dsh-imagegen-video

AI image AND video generation plugin for the dsh web GUI, with a complete video pipeline alongside the image pipeline. Images: text-to-image and image-to-image through configurable provider channels (gpt-image-2 / grok-imagine-image / nanobanana series / seedream-5.0-pro / dall-e-3, with native xAI Grok Imagine, Google Nano Banana and ByteDance Seedream request shaping), per-channel model catalogs, a three-column studio beside the native conversation, an infinite canvas with node-graph workflows (annotation boxes with attached prompt cards, local background removal, AI layer split, per-node model choice, file nodes with any-file upload, and a canvas skill system covering skill-driven next steps on every node: text polish, image description, content extraction, and long-running headless-agent pipelines such as image-to-editable-ppt, with a local skill library that installs and removes skills from URLs or uploaded archives), an ecommerce product-set mode and a prompt template library. Video: text-to-video, image-to-video, first/last-keyframe and multi-reference modes with per-channel video model catalogs, an async submit/poll/download pipeline, a clip history merged into the sidebar, favorited clips in the asset library, host-side Agent video tools, video nodes on the infinite canvas with the same controls as image nodes, a storyboard node whose shot list runs one clip per shot into ordinary video nodes (independent shots or each shot starting from the previous shot's last frame; any finished clip can also turn its tail frame into a ready-to-run frame node), clip stitching of two or more canvas video nodes into one MP4 with the local ffmpeg in canvas reading order, and a graph-level workflow runner that walks a whole connected chain in dependency order. A director step runs before every render, decomposing a one-line request into shots, motion, camera work, duration and style, and the plan it produces is what the provider is sent (duration and frame may only narrow, never widen); the plan is previewable without rendering, echoed on the task and stored in the clip history.

一句话定位

AI image AND video generation plugin for the dsh web GUI, with a complete video pipeline alongside the image pipeline. Images: text-to-image and image-to-image through configurable provider channels (gpt-image-2 / grok-imagine-image / nanobanana series / seedr…

安装方式

在 DSH 的 web profile 中执行下面的命令；装完刷新页面即可。

$ dsh plugin --profile web add @q253595422/dsh-imagegen-video@1.27.0

兼容的 DSH 版本

未声明

作者与热度

q253595422 · ★ 90 · 更新于 2026-11-09

关于这个插件

相似插件