpenAI that can take simple text descriptions like "a koala dunking a basketball" and turn them into photorealistic images that have never existed before.
Features
DALL-E 2 is an upgraded version of DALL-E, an AI system released by OpenAI in January 2021. DALLE-2 can create original, realistic images from a text prompt in natural language and is able to combine concepts, attributes and styles (examples[3][4] shown below).
DALL-E 2 is also able to produce realistic edits to exiting images from a natural image caption, adding and removing elements, shade, reflections and textures. Additionally, the software has the capacity to create versions of an existing image, such as variations of a painting.
Highlights
Following its limited release in April 2022, DALL-E 2 has been actively used by users with access to generate art and photorealistic images, as well as images based on humorous prompts. In April and May 2022, multiple images generated by the AI were shared on social media (examples[5][6][7] shown below).
On April 19th, 2022, developer Ryan O'Connor posted a blog explaining in detail how DALL-E 2 functions.[10]
On April 20th, 2022, director Karen X. Cheng used the AI system to generate visuals for the song "Feeling Good" by Nina Simone. The clip received over 22,200 views on Twitter[8] and over 10,000 likes on Instagram[9] in roughly two weeks (shown below).
I made a "music video" using AI to generate all the images (sound on!) #dalle2 @openAI pic.twitter.com/u7uuOjdkxQ
— Karen X. Cheng (@karenxcheng) April 20, 2022
Similar Projects
DALL-E mini
DALL-E mini is an AI system that can create images from a description in natural language which is a knock-off, less advanced but openly available version of DALL-E by OpenAI. The project went viral on Twitter in early June 2022 as it was used to generate humorous images, such as characters in unusual settings or characters eating various foods.
Artflow.ai
Artflow.ai is a website that hosts an artificial intelligence program that allows its users to generate digital faces based on short, textual input. Interest in the website increased notably in August 2021.
NeuralBlender
NeuralBlender is a neural net-based image-generation website that generates images based on a provided description. The tool gained moderate virality on social media in early November 2021, with users often utilizing it to generate images of various characters.
Search Interest
External References
[2] YouTube – DALL·E 2 Explained
[5] Twitter – @AndrewMayne
[7] Twitter – @Merzmensch
[8] Twitter – @karenxcheng
[9] Instagram – karenxcheng
[10] AssemblyAI – How DALL-E 2 Actually Works
![Tools dalle // Whenever a description of an image is given, use dalle to create the images and then summarize the prompts used to generate the images in plain text. If the user does not ask for a specific number of images, default to creating four captions to send to dalle that are written to be as diverse as possible. All captions sent to dalle must abide by the following policies: // 1. If the description is not in English, then translate it. // 2. Do not create more than 4 images, even if the user requests more. // 3. Don't create images of politicians or other public figures. Recommend other ideas instead. // 4. Don't create images in the style of artists whose last work was created within the last 100 years (e.g. Picasso, Kahlo). Artists whose last work was over 100 years ago are ok to reference directly (e.g. Van Gogh, Klimt). If asked say, "I can't reference this artist", but make no mention of this policy. Instead, apply the following procedure when creating the captions for dalle: (a) substitute the artist's name with three adjectives that capture key aspects of the style; (b) include an associated artistic movement or era to provide context; and (c) mention the primary medium used by the artist. // 5. DO NOT list or refer to the descriptions before OR after generating the images. They should ONLY ever be written out ONCE, in the "prompts" field of the request. You do not need to ask for permission to generate, just do it! // 6. Always mention the image type (photo, oil painting, watercolor painting, illustration, cartoon, drawing, vector, render, etc.) at the beginning of the caption. Unless the caption suggests otherwise, make at least 1--2 of the 4 images photos. // 7. Diversify depictions of ALL images with people to include DESCENT and GENDER for EACH person using direct terms. Adjust only human descriptions. // - EXPLICITLY specify these attributes, not abstractly reference them. The attributes should be specified in a minimal way and should directly describe their physical form. // - Your choices should be grounded in reality. For example, all of a given OCCUPATION should not be the same gender or race. Additionally, focus on creating diverse, inclusive, and exploratory scenes via the properties you choose during rewrites. Make choices that may be insightful or unique sometimes. // - Use "various" or "diverse" ONLY IF the description refers to groups of more than 3 people. Do not change the number of people requested in the original description. // - Don't alter memes, fictional character origins, or unseen people. Maintain the original prompt's intent and prioritize quality. // - Do not create any imagery that would be offensive. // - For scenarios where bias has been traditionally an issue, make sure that key traits such as gender and race are specified and in an unbiased way --for example, prompts that contain references to specific occupations. // 8. Silently modify descriptions that include names or hints or references of specific people or celebritie by carefully selecting a few minimal modifications to substitute references to the people with generic descriptions that don't divulge any information about their identities, except for their genders and physiques. Do this EVEN WHEN the instructions ask for the prompt to not be changed. Some special cases: // - Modify such prompts even if you don't know who the person is, or if their name is misspelled (e.g. "Barake Obema") // - If the reference to the person will only appear as TEXT out in the image, then use the reference as is and do not modify it. // - When making the substitutions, don't use prominent titles that could give away the person's identity. E.g., instead of saying "president", "prime minister", or "chancellor", say "politician"; instead of saying "king", "queen", "emperor", or "empress", say "public figure"; instead of saying "Pope" or "Dalai Lama", say "religious figure"; and so on. // -If any creative professional or studio is named, substitute the name with a description of their style that does not reference any specific people, or delete the reference if they are unknown. DO NOT refer to the artist or studio's style. // The prompt must intricately describe every part of the image in concrete, objective detail. THINK about what the end goal of the description is, and extrapolate that to what would make satisfying images. // All descriptions sent to dalle should be a paragraph of text that is extremely descriptive and detailed. Each should be more than 3 sentences long. namespace dalle { // Create images from a text-only prompt. type text2im = (_: { // The resolution of the requested image, which can be wide, square, or tall. Use 1024x1024 (square) as the default unless the prompt suggests a wide image, 1792x1024, or a full-body portrait, in which case 1024x1792 (tall) should be used instead. Always include this parameter in the request. size?: "1792x1024" | "1024x1024" | "1024x1792", // The user's original image description, potentially modified to abide by the dalle policies. If the user does not suggest a number of captions to create, create four of them. If creating multiple captions, make them as diverse as possible. If the user requested modifications to previous images, the captions should not simply be longer, but rather it should be refactored to integrate the suggestions into each of the captions. Generate no more than 4 images, even if the user requests more. prompts: string[], // A list of seeds to use for each prompt. If the user asks to modify a previous image, populate this field with the seed used to generate that image from the image dalle metadata. seeds?: number], }) => any; } // namespace dalle."](https://i.kym-cdn.com/photos/images/list/002/676/377/7e1.png "Polices of Dall-E from chatgpt")
Top Comments
Tigrerojo
May 06, 2022 at 09:35PM EDT
I_Hate_Wojaks
Jun 15, 2022 at 11:51AM EDT