返回目录

GITHUB TOPIC

multimodal

18个项目包含此标签

18 个项目

GitHub Topic 精确匹配

文件与数据

Scene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.

已验证
asrcontact-sheetdeepseek-harnessdsh-plugin
安全与治理

dsh-crew

ZSeven-W

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

已验证
ai-agentsclaude-codecodexcoding-agent
文件与数据

dsh-vision

oil-oil

Near-native image understanding for DeepSeek Harness

已验证
deepseek-harnessdsh-pluginimage-understandingmultimodal
文件与数据

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

已验证
dashscopedeepseek-harnessdsh-pluginimage-understanding
文件与数据

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)

已验证
agent-toolai-agentcordisdeepseek-harness
开发工具

DeepSeek Harness 第三方 API 与自定义模型设置插件:支持请求头、User-Agent、模型列表、图像输入和思考等级 | WebUI plugin for third-party APIs and custom models with request headers, image input, and reasoning levels

已验证
deepseek-harnessdshdsh-pluginmodel-provider
开发工具

visual-review

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。

已验证
deepseek-harnessdshdsh-pluginimage-analysis
开发工具

DeepSeek Herness plugin. dsh插件,支持在创建自定义模型时手动选择模型能力,比如模型是否支持图片输入等。DeepSeek Herness plugin. dsh插件,支持在创建自定义模型时手动选择模型能力,比如模型是否支持图片输入等。DeepSeek Herness plugin. dsh插件,支持在创建自定义模型时手动选择模型能力,比如模型是否支持图片输入等。The DSH plugin allows users to manually configure model capabilities when creating a custom model, such as image input support.

已验证
deepseek-harnessdsh-pluginmodel-capabilitiesmodel-configuration
开发工具

dsh-free-media

bdydgz114514

DSH 免费多模态三件套:零 Key 文生图 + 零 Key 视频理解 + 免费文生视频/图生视频。三个工具 + 一份 skill,MIT。

已验证
cogvideoxdeepseek-harnessdshdsh-plugin
文件与数据

统一接入 Image2 与 Nano Banana 四款模型,覆盖文生图、多参考图编辑、2K/4K 输出、顺序批量任务、默认模型持久化和脱敏 Key 配置。

已验证
88apideepseek-harnessdshdsh-plugin
文件与数据

DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.

已验证
cordisdeepseek-harnessdshdsh-plugin
文件与数据

Vision routing and image generation for DeepSeek Harness through a fixed Mix model.

已验证
deepseek-harnessdsh-plugingpt-image-2image-generation
文件与数据

dsh-video-see

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.

已验证
agent-toolsdeepseek-harnessdshdsh-plugin
文件与数据

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。

已验证
deepseek-harnessdshdsh-plugindsh-plugins
Agent 与会话

Lossless visual memory for DSH agents: store an image once, address it by sha256, read exact pixels, compare past frames, recall by text/tag/turn — no second vision model in the loop.

已验证
agent-memorydeepseek-harnessdsh-pluginimage-memory
开发工具

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

已验证
deepseek-harnessdshdsh-plugininput-modalities
文件与数据

dsh-xiapan-media

dongsheng123132

Native vision, gpt-image-2 and Seedance plugins for DeepSeek Harness via Xiapan Cloud

已验证
deepseek-harnessdsh-pluginimage-generationmultimodal
文件与数据

dsh-open-eyes

hyper-dsh-plugins

A lightweight DeepSeek Harness vision delegation tool for text-only routes, with native OpenAI Responses, Chat Completions, and Anthropic Messages adapters.

已验证
anthropicdeepseek-harnessdsh-pluginmultimodal