DSH Multimodal
chenkezhen480/dsh-multimodal · model-adapters
Image recognition and image generation for DeepSeek Harness (dsh-plugin, a Cordis plugin).
★ 4GitHub stars
0Forks
2026-09-01Last updated
TypeScriptLanguage
Apache-2.0License
Key features
- The plugin is just toolsimage_recognize, image_generate, and vision_providers call whichever external API models the deployer declares — vision via multimodal chat/completions
- Local files are inlined as base64 data URIs (25 MiB cap)
- prompt (what to ask), max_tokens / temperature, per-call provider selection
- image_generate — generate or transform an image through a configured image model, save it to disk, and return its file path plus a Web-renderable URL when the static server is enabled
Requirements
- 25 MiB inline cap for local images — compress or use a URL for larger files
- Generated-image format detection — PNG/JPEG/WebP/GIF base64 payloads use their detected extension
Install command
dsh plugin --profile web add github:chenkezhen480/dsh-multimodal