Type a rough description of a scene and it will generate a short video matching this text. Google Imagen Video and Nvidia Align Your Latents are similar concepts.
Graeme Fulton explores how photo stocks work with generated images. New products like Prompt Hero & GhostlyStock emerge, while classic companies are taking little steps: Shutterstock partners with DALL-E 2, Adobe Stock opened submissions with limitations (you can't copy an existing style). Another review by Alina Valyaeva.
This text prompt-based generator can refine photos & images.
It helps to generate 3D objects for virtual worlds. You can get a whole series of cars, animals, furniture, or other items that are varied, but still a part of a family.
The tool creates realistic photos and illustrations from a text description based on GPT-3. It started simple, but then became one of the hottest movements. Its simplified version exploded into a meme generator (see also Wordle mashup). There are prompt generators for better results (more like that), although these personal explorations (another one) are amazing. There are similar concepts like Google Imagen or Disco Diffusion. Professional illustrators discuss risks & possibilities, but not all of them are worried. Microsoft put a serious bet on it and included DALL-E into Azure Cloud.
Abstract art generator via text prompt. It's one of the most spectacular and it's launched before DALL-E-like models.
These faces are actually generated, not just tweaked real photos of people. It's a major privacy risk — researchers backtracked photos from a popular face generator to find original people.
Stas Kulesh made a plugin that puts AI-generated faces into design mockups. It's a great application of a popular idea. Here's also a website (see similar websites for cats and rentals). Caution: researchers backtracked these photos to find original people (see the research paper).
A tool by a comic book publisher can stylize any photo into their visual style.
Loading...
