{"id":159142,"date":"2025-03-27T06:03:51","date_gmt":"2025-03-27T06:03:51","guid":{"rendered":"https:\/\/peraltafinancing.com\/entertainment\/art\/features-wombo-dream-and-ai-art-with-salman-shahid\/"},"modified":"2025-03-27T06:03:51","modified_gmt":"2025-03-27T06:03:51","slug":"features-wombo-dream-and-ai-art-with-salman-shahid","status":"publish","type":"post","link":"https:\/\/fivemor.com\/?p=159142","title":{"rendered":"FEATURES \u2013 WOMBO Dream and AI Art with Salman Shahid"},"content":{"rendered":"


\n<\/p>\n

\n

Do AI dream of electric sheep? Yes, if we tell them to.<\/p>\n

In fact, the electric sheep can look something like this:<\/p>\n

Electric Sheep. <\/em>Created by Annie Truuvert with WOMBO Dream.<\/figcaption><\/figure>\n

These sheep were created by Dream<\/a>, an app by WOMBO<\/a> that uses artificial intelligence (AI) to generate intricate works of art. The user simply enters a prompt (or picks from Dream\u2019s suggestions, like \u201cFuturistic City,\u201d \u201cCrawling Brains,\u201d or \u201cDiamond Trees\u201d), and selects an art style, like Dali, Fantasy, Ukiyo-e, or Steampunk. Then, they watch in real time as Dream creates an artwork based on these inputs. Users are so thrilled with their creations that vibrant communities have sprung up on social media and Discord, where they eagerly share their \u201cdreams.\u201d <\/p>\n

\u201cI\u2019m a big fan of Italian Renaissance art,\u201d Dream engineer Salman Shahid tells me in an interview, \u201cand I think the first time I saw The School of Athens<\/em>, I was just mesmerized. I asked WOMBO Dream what it thinks The School of Athens<\/em> looks like in the Synth Wave style. That was pretty cool.\u201d<\/p>\n

\"A<\/a>
School of Athens.<\/em> Created by Salman Shahid with WOMBO Dream.<\/figcaption><\/figure>\n

Since joining the WOMBO team in July, Shahid has worked on the machine learning models of both of WOMBO\u2019s applications: Dream, released in late 2021, and the company\u2019s first app, WOMBO, which animates a user\u2019s photo to lip sync a song of their choice. The team includes application designers, content creators, product managers, mobile and web app engineers, and AI engineers, like Shahid.<\/p>\n

\u201cWe really value democratizing creativity using AI,\u201d Shahid says. \u201cWe work on abstracting away the complexity and bringing really cool AI models to millions of users across the globe.\u201d<\/p>\n

The Dream algorithm uses a CLIP-guided approach. CLIP is an open-source neural network (a freely available algorithm that learns about patterns in data) by research lab OpenAI. The network is trained on image-caption pairings found on the internet, and can rate how well user-fed captions pertain to images.<\/p>\n

To generate its artworks, the Dream model starts with a randomly-generated vector, a mathematical representation of an image. Each entry in the vector corresponds to a tiny detail of the image. Some might correspond to colour, some to shape, some to more abstract meaning. Often, the random vector first corresponds with a grey blob of pixels. The algorithm then uses CLIP to ascertain how well the current vector image corresponds to the user\u2019s prompt and improves the correspondence over several iterations. The user watches the algorithm conduct this process in real time; the app creates multiple images before the final product appears. The randomness of the process means that Dream never produces the same artwork twice.<\/p>\n

I ask Shahid why the app is called Dream. He says that the team cycled through a few different names, including \u201cPaint\u201d and \u201cArt,\u201d before settling on \u201cDream.\u201d \u201cWe found it was a playful interpretation of how we believe AI dreams\u2026. [The] internal representation is not something we specifically guide, where we say that one attribute should refer to one specific thing. It\u2019s just something that the model learns during its training time\u2026. The vector itself is not human-readable in any sense.\u201d<\/p>\n

\"A<\/a>
Satan\u2019s dream house, flemish baroque. <\/em>Created by Twitter user @baileyurban2 with WOMBO Dream. This image is one of Shahid\u2019s favourite creations, and the winner of Dream\u2019s first contest.<\/figcaption><\/figure>\n

WOMBO Dream recently expanded to offer multilingual support. Its model can now take prompts in a vast array of languages, including Japanese, Hindi, and Indonesian. In addition to offering more languages, the app will soon offer social features, such as the ability to see and \u201clike\u201d other users\u2019 dreams if they choose to share them. The team is also experimenting with 3D animations of dreams so that users could walk through the dreams they create in virtual reality.<\/p>\n

While playing with different art styles in the app, I found myself returning to Etching and Baroque. Etching seemed to essentialize the prompts, creating simple pieces with a nightmarish quality. Baroque, on the other hand, dazzled with convincing brushstrokes and the colour palette of the period.<\/p>\n

\n