Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
famouswaffles
on April 19, 2023
|
parent
|
context
|
favorite
| on:
LLaVA: Large Language and Vision Assistant
specifics work too if they're targeted. For instance, asking "what's the color of the boy's shirt ?", "what of his shorts ?" all return accurate results even if those details are missed in a general, "describe this image" request.
https://imgur.com/a/4KLRDUv
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://imgur.com/a/4KLRDUv