DeepSeek Harness Plugin Hub
← Plugins

vision-exp-tile

Vision Exp Tile

A large-image intelligent recognition plugin tailored for deepseek-v4-flash-vision-exp: whole-image precheck → local OCR + pixel grid (text) + proportional tiling around points of interest (longest edge 800) → aggregation; retains the whole-image 800x800 grid tiling mode. Does not count tokens or ca

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:Nicholas023/vision-exp-tile#100ca1c5122c11958e3fc0e53b879b7e98a70137

Description

A large-image intelligent recognition plugin tailored for deepseek-v4-flash-vision-exp: whole-image precheck → local OCR + pixel grid (text) + proportional tiling around points of interest (longest edge 800) → aggregation; retains the whole-image 800x800 grid tiling mode. Does not count tokens or calculate costs. v0.4.2: picturereader adaptability improvements (coexistence and task-allocation guidance / visual endpoint reuse / shared OCR venv).

Compatibility and provenance

Vision Exp Tile is published as vision-exp-tile and currently resolves to version 0.4.2. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated

Versions

0.4.2stable
0.4.1stable
0.4.0stable
Show 3 more versionsCollapse versions
0.3.1stable
0.3.0stable
0.1.4stable

Related plugins

More verified plugins in vision-media.

Tool Describe Image@linxin666/dsh-tool-describe-imageModel-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable — Modlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLIVision Routerdsh-vision-routerEyes 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.Vision Toolkit@anionex/dsh-vision-toolkitDeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.