11:47
Leaked details hint at big AI and camera upgrades for Google Pixel 10 and 11
11:47
Meta reportedly developing a search engine to power its AI chatbot
21:54
Apple introduces iMac with M4 chip and Apple Intelligence in cool new colors
12:30
OpenAI’s speech-to-text transcription tool reportedly has hallucination issues
12:29
Google develops AI "agent" that may soon take over computers
20:45
Tesla’s futuristic light bar comes with a catch
11:47
Leaked details hint at big AI and camera upgrades for Google Pixel 10 and 11
11:47
Meta reportedly developing a search engine to power its AI chatbot
21:54
Apple introduces iMac with M4 chip and Apple Intelligence in cool new colors
12:30
OpenAI’s speech-to-text transcription tool reportedly has hallucination issues
12:29
Google develops AI "agent" that may soon take over computers
20:45
Tesla’s futuristic light bar comes with a catch
11:47
Leaked details hint at big AI and camera upgrades for Google Pixel 10 and 11
11:47
Meta reportedly developing a search engine to power its AI chatbot
21:54
Apple introduces iMac with M4 chip and Apple Intelligence in cool new colors
12:30
OpenAI’s speech-to-text transcription tool reportedly has hallucination issues
12:29
Google develops AI "agent" that may soon take over computers
20:45
Tesla’s futuristic light bar comes with a catch
11:47
Leaked details hint at big AI and camera upgrades for Google Pixel 10 and 11
11:47
Meta reportedly developing a search engine to power its AI chatbot
21:54
Apple introduces iMac with M4 chip and Apple Intelligence in cool new colors
12:30
OpenAI’s speech-to-text transcription tool reportedly has hallucination issues
12:29
Google develops AI "agent" that may soon take over computers
20:45
Tesla’s futuristic light bar comes with a catch
Microsoft launched a Visual ChatGPT — a combination of ChatGPT and a series of Visual Foundation Models
13 Mar, 2023
1 min time to read
Visual ChatGPT enables users to send, receive and edit images during chatting.
In other words, Visual ChatGPT supports talking, drawing and editing. This is the next advanced stage in development of large language models.
According to Miscrosoft team, the system combines different Visual Foundation Models and activates more options of interaction with ChatGPT.
Visual ChatGPT enables to:
- send and receive not only text lines but also images,
- provide complex visual questions or visual editing instructions that require the collaboration of multiple AI models with multi-steps,
- provide feedback and ask for amended results.
Instead of training a new multi-modal ChatGPT from scratch the developers built Visual ChatGPT directly based on ChatGPT and incorporated a variety of Visual Foundation Models, such as Visual Transformers or Stable Diffusion.
Editor’s pick
