Deepseek-Continuity
本地生成图像/配音/音乐/音效并听写，同一性锁定：角色、动物、道具与配音角色定妆定声一次，之后每次调用复用同一份参考；退化产物（接近纯色的图、静音的音频）被拒绝而不是当成成功返回；生成的台词可以听写回文字，好让吞掉结尾的克隆暴露出来。空闲时引擎卸载显存，生图与听写也可改指向任意 OpenAI 形状的 API 而不用本地 Vulkan 后端。
Local image, voice, music and SFX generation plus transcription, with pinned identity: characters, animals, objects and actor voices are defined once and reused on every later call, degenerate output (a near-flat image, silent audio) is rejected instead of returned as success, and a generated line can be read back as text so a clone that swallowed its ending becomes visible. The engines unload when idle, and image generation and transcription can each be pointed at an OpenAI-shaped API instead of the local Vulkan backend.
怎么安装
dsh plugin add dsh-plugin-continuity npx -y dsh-plugin-continuity 简介
场记 / Continuity A DeepSeek Harness plugin that gives an agent local image / speech / music / SFX generation, the transcription to hear its own output back, **and a memory of what it made** — the same character stays the same character across every call, and a failed generation is never allowed to pass as a success. Runs locally. Models are lazy-loaded per request and released when idle, so **when you are not using it the GPU is untouched** — 0.21 GiB resident, measured. You can play a game on the same card. Or keep only the half you want local: image generation speaks any OpenAI-shaped /v1/ima…
推荐参考
信息
- 协议
- MIT
- 语言
- Python
- GitHub 星标
- 2
- 月下载
- –
- 最近更新
- 2026-08-25
- 创建于
- 2026-08-20
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- 主题标签
- agent-tools, deepseek-harness, dsh-plugin, image-generation, mcp, mcp-server, text-to-speech, vulkan
同类推荐
modlens
liustack/modlens
为纯文本模型架起视觉桥梁：粘贴图片，输出结构化 JSON 证据（OCR、版面、语义）。
dsh-vision-router
ysr666/dsh-vision-router
为纯文本 Agent 提供视觉能力：内置免 Key 视觉链 + 像素级视觉工具（看图问答、定位、裁剪、像素对比、取色、OCR、矢量化、抠图、截图）；粘贴图片即可用。
dsh-vision-toolkit
Anionex/dsh-vision-toolkit
让纯文本模型处理视觉任务：粘贴图片后自动切换到 Vision Toolkit 变体，支持图片问答、多图比较、长截图 OCR、截图还原前端 UI、元素定位与像素对比。默认无需 API Key——图片经作者自建的免费服务处理，每台机器每天 100 张；也可改为指向自己的服务商。
dsh-deepseek-vision
siegfly/dsh-deepseek-vision
视觉语言网关：注册支持图片输入的 DeepSeek provider 路由，图片先由可配置 VL 模型（默认 Qwen-VL）描述成文字再发送。