Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Magma: A GPT-style multimodal model for any combination of image and text
(
github.com/aleph-alpha
)
2 points
by
beernet
on March 16, 2022
|
hide
|
past
|
favorite
|
1 comment
beernet
on March 16, 2022
[–]
MAGMA semantically understands images beyond traditional object classification and can, for exmaple, be used to automatically generate image captions for arbitrary images. Some of these results are really astonishing and surprisingly precise.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: