gemini-4IMAGE
Gemini 4 Argon supports box prompts for object detection
Hands-on testing shows Gemini 4 Argon can take box prompts, positive or negative, to generate new detections, which helps when a text prompt is ambiguous.
SkalskiP
@skalskip92Archived 21 days agoOriginally posted 2026.10.15

SkalskiP @skalskip92Originally posted 2026.10.15
you can also prompt Gemini 4 Argon with boxes to generate new detections - works with positive and negative examples - useful when text prompt is ambiguous - works across images vlms are so versatile... take a look, just the pawns ↓ more box prompts
This post quotes another post: “Gemini 4 Argon tops Astra in vision evals for detection and text extraction”
x.com/skalskip92/status/2110424053152698800Archived 2026.10.15 11:25