I wrote about a Twitch channel called Nothing Forever that consisted of completely AI generated dialog and animation.
Fast forward and someone has given Spongebob the same treatment. The dialog is generated by AI, the voices synthesized, and animations generated – automatically. You can even suggest things via the discord channel. It can get really strange and random, so don’t expect anything deep.
Jay Alammar does a reasonably good job describing how AI generated art works. I wouldn’t call it comprehensive, but worth it if you’re interesting in more of how the details work. He also has a decent write up from the video on his github site.
AI is not only for just generating new images, it can also help you enlarge your original images by filtering missing details intelligently while upscaling.
Note that most of these ‘free’ applications will scrape and can use any image you upload for whatever purposes they want – so I wouldn’t upload anything sensitive on them.
Rekkie started making smart snow goggles that have a heads-up digital data display that projects data at the top of your view area. I wouldn’t call these augmented reality since the goggles are simply overlaying data without being aware of what you’re looking at.
OpenAI announced on Tuesday the release of its newest picture-making machine POINT-E, which can produce 3D point clouds directly from text prompts. Existing systems like DreamFusion typically require multiple hours — and GPUs — to generate their images, Point-E only needs one GPU and a minute or two. Paper here, and code here.
Links:
DALL-E 2 beta now provides an open API which allows users to embed the ability to generate new images from text prompts or edit existing images in their own apps.
Microsoft is already leveraging it in Bing and Microsoft Edge with its Image Creator tool, which lets users create images if web results don’t return what they’re looking for. Fashion design app CALA is using the DALL-E 2 API for a tool that allows customers to refine design ideas from text descriptions or images, while photo startup Mixtiles is bringing it to an artwork-creating workflow.
Pricing for the DALL-E 2 API varies by resolution. For 1024×1024 images, the cost is $0.02 per image; 512×512 images are $0.018 per image; and 256×256 images are $0.016 per image. Volume discounts are available to companies working with OpenAI’s enterprise team.
Link:
There have been numerous attempts to make Stable Diffusion plugins for Adobe Photoshop. Many are not well baked nor free at this point but some are worth taking a look at.
KerasCV is another implementation of stable diffusion. It offers some interesting features that makes it one of the fastest implementations of stable diffusion:
jit_compile=TrueCheck out this setup, feature walkthrough, and comparison guide.
It appears several folks have gotten stable diffusion to work on the new Mac M1 (and M2’s). This is one of the really big advantages of a unified memory architecture in which the CPU and GPU can access the same memory without needing to be transported across a PCI bus first.
Links