Synthetic media startup Stability AI has introduced a new tool for producing animation with its open-source Stable Diffusion generative AI models. The new Stable Animation SDK creates animated videos out of a text prompt, with potential assistance from an image or existing video clip.
Stable Animation SDK is essentially a text-to-3D-image generator that relies on the current Stable Diffusion model as well as the new Stable Stable Diffusion XL. Instead of a single three-dimensional image, the AI replicates the process of animation, where thousands of slightly different images give the illusion of motion. Natural language prompts are all that’s needed to direct the video clip, with the AI acting as the director of photography and adjusting lights, angles, background, and all the other elements of the “film.” The new tool is available through Stability AI’s API or through plug-ins with media edting software like Photoshop and Blender. To produce the animation, users can submit a text prompt either by itself, with a still image, or with an existing video for Stable Animation to use as guidance in developing the final video clip.
“Our mission is to build the foundation to activate humanity’s potential,” Stability AI CEO Emad Mostaque said in a statement. “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.”
Stable Animation SDK is now in beta and joins the rapidly proliferating collection of Stability AI synthetic media tools, including a partnership with digital collectible platform Revel.xyz to make an image-to-animation tool called Animai. Most recently, the company showcased the DeepFloyd IF image generator, which doesn’t use the Stable Diffusion model and follows Stability’s release of the non-image open-source LLM Stable Diffusion XL (SDXL). This is a larger version of the standard image generator. SDXL also boasts of being able to embed readable text and a high degree of photorealism. StableLM.
Stable Animation seems to center on enterprise use cases, similar to DeepFloyd IF. In the last several months, Stability AI helped bring several new products to the public in recent months, Stability’s expanding generative AI research is fueled in part by the $101 million it raised last year. Stability has also made acquisition part of its strategy, starting with the company behind AI image manipulation service Clipdrop,
Follow @voicebotaiFollow @erichschwartz
Stability AI Unveils Image-to-Animation Generative AI Tool Animai
Stability AI Debuts Photorealism-Focused Stable Diffusion XL Text-to-Image Generative AI Model
Stability AI Debuts New Text-to-Image Model DeepFloyd IF
Read the full article here