时间:2025-04-26 21:14:23 来源:网络整理编辑:探索
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
Mall builds real2025-04-26 20:56
英文字母被“開除”時 俄語成了國際足聯官方語言2025-04-26 20:30
曼聯官宣與B費續約 簽到2026年附加一年延長選項2025-04-26 20:27
世界杯C組解簽:阿根廷占據優勢 沙特或成“大禮包”2025-04-26 19:53
Ivanka Trump's unpaid interns share cringeworthy financial advice2025-04-26 19:41
西德同組險釀“超級死亡之組” 梅西簽運略勝C羅2025-04-26 19:31
官方:洛國富加盟米內羅美洲 簽約至2023年底2025-04-26 19:29
國足防守12強最差:丟19球無零封 頻繁變陣是禍根 ?2025-04-26 19:02
Carlos Beltran made a very interesting hair choice2025-04-26 18:47
世界杯分組日本最悲催 亞洲球隊能否再創曆史?2025-04-26 18:47
Slack goes down again, prompting anxiety everywhere2025-04-26 21:09
日本球迷哀歎死亡之組 :日本列島傳來一聲尖叫 太糟糕了2025-04-26 21:08
津媒:田依濃接近加盟津門虎 5外援配置基本確定2025-04-26 21:03
巴坎布發文回應指責教練不懂球 無論勝利還是失敗我都承擔責任2025-04-26 20:55
This company is hiring someone just to drink all day2025-04-26 19:42
韓媒:越南新星令日本王牌無功而返 展現了戰鬥精神2025-04-26 19:36
世界杯淘汰賽對陣:相鄰組交叉PK 梅羅有望決賽相遇2025-04-26 19:04
無緣卡塔爾世界杯球星陣容 :伊布領銜 哈蘭德在列2025-04-26 19:01
Balloon fanatic Tim Kaine is also, of course, very good at harmonica2025-04-26 18:35
馬競VS阿拉維斯首發:菲利克斯格子領銜 蘇牙替補2025-04-26 18:34