CATEGORY
Vision & Media DSH plugins
Verified manifests and exact versions in this category.
All plugins
376 pluginsdsh-plugin-video-playerPlugin Video Player
DSH web GUI client plugin: video browsing window (select folder / Douyin-style vertical video browsing / ←→ seek / ↑↓ or drag to switch)
dsh-vidgen-pluginVidgen Plugin
Multi-provider AI video/image generation plugin for DeepSeek Harness (DSH). ComfyUI-style node canvas studio + multi-provider settings, with agent tools list_video_models / generate_video / poll_video_task. | DeepSeek Harness AI 视频/图片生成插件：多提供者、节点画布工作室、Agent 工具与 REST RPC。
dsh-plugin-glm-visionPlugin Glm Vision
Image translation for non-multimodal models via GLM-4V-Flash: intercepts images, generates descriptions, injects as text.
dsh-image-previewImage Preview
DSH in-session image preview service: HTTP exposure of workspace images, text-to-image rendering (dual fonts to prevent garbled text), SVG-to-PNG conversion, and CDP application interface screenshots. AI replies can include markdown image URLs for users to view images directly in the conversation.
dsh-portraitPortrait
Portrait Photography
dsh-phone-photoPhone Photo
Mobile photography
dsh-edit-photoEdit Photo
Photo post-processing
@dsh-external/dsh-image-genImage Gen
DSH universal image generation plugin: connects to any OpenAI-compatible image generation gateway (custom baseUrl + model + API Key), with visual configuration in the settings page. Tools dsh_image_gen / dsh_image_gen_config + command /dsh-image-gen + skill.
@zhangbo-cn/dsh-client-ui-voice-inputClient Ui Voice Input
Composer mic for DeepSeek Harness Web: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.
dsh-video-sizeVideo Size
Video file size
dsh-video-lengthVideo Length
Recommended video duration
dsh-vision-checkVision Check
Visual refractive power
dsh-sd-capacitySd Capacity
Video recording storage capacity
dsh-pixel-printPixel Print
Pixel print size
my-image-dropMy Image Drop
DeepSeek Harness plugin: drag images into the composer and get a file path back, so text-only models can read them via the read tool.
dsh-client-paste-imageClient Paste Image
Paste clipboard images as file PATHS only on configured text-only routes: for listed models the paste is intercepted, saved through dsh-drop-caret's session upload route, and the path lands in the composer — vision-capable models keep their native image pipeline untouched. v0.3.0: host half bridges