A new method developed by researchers uses multiple models to create more complex images with better understanding. With the introduction of DALL-E, the internet had a collective feel-good moment. This artificial intelligence-based image generator is inspired by artist Salvador Dali and the lovab
A sample DALL·E 2 generated image of “an astronaut riding a horse in a photorealistic style.” Credit: Open AI
It is not a small task to get said smiling gopher and attributes to pop up on your screen. DALL-E 2 uses something called a diffusion model, where it tries to encode the entire text into one description to generate an image. However, once the text has a lot more details, it’s hard for a single description to capture it all.
This array of generated images, showing “a river leading into mountains” and “red trees on the side,” was generated using a new method developed by MIT researchers. Credit: Image courtesy of the researchers Researchers were able to create some surprising, surreal imagery with the text, “a dog” and “the sky.” On the left appear a dog and clouds separately, labeled “dog” and “sky” underneath, and on the right appear two images of cloud-like dogs with the label, “dog AND sky,” underneath. Credit: Image courtesy of the researchers
Now that Composable Diffusion can work on top of generative models, such as DALL-E 2, the researchers are ready to explore continual learning as a potential next step. Given that more is usually added to object relations, they want to see if diffusion models can start to “learn” without forgetting previously learned knowledge — to a place where the model can produce images with both the previous and new knowledge.
Canada Latest News, Canada Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
AI-designed Apple Car concept shows how it could stand out from TeslaAn industrial designer has just designed a gorgeous Apple Car using artificial intelligence-backed software DALL-E 2.
Read more »
Woman Horrified To Discover Her Private Medical Photos Were Being Used To Train AIAn AI artist unexpectedly discovered that private medical photos from over ten years ago were included in the AI training image database LAION.
Read more »
Citing Murky Copyright Territory, Getty Images Bans A.I.-Generated Art | Artnet NewsThe global image bank Getty Images said that selling A.I. art may unwittingly end up putting users at legal risk.
Read more »
AI-designed Apple Car concept shows how it could stand out from TeslaAn industrial designer has just designed a gorgeous Apple Car using artificial intelligence-backed software DALL-E 2.
Read more »