dsh-image-describer
Giving text models eyes to see in DeepSeek Harness.
73 results
Giving text models eyes to see in DeepSeek Harness.
即梦(火山方舟 Seedream)文生图/图生图插件:模型工具 generate_image / image_to_image + 设置面板可编辑 API 配置 + 手动生图面板
Convert model-bound images to JPEG/PNG/WebP for LM Studio compatibility
Render local image files inline in the DSH conversation via a global show_image tool.
Use image-generation HTTP APIs as native image models in DeepSeek Harness
DeepSeek Harness plugin: typeset LaTeX as font-free SVG/PNG images, draw geometry and function figures from a declarative spec, convert formulas or SVG into embeddable images, and assemble documents with those images inserted
Normalize undersized Grok Responses images with Sharp while leaving supported large images unchanged.
DeepSeek Harness Web plugin: native image previews plus persistent non-image file-drop attachment cards
MxPage for DeepSeek Harness: ecommerce product-image workbench (analyze → plan → Visual Prompt Agent → generate) on top of an extracted, host-agnostic core of ziguishian/MxPage.
Hover-to-download buttons for images in DeepSeek Harness conversations.
Cordis plugin: image/video backgrounds for DeepSeek Harness web.
DSH web plugin: serve workspace image files over a constrained /dsh-image route so agents can embed images inline in conversation.
Renders chat Markdown image references () as a gallery under each closing assistant message
DSH tool plugin: generate images through ToAPIs async GPT-Image-2 API (submit task, poll, download).
图片处理:读取图片尺寸/格式、缩放与格式转换(内置 ffmpeg,跨平台)
Codex-style generated-image gallery and lightbox for DeepSeek Harness
DSH 高清图自动切片插件:发送前把大图切成 ≤800×800 小图,附带简洁设置页。
电商素材工坊(中英双语)。用户需要生成电商主图、详情图、场景图、产品图合成、品牌叠加时使用。自动识别品类→匹配风格→场景感知合成→统一文字→自动质检→多平台适配→标准化交付。E-commerce product image studio: category detection, style matching, scene-aware compositing, text overlay, quality check, multi-platform adaptation, batch delivery.
检测图像中的80类COCO目标(人、车、动物、日常物品等),输出边界框、置信度和类别标签。
Sprite Sheet Generator with AI Image Generation
Inline previews for the images an agent already produced in DeepSeek Harness: read_image attachments and local paths in any format (HEIC/TIFF/PSD/SVG/BMP/ICO/TGA/PNM/JP2 …), rendered through the official gallery and lightbox.
DSH 生图插件:在设置中配置多个生图供应商/模型,并在对话中通过 image_generate 调用当前选中的模型。
Agnes AI 图像 / 视频生成插件:注册 agnes_image 与 agnes_video 工具,内置跨进程 RPM 限流、429 退避与本地 ffmpeg 转 GIF;带 Web 配置卡(API Key / RPM 预设 / ffmpeg 检测)。
DeepSeek Harness background wallpaper plugin: upload an image and tune fit/scale/position/opacity/blur plus interface translucency, from a row at the bottom of Settings > General.