Stable Diffusion 3 Launch Drama
Suuup - Long time no see, hope you still remember us - the SinkIn Newsletter, a 5 minutes read made at sinkin.ai to cover the most interesting stuff in the Image AI world.
Stable Diffusion 3 Medium (the 2B parameters version) was launched on June 12th, and it’s been a disappointment to the community. It was later banned from Civitai due to lack of clarity in the license. To address these concerns, Stability AI recently updated the license and acknowledged “SD3 Medium is still a work in progress. We aim to release a much improved version in the coming weeks.”
“Girl lying on the grass” generated by SD3 Medium
LivePortrait is a new method to create realistic videos from a single image. By using a large dataset and advanced techniques, the method enhances animation quality and speed, achieving up to 12.8 milliseconds per frame. It includes modules for stitching and retargeting facial features, making it more practical and effective for real-time use. Check out their Github repo for further exploration.
Showcase Video
At SinkIn we recently launched Drawbert, a product that aims to make it real easy to create portrait art. With a simple photo, you can generate beautifully drawn portrait paintings for you and your loved ones. It can create single portrait or group portrait within seconds and offers multiple art styles covering oil painting, watercolor, sketch, caricature and more. You can also use text prompt to fully customize the generation to your liking. Try it out and let us know what you think.
Group Portrait Easily Done
Runway has launched Gen-3 Alpha, a powerful text-to-video AI model now generally available. Previously, it was only accessible to partners and testers. This tool allows users to generate high-fidelity videos from text prompts with remarkable detail and control. Gen-3 Alpha offers improved quality and realism compared to recent competitors Luma and Kling. It's designed for artists and creators, enabling them to explore novel concepts and scenarios.
Paints-Undo is a project aimed at providing base models of human drawing behaviors with a hope that future AI models can better align with the real needs of human artists. It presents a family of models that take an image as input and then output the drawing sequence of that image. The model displays all kinds of human behaviors, including but not limited to sketching, inking, coloring, shading, transforming, left-right flipping, color curve tuning, changing the visibility of layers, and even changing the overall idea during the drawing process.
Meme of the Week
That’s it for today, hope they were as sweet as summer time mangos!
What'd you think of today's edition? |