Show HN: Papermusic (draw an instrument, then play it) https://ift.tt/UxTsNqy

Show HN: Papermusic (draw an instrument, then play it) This was a fun experiment to try PaliGemma (open vision-language model). I found that PaliGemma performed better than Gemini Flash for this type of specific image task, especially around latency. (~0.9 seconds for PaliGemma inference on a VM, vs. 3-4 seconds for Gemini Flash.) Would love feedback on ways to potentially improve this setup. https://ift.tt/AQwlXKh June 17, 2024 at 09:56PM

Comments

Popular posts from this blog

Show HN: Create a “rogue” WiFi AP & Captive Portal with a Raspberry Pi https://ift.tt/2AvGXHQ

"A Crane, For God's Sake": Inside Turkey's Struggling Earthquake Response