时间:2025-04-26 17:39:17 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
Dog elected for third term as mayor of Minnesota town2025-04-26 17:13
This university has almost as many Olympic medals as Brazil2025-04-26 17:09
Video compilation highlights all the sexist moments from the Olympics coverage2025-04-26 16:42
Rihanna visited the massive, headless Rihanna statue in Germany2025-04-26 15:58
Twitter grants everyone access to quality filter for tweet notifications2025-04-26 15:55
Intense video shows humpback whales breaching just feet from kayakers2025-04-26 15:41
This university has almost as many Olympic medals as Brazil2025-04-26 15:35
YouTuber Louis Cole responds to outrage over his North Korea travel videos2025-04-26 15:23
Is Samsung's Galaxy Note7 really the best phone?2025-04-26 15:06
'Game of Thrones' laid waste to all Twitter's #7FavTVShows rivals2025-04-26 14:55
We asked linguists if Donald Trump speaks like that on purpose2025-04-26 17:39
YouTuber Louis Cole responds to outrage over his North Korea travel videos2025-04-26 17:15
Intense video shows humpback whales breaching just feet from kayakers2025-04-26 16:54
YouTuber Louis Cole responds to outrage over his North Korea travel videos2025-04-26 16:39
Fake news reports from the Newseum are infinitely better than actual news2025-04-26 16:35
Video compilation highlights all the sexist moments from the Olympics coverage2025-04-26 16:03
Video compilation highlights all the sexist moments from the Olympics coverage2025-04-26 15:28
Video compilation highlights all the sexist moments from the Olympics coverage2025-04-26 15:21
This weird squid looks like it has googly eyes, guys2025-04-26 15:14
Rihanna visited the massive, headless Rihanna statue in Germany2025-04-26 15:12