Apple reveals AI tool that can turn still images into animations — Keyframer research shows LLM animation powered by GPT-4
A 31-page research report has just been published, showing off a brand-new animation tool that could be a huge step in AI implementation for Apple.
VentureBeat initially spotted the report entitled “Keyframer: Empowering Animation Design using Large Language Models.” In the report, Keyframer is described as a tool powered by Large Language Models like Open AI’s ChatGPT-4 that can turn simple images into animations.
The research paper for Keyframer says: “Keyframer takes advantage of the code generation capabilities of LLMs and affordances for natural language input to empower users to generate animations using highly semantic prompts.” This means that users don’t have to give specific prompts about dimensions, sizes, and objects, they can simply informally request changes like “make it look cool” to get a response.
84.4% of users who tested this tech out used ‘semantic’ prompts to get the outcome they desired.
How does it all work?
The paper talks extensively about generative AI tools and how it is held back “due to the serendipitous and uncertain nature of the design space.” Though many other AI tools have worked on generating images and animations, Keyframer attempts to set itself apart by exploring existing images without generating new content.
If research proves fruitful and Keyframer becomes an official app, it would likely be part of the suite of apps available on iPhone, where you can add your picture and select prompts to make it move around. This could be a great tool for presentations or short ways of quickly displaying information. A user would prompt it with commands like ‘move X up’ or ‘make it look prettier’, and it would use ChatGPT-4 to guess what it intended with that phrase and create an animation. Then, you could fine-tune the animation with extra prompts and changes, much like what you would do when talking to another human.
It is designed as an additive tool to creativity and not a replacement for it. The paper’s conclusion says “we hope to inspire future animation design tools that combine the powerful generative capabilities of LLMs to expedite design prototyping with dynamic editors”. Apple is reportedly working on a major AI upgrade this year, and this report is likely one of many steps in the research process.
More from iMore
A 31-page research report has just been published, showing off a brand-new animation tool that could be a huge step in AI implementation for Apple.
VentureBeat initially spotted the report entitled “Keyframer: Empowering Animation Design using Large Language Models.” In the report, Keyframer is described as a tool powered by Large Language Models like Open AI’s ChatGPT-4 that can turn simple images into animations.
The research paper for Keyframer says: “Keyframer takes advantage of the code generation capabilities of LLMs and affordances for natural language input to empower users to generate animations using highly semantic prompts.” This means that users don’t have to give specific prompts about dimensions, sizes, and objects, they can simply informally request changes like “make it look cool” to get a response.
84.4% of users who tested this tech out used ‘semantic’ prompts to get the outcome they desired.
How does it all work?
The paper talks extensively about generative AI tools and how it is held back “due to the serendipitous and uncertain nature of the design space.” Though many other AI tools have worked on generating images and animations, Keyframer attempts to set itself apart by exploring existing images without generating new content.
If research proves fruitful and Keyframer becomes an official app, it would likely be part of the suite of apps available on iPhone, where you can add your picture and select prompts to make it move around. This could be a great tool for presentations or short ways of quickly displaying information. A user would prompt it with commands like ‘move X up’ or ‘make it look prettier’, and it would use ChatGPT-4 to guess what it intended with that phrase and create an animation. Then, you could fine-tune the animation with extra prompts and changes, much like what you would do when talking to another human.
It is designed as an additive tool to creativity and not a replacement for it. The paper’s conclusion says “we hope to inspire future animation design tools that combine the powerful generative capabilities of LLMs to expedite design prototyping with dynamic editors”. Apple is reportedly working on a major AI upgrade this year, and this report is likely one of many steps in the research process.
More from iMore
Denial of responsibility! Techno Blender is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – [email protected]. The content will be deleted within 24 hours.