SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18

Image Processing & Optimization

对已有图像执行确定性变换和优化:裁剪、缩放、压缩、格式转换、水印、去背景、像素比较、切块、TIFF 解码与尺寸读取等。不进行模型语义推理,也不生成新的图像内容。

Use keyword search
Source catalog discovery.composite.2026-09-06.v1-0-5.b92b985e31dfCanonical structure · 823 nodes · 14829 plugins

Leaf membership

46 plugins

dsh-screenshot-diffPangYiMing/dsh-screenshot-diffCatalog AnalyzedDSH plugin: pixel-diff two screenshots into diff.png + triptych (pixelmatch) — 像素对比工具Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-simpletex-ocrHuoer9527/dsh-simpletex-ocrCatalog AnalyzedDSH plugin from Huoer9527/dsh-simpletex-ocrVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-tesseract-ocrdsh-tesseract-ocrCatalog AnalyzedLocal OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.3.8Evidence updated2026-09-07Public signals5 stars · 0 downloadsdsh-tool-describe-imagesoli0x4ea/dsh-tool-describe-imageCatalog AnalyzedDSH plugin from soli0x4ea/dsh-tool-describe-imageVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-tool-imagegenGithub-CJX/dsh-tool-imagegenCatalog AnalyzedOpenAI-compatible image generation in DSH Desktop chat: generate inline, edit reference images or chain-edit previous results directly (image-to-image) without re-uploading, with storage cleanup.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-tool-read-tifffulander0301/dsh-tool-read-tiffCatalog AnalyzedModel-facing read_tiff tool for DeepSeek Harness: decodes TIFF/TIF images (multi-page, LZW/Deflate/PackBits/CCITT/JPEG compression, bilevel, 8/16-bit and float) into viewable PNGs with full header metadata, plus optional vision-model description.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-v4flash-tilerdoublehappy123/dsh-v4flash-tilerCatalog AnalyzedDSH plugin: auto-tiles oversized chat images into labelled grid tiles for DeepSeek v4Flash vision, with Python tiling engineVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-visibridgelhbsaa/dsh-visibridgeCatalog AnalyzedStructured vision evidence (OCR/layout/semantics) plus a USB camera capture tool for a "shoot-look-adjust" debug loop; backends: Ollama, DeepSeek, Xiaomi.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-vision-bridgeShiraGawaAnri/dsh-vision-bridgeCatalog AnalyzedDSH profile Plugin包:当会话使用不支持图片的模型(如 DeepSeek)时,不再弹出 "当前模型不支持图片"之类的拦截,而是调用工具进行视觉识别Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision-fallback-bridgebaizhichen-web/dsh-vision-fallback-bridgeCatalog AnalyzedLightweight DeepSeek Harness upload bridge: images and common documents become workspace paths so text-only DeepSeek models can read them with Qwen-MM-Plugins vision tools.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision-LMstudioTiankunDai/dsh-vision-LMstudioCatalog Analyzed让你能通过deepseek harness调用LM studio加载的本地视觉模型Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-vision-no-visionwdwind/dsh-vision-no-visionCatalog AnalyzedDeepSeek Harness native vision plugin!Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-vision-pluginZhangbo-cn/dsh-vision-pluginCatalog AnalyzedDSH plugin from Zhangbo-cn/dsh-vision-pluginVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision-solutionbr1nosense/dsh-vision-solutionCatalog AnalyzedGive DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsecommerce-material-studiojiawood2006/ecommerce-material-studioCatalog AnalyzedBatch e-commerce product image compositing tool. 电商批量合成素材。Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsfree-vision-skillniyongsheng/free-vision-skillCatalog AnalyzedFully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals5 starsimage-mcpTOBYCAI/image-mcpCatalog Analyzed本地 Pillow 图片处理 MCP:12 工具(信息/缩放/裁剪/转换/压缩/旋转/翻转/缩略图/水印/特效/占位/叠加),离线零成本,经 dsh-mcp-client 接入 DSH。Local Pillow image MCP with 12 tools for DeepSeek Harness, offline & free. | Platforms: macOS/Windows/Linux (Python+Pillow)Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsmodlens@liustack/modlensCatalog AnalyzedVision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact3.25.4Evidence updated2026-09-06Public signals3868 stars · 145389 downloads

Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.