For the DeepSeek Harness native vision model deepseek-v4-flash-vision-exp, raises image admission limits to 32 MiB / 8192 px / 600 images and adds a highres_read tool that tiles large images, then returns the whole image plus 800x800 tiles through the host read_image tool.
- GitHub stars
- 4
- License
- MIT
- Added
- 2026-08-28
GitHub info
- GitHub stars
- 4
- License
- MIT
- Primary language
- Python
- Last push
- Aug 24, 2026, 5:46 PM
- Maintainer
- azwosile
- Added
- 2026-08-28
Install
dsh plugin --profile web add github:azwosile/dsh-highres-visionREADME badge
Add this Markdown to your plugin README to link back to its listing.
[](https://dshget.com/plugins/azwosile/dsh-highres-vision)Related plugins
Vision & Multimodalmodlens
★ 3768Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-vision-router
★ 1030Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
dsh-vision-toolkit
★ 842Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.