时间:2025-04-03 13:29:25 来源:网络整理编辑:知識
Apple is dabbling in AI image-editing with an open-source multimodal AI model.Earlier this week, res
Apple is dabbling in AI image-editing with an open-source multimodal AI model.
Earlier this week, researchers from Apple and the University of California, Santa Barbara released MLLM-Guided Image Editing, or "MGIE;" a multimodal AI model that can edit images like Photoshop, based on simple text commands.
On the AI development front, Apple has been characteristically cautious about its plans. It was also one of the few companies that didn't announce any big AI plans in the wake of last year's ChatGPT hype. However, Apple reportedly has an in-house version of a ChatGPT-esque chatbot dubbed "Apple GPT" and Tim Cook said Apple will be making some major AI announcements later this year.
SEE ALSO:Tim Cook says big Apple AI announcement is coming later this yearWhether this announcement includes an AI image editing tool remains to be seen, but based on this model, Apple is definitely doing some research and development.
While there are already AI image editing tools out there, "human instructions are sometimes too brief for current methods to capture and follow," said the research paper. This often leads to lackluster or failed results. MGIE is a different approach that uses MLLMs, or multimodal large language models, to understand the text prompts or "expressive instruction," as well as image training data. Effectively, learning from MLLMs helps MGIE understand natural language commands without the need for heavy description.
In examples from the research, MGIE can take an input image of a pepperoni pizza and using the prompt, "make this more healthy" infer that "this" is referring to the pepperoni pizza and "more healthy" can be interpreted as adding vegetables. Thus, the output image is a pepperoni pizza with some green vegetables scattered on top.
In another example comparing MGIE to other models, the input image is a forested shoreline and a tranquil body of water. With the prompt "add lightning and make the water reflect the lightning," other models omit the lightning reflection, but MGIE successfully captures it.
MGIE is available as an open-source model on GitHub and as a demo version hosted on Hugging Face.
TopicsAppleArtificial Intelligence
Researchers create temporary tattoos you can use to control your devices2025-04-03 13:29
This letter to Americans has an important message ahead of elections2025-04-03 13:16
Trump is the first president2025-04-03 13:09
The 9 most impressive social good innovations from October2025-04-03 13:02
Photos show the Blue Cut fire blazing a path of destruction in California2025-04-03 12:56
Actual voters scoff at Trump's poll watchers2025-04-03 12:39
Rolling Stone loses defamation lawsuit over 'A Rape on Campus' article2025-04-03 12:10
Here's where you can and can't snap that ballot selfie2025-04-03 11:54
Over 82,000 evacuate as Blue Cut fire rapidly spreads in southern California2025-04-03 10:54
What to watch on election night to maintain your sanity2025-04-03 10:48
Fake news reports from the Newseum are infinitely better than actual news2025-04-03 13:06
Donald Trump makes yuge mistake and mispronounces Beyoncé's name2025-04-03 12:57
This letter to Americans has an important message ahead of elections2025-04-03 12:33
Glowing Vincent van Gogh costume will illuminate your Halloween2025-04-03 12:18
Pokémon Go is so big that it has its own VR porn parody now2025-04-03 12:08
Teen dressed as a water bottle for Halloween is flipping amazing2025-04-03 12:07
The ugly intersection of World Series racism and the Dakota Access Pipeline2025-04-03 11:42
The Obama administration just made it easier to take a road trip in an electric car2025-04-03 11:37
Australian football makes history with first LGBT Pride Game2025-04-03 10:54
Donald Trump makes yuge mistake and mispronounces Beyoncé's name2025-04-03 10:51