← Leaderboard / Models / Plugin
Last repository activity August 16, 2026 · Created August 16, 2026
Leeminjing/dsh-eyes
“On-demand vision for text-only LLMs in DeepSeek Harness: keep pasted/attached images in the backend, and let the model call view_image to look at them anytime via any OpenAI-compatible vision endpoint — as if the model were natively multimodal.”
Star rank
Pendinginstall verification
In Models
Pendinginstall verification
Stars
1GitHub repository
Forks
0GitHub repository
Watchers
1GitHub subscribers
Description
On-demand vision for text-only LLMs in DeepSeek Harness: keep pasted/attached images in the backend, and let the model call view_image to look at them anytime via any OpenAI-compatible vision endpoint — as if the model were natively multimodal.
30 days of GitHub stars
+0 stars
+0% observed change
Jul 18Aug 1Aug 16