synmindai/dsh-seedance2
synmindai★ 0JavaScriptLast synced: 2026-08-14
DeepSeek Harness plugin for Seedance 2 image and video generation
README excerpt
Seedance 2 for DeepSeek Harness dsh-seedance2 adds image and video generation to DeepSeek Harness through the Seedance 2 AI public API. The same plugin can create images with Nano Banana Pro, Nano Banana 2 Lite, or GPT Image 2 and create videos with Seedance 2 or Seedance 2.5. Tools: - seedance2 generate image - seedance2 generate video - seedance2 get task - seedance2 account help 中文说明 Account, credits, and API key 1. Sign up or sign in at . 2. Buy credits at . 3. Create and manage an API key at . 4. Set the key only in the environment that launches Harness: 5. Restart Harness. Use the public key created on the API page. Internal provider credentials such as SEEDANCE API KEY are not accepted by the public API. Official API documentation and current model parameters: Install The config dump should contain a seedance2 bundle layer. To install a cloned checkout instead: Try it Reference assets must be public HTTPS URLs. For best Seedance results, describe the subject, action, scene, camera movement, visual style, constraints, and the role of every supplied asset in the prompt. Safety and billing behavior - Paid image and video tools ask for approval by default. - The API key is resol…
View full README on GitHub →Category
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网第一个 DeepSeek Harness 视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
★ 1,123
Anionex/agent-vision-toolkit为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
★ 794
Anionex/dsh-vision-toolkit让纯文本模型更好地做视觉任务的DeepSeek Harness插件:带意图的图片问答、长截图 OCR、UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
★ 298