New AI video generators • Robots with muscles • AI detects cancer • New AI animation tools • AI news this week
New AI video generators • Robots with muscles • AI detects cancer • New AI animation tools • AI news this week
Welcome to the AI Search newsletter. Here are the top highlights in AI this week.
A new AI technique called Motion Inversion allows users to customize video motion by transferring it from one video to another. This method uses Motion Embeddings to capture how objects move, ensuring that the new video maintains a natural flow of motion. It's especially beneficial for filmmakers who want precise control over camera movements in their projects. Read more
Anthropic has launched an AI agent that can interact with computers like a human. This model allows developers to direct Claude to perform tasks such as moving a cursor, clicking buttons, and typing text, which opens up new possibilities for automating complex processes.
Researchers at Google have developed a new method for editing images using Rectified Flows. This approach, called RF-inversion, allows for efficient image editing with text only, removing the need for other tools like inpainting and controlnet. Read more
Alibaba has developed Tora, an AI tool that lets users control the movements of objects in videos by simply drawing paths for them to follow. Tora stands for Trajectory-oriented Diffusion Transformer and works by breaking down the drawn paths into data that the AI can understand, ensuring smooth and realistic motion in the generated videos. Read more
A good photo on your Linkedin or business profile makes a huge difference. You could do a physical photoshoot, which costs you over $200 and hours posing awkwardly at a camera. Or, with AI Portrait, just upload one photo, and get a portfolio of 50 professional photos in minutes. Save time and money - try it today!
Vidpanos is a new AI tool from DeepMind that creates stunning panoramic videos from regular panning videos. It works by analyzing the input video, filling in missing areas, and stitching together frames to produce a seamless 360-degree view. This technology allows anyone with a simple camera to capture immersive experiences without needing special equipment. Read more
Don’t like reading? Here’s a video overview covering all the highlights in AI this week:
Allegro is a new AI video generation model from RhymesAI that creates short, high-quality videos based on text prompts. It can produce 6-second videos at 15 frames per second and 720p resolution. The full model and code are open-source, making it accessible for anyone interested in creating their own videos. Read more
xAlerts is a powerful tool that helps you track the activity of your favorite accounts. Stay informed from the latest activities of investors, celebrities, influencers, athletes, and more. Try it for free!
Mochi 1 is a new open-source video generator from Genmo that creates high-quality videos based on text prompts. Currently, it generates videos at 480p resolution, with plans for higher resolutions in the future, and is available for free. Read more
AiOS is an open-source algorithm for human detection and pose estimation. It processes the video by breaking it down into tokens, predicting human locations, and refining the details of their limbs and facial features, all without needing separate detection steps. This technology is especially useful for animation, eliminating the need for complex motion capture systems. Read more
Harvard scientists have developed an AI that can detect cancer with an impressive 96% accuracy. Trained on a massive dataset of over 60,000 medical images, the AI learns to identify 19 different types of cancer and even predicts tumor genetic profiles and patient survival rates. Read more
Ideogram has launched a new feature called Ideogram Canvas, which allows users to easily generate and edit images using AI. This tool lets you upload your own images or create new ones, and then use advanced features like Magic Fill to edit specific areas and Extend to expand images beyond their original borders. Read more
Stable Diffusion 3.5 has been released, featuring advanced capabilities for generating high-quality images from text prompts. This new version includes multiple models, like the Large and Turbo variants, which are designed to run efficiently on consumer hardware while producing diverse and realistic outputs. Read more