Featured
Computer vision
New 2026
DeepSeek Harness local OCR plugin powered by light-ocr
New 2026
Feature Island Induction From a Semantically Rich Ocean. Not the title of a deeply philosophical book about representation.
New 2026
Local OK-hand gesture recognition for DeepSeek Harness composer send
New 2026
A better face management layer for UniFi Protect. Pulls face detections via reverse-engineered Protect APIs and runs them through a dedicated facial recognition engine for accurate matching and clustering — fixing the false positives and clunky triage UI that Protect ships with.
New 2026
On-device AI background remover built with React Native, Expo, executorch & Skia.
11115
New 2026
Move things on your screen with your bare hands. A webcam-powered, hand-tracked interface for your AI. No headset. No controllers.
New 2026
Give DeepSeek verified multimodal vision and browser computer use inside DeepSeek Harness
New 2026
Sero — on-device AI image detector Chrome extension (ONNX/WASM, MV3)
New 2026
cat cam meme camera if you're coming from instagram! we luh cats
New 2026
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
New 2026
让纯文本模型更好地做视觉任务的DeepSeek Harness插件：带意图的图片问答、长截图 OCR、UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
New 2026
INT8 single-class YOLOv3-Tiny accelerator and OV5640-to-HDMI bare-metal demo for Xilinx Zynq-7000 XC7Z100, with PyTorch training and parameter-export tools. Topics yolov3-tiny, fpga, zynq-7000, xc7z100, verilog, vivado, vitis, pytorch, int8-quantization, object-detection, axi4-stream, ov5640, hdmi, embedded-systems, computer-vision
New 2026
MLX / mlx-vlm architecture support for Muse-Glimmer multimodal (vision+language) models on Apple Silicon
New 2026
Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.
New 2026
Local-first activity and enrichment-use analysis for zoo animal videos
Other topics
Browse other topics on Trendshift
A
N