Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
prettyblocks
1 day ago
|
parent
|
context
|
favorite
| on:
Ollama's new engine for multimodal models
I'm very interested in working with video inputs, is it possible to do that with Qwen2.5-Omni and Ollama?
oezi
1 day ago
|
next
[–]
I have only tested Qwen2.5-Omni for audio and it was hit and miss for my use case of tagging audio.
reply
tough
22 hours ago
|
prev
|
next
[–]
https://huggingface.co/blog/smolvlm
reply
machinelearning
1 day ago
|
prev
[–]
What's a use case are you interested in re: video?
reply
prettyblocks
18 hours ago
|
parent
[–]
I'm curious how effective these models would be at recognizing if the input video was ai generated or heavily manipulated. Also various things around face/object segmentation.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
