Stability AI, the world's leading open source generative AI company, has recently launched its Stable Animation SDK, a new tool that allows developers to create and animate 3D models using natural language commands. The SDK is powered by Stability AI's flagship model, Stable Diffusion, a text-to-image generator that can produce realistic and diverse images from any text input.
The Stable Animation SDK enables users to easily generate 3D models of any object, character, or scene by simply describing them in words. For example, one can write “a dragon with red scales and green eyes” and get a 3D model of a dragon that matches the description. Users can also modify the models by adding or changing attributes, such as color, shape, size, texture, pose, and more.
But the SDK does not stop at generating static models. It also allows users to animate them using natural language commands. For example, one can write “make the dragon breathe fire” or “make the dragon fly” and see the model come to life with realistic motions and effects. Users can also control the camera angle, lighting, background, and other aspects of the animation.
The Stable Animation SDK is designed to be easy to use and integrate with existing applications and platforms. Users can access the SDK through Stability AI's Platform API, which provides a simple interface for interacting with Stability AI's models. Users can also use Stability AI's plugins for popular software such as Photoshop and Blender to generate and edit 3D models and animations right inside their favorite tools.
In its announcement blog post, Stability AI points to three different ways that users can input into the AI to generate animations:
- “Text to animation: Users input a text prompt (as with Stable Diffusion) and tweak various parameters to produce an animation.
- Text input + initial image input: Users provide an initial image that acts as the starting point of their animation. A text prompt is used in conjunction with the image to produce the final output animation.
- Input video + text input: Users provide an initial video to base their animation on. By tweaking various parameters, they arrive at a final output animation that is additionally guided by a text prompt.”
Stability AI's founder and CEO, Emad Mostaque, said: “Our mission is to build the foundation to activate humanity's potential. With the Stable Animation SDK, we are giving users a new way to unleash their creativity and imagination using generative AI. We are excited to see what amazing things people will create with this tool.”
The Stable Animation SDK is now available for beta testing for selected developers. Interested users can sign up on Stability AI's website to get early access and updates on the SDK. Users can also learn more about Stability AI's other products and services on their website or follow them on social media for the latest news and announcements.
Stability AI is a Leader in Open Source Intelligence and May Outcompete Google and Microsoft
Stability AI is a company that makes open source AI tools that anyone can use. It makes AI models for different things like images, words, sounds, videos and more. It also makes apps and plugins that let people use its AI models easily. The company is the largest open source generative AI developer in the world and uses the Ezra-1 UltraCluster, which is the fifth most powerful supercomputer in the world. The company develops Stable Diffusion, a machine learning model that can generate images from text, modify images based on text, or fill in details on low-resolution or low-detail images.
Last month, we reported on a leak of an internal Google memo that highlighted the company's concerns that open source providers such as Stability AI will outcompete private developers such as Microsoft, OpenAI, and Google. Those companies have very public AI tools, Bing Chat (Microsoft), ChatGPT (OpenAI), and Bard (Google).
The document, which Semianalysis says is genuine and provides deep insights into the semiconductor industry, reveals that Google and OpenAI are vulnerable to being surpassed by their open-source rivals.
It states, “We have no moat, and neither does OpenAI”. It also highlights the fast improvements made by open-source AI projects, which have arguably been more innovative than Google and OpenAI in recent months. The document mentions several remarkable feats by open-source AI, such as running foundation models on a Pixel 6 at 5 tokens per second, fine-tuning personalized AI on a laptop in an evening, and creating multimodal models in record time.