Community Picks·4yTurn anyone into a pokémon with this AI art model
The model is the work of machine learning researcher Justin Pinkney, who’s built a number of visual AI tools and resources. A quick search on Twitter shows people have been using Text-to-Pokémon to make all sorts of mash-ups, including Goku, Sonic the Hedgehog, and Jesus H. Christ himself.
Hacker News·4yStable Diffusion is a really big deal
Stable Diffusion is a new ‘text-to-image diffusion model’ that was released to the public by Stability.ai six days ago. You can download and run the model on your own computer (if you have a powerful enough graphics card) You can use it for commercial and non-commercial purposes, I’m personally more concerned with the morality.
Hacker News·3yStable Diffusion 2.0 Release — Stability.Ai
The Stable Diffusion 2.0 release includes robust text-to-image models trained using a brand new text encoder (OpenCLIP), developed by LAION with support from Stability AI, which greatly improves the quality of the generated images compared to earlier V1 releases.
The Register·4yOpenAI opens its doors to DALL-E text-to-image service
OpenAI opens its doors to DALL-E, its cloud service for generating images from text prompts, available to the public without any waitlist. The original service debuted in January 2021 and was superseded by Dall-E 2 this April. OpenAI justified the closed list by citing the need to be cautious.
Changelog·4yAUTOMATIC1111/stable-diffusion-webui: Stable Diffusion web UI
Stable Diffusion web UI a browser interface based on Gradio library for Stablediffusion. Features include images, art by Greg Rutkowski, original txt2img and img2img modes. You need python and git installed to run this, and an NVidia videocard. You can, through command line arguments, enable the various optimizations which sacrifice some/a lot of speed in favor of using less VRAM. You can run the program.
DevOps.com·4yStable Diffusion Goes Public — and the Internet Freaks Out
Stable Diffusion is the new open source machine learning model for creating images from text and even other images. It's similar to DALL-E and Midjourney, you give it a textual ‘prompt’ and it generates amazing images. The team behind the model have been very transparent about how their model is trained.
Hacker News·4yOpen-source rival for OpenAI’s DALL-E runs on your graphics card
Stable Diffusion is already expected to run on a single graphics card with 5.1 gigabytes of VRAM – bringing AI technology to the edge that until now has only been available through cloud services. The code and a trained model will be published as open source. There will be a hosted version with a web interface August 7, 2022 Stable diffusion. The model is also supposed to running on MacBooks with Apple's M1 chip.
