dsh-vision
oil-oil
Near-native image understanding for DeepSeek Harness
GITHUB TOPIC
29个项目包含此标签
29 个项目
GitHub Topic 精确匹配
oil-oil
Near-native image understanding for DeepSeek Harness
MJorgin
Free image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2 / v0.1.2-alpha.3) — paste-image reading with auto vision transcription, DeepSeek-V4-Flash-Vision-Exp / GLM-4V-Flash / SenseNova / Gemini failover, Kolors + U1 Fast generation. No keys in repo.
Flyvhidbwo
DeepSeek Harness 插件:DeepSeek Pro 大脑 + 自动识图。GUI 附加图片默认经官方 deepseek-v4-flash-vision-exp 原生识图,转译成文字后交给 DeepSeek 作答(纯文本的 V4-Pro 也能看图);支持百炼/智谱/OpenRouter 等任意 OpenAI 兼容 VLM,无 key 自动探测本地 Ollama;安装时有一问式确认
welsione
一个工具 = MiniMax 全部多模态能力:DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover/search/quota) for DeepSeek Harness (DSH)
loudMore
DSH 插件:图片与文件直达纯文本模型——图片保留原生附件体验,PDF/Office/压缩包/视频/音频显示为附件栏方块,点击发送时自动转为工作区路径,配合 dsh-vision-toolkit 粘贴即看图。A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep the native attachment UI, other files show as square chips in the rail, paths append on send — pairs with dsh-vision-toolkit.
Destinhue
Look at a video instead of being told about one: a contact-sheet storyboard tool for DeepSeek Harness (video_probe / video_storyboard / video_zoom).
paicat1
DSH 轻量截图插件:轻 : 纯 PowerShell 实现,零依赖、零二进制;截图能力独立维护,不随任何上游更新而失效。 摆 :一键全屏即拍;框选前整个桌面保持可操作,所有窗口像布置画面一样自由移动、缩放;鼠标悬停任意窗口即亮起吸附边框,点一下直接截该窗口,被遮挡也能拿到完整内容,所得即所见。 自助:Agent 可随时自行截屏;接上 modlens(选装),截屏 + 识图一步产出结构化内容(OCR/版面/语义),纯文本模型也能消费。
azwosile
专供 deepseek-v4-flash-vision-exp 的高清识图增强插件:放宽 DSH 图片限制 + highres_read 分块识图工具。
FuzzySoul
为DSH(DeepSeek Harness)量身打造的视觉插件,现已支持agent调用图片显示/Vision plugin for DSH(DeepSeek Harness),support Proactive Image Display.
csukingzq
AI vision PDF translation and LaTeX reconstruction for DeepSeek Harness
a961282799-crypto
DeepSeek Harness 桌面插件:自由圈选预览内容,视觉识别目标,再用自然语言提出修改要求。无需截图。
wang-bool
DeepSeek Harness plugin for image upload, in-chat rendering, and vision analysis with cloud or local models. 图像上传、显示与解析。
GXX182
DeepSeek Harness plugin that bridges session images to pluggable vision APIs while keeping DeepSeek as the primary model.
linkingoscar
Codex-style attachment formats for the DeepSeek Harness Web GUI: PDF text-layer extraction, Office text extraction, scanned-PDF OCR, long-document spill + index cards, image-to-PNG.
niyongsheng
Local‑only vision skill for macOS 本地化识图技能dsh-plugin
tdf1995
Vision for text-only LLMs in DeepSeek Harness (DSH): describe images / OCR / VQA via free Gemini & GLM vision APIs
zzy6-a
DSH Computer Use:让 Agent 看见并操作 Windows 桌面(Windows 原生 / WSL 自动识别);视觉通道 + 鼠标键盘 + Codex 风格蓝色覆盖层,Esc 随时中止。
1HelloMan1
DeepSeek Harness usage dashboard with API balance, daily spend, external vision-call accounting, per-model stats, call logs, cache rate, TTFT, and CSV export.
Favio8
DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.
haiziyao
Vision routing and image generation for DeepSeek Harness through a fixed Mix model.
HongtaoWang75
Look at video with your own eyes: a DeepSeek Harness plugin that samples frames with ffmpeg and returns them to the agent as real images, each labelled with its timestamp — no vision API, no key, nothing leaves the machine.
MC5lan
给 DeepSeek 安装一双眼睛和一支画笔:会话里直接贴截图/图片,GLM 视觉模型先精确转写图片内容(报错信息、代码、界面逐字保留),然后 DeepSeek 继续处理你的问题——同一轮完成,全程无感;需要配图时,DeepSeek 自动调用文生图后端出图并显示在会话中。
ns-zzj
DSH 投屏控制的共用核心:界面、设备列表、投屏面板与 AI 工具(配合其他 provider 使用)
xiaoyuink
图片识别插件 for DeepSeek Harness:自动判断当前模型识图能力,支持多供应商视觉模型管理与检测
yhm0619
基于 dsh-pet 的互动碎碎念:每 30 秒识屏,用视觉模型在宠物头顶随口吐槽(不需要回复、不带表情包)。
bamboostrip
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
DDDFXYqiming
Vision skill plugin for DeepSeek Harness (image analysis and OCR)
dongsheng123132
Native vision, gpt-image-2 and Seedance plugins for DeepSeek Harness via Xiapan Cloud
hyper-dsh-plugins
A lightweight DeepSeek Harness vision delegation tool for text-only routes, with native OpenAI Responses, Chat Completions, and Anthropic Messages adapters.