image-to-prompt 开源项目推荐（43 个）

kevinchin12 /ImageLens

一个可以帮你快速反推出网页上图片的提示词，并快速生图测试提示词效果的 Chrome 扩展：从网页图片反向推断提示词，并通过实时生成即时验证。

papperrollinggery /zhijuan-prompt-card

Local-first Chrome extension that turns images into generator-ready prompts.

binghe1980 /PromptLens

一款把任意图片转换为专业生图提示词的 Chrome / Edge 浏览器插件。支持网页右键识图、本地上传与剪贴板粘贴，生成中文、英文和 JSON 提示词，并提供历史记录与收藏。

wk240 /oh-my-prompt

提示词管理工具，Chrome 扩展，告别复制粘贴，在任意平台一键插入你的提示词。无需离开创作界面。

gracech0322-cmd /promptlab-image-video-to-prompt

PromptLab is a free and open-source image and video prompt generator. It turns local videos and web/local images into ready-to-use prompts, with Video to Prompt output generated in a Seedance 2.0-style prompt format.

jiemianduan /image-to-prompt

An open Agent Skill for reconstructing faithful, reusable image-generation prompts from reference images.

Technicalflight /image-prompt-reverse

把一张图片逆推成生成提示词（Image to Prompt）：中英双语重建提示词 + 风格标签 + 结构化 JSON prompt，零依赖校验脚本 | Forensic image-to-prompt reconstruction. AGPL-3.0 · Commercial use requires license.

ZenHG /ComfyUI-MOSS-Storyboard

ComfyUI nodes for MOSS-Image: storyboard grids, layout editor, crop/paste, face swap, and an LLM prompt node (caption/expand/edit/assemble) with up to 9 reference images and MiniMax-H3 output. Zero deps, MIT. ｜ 中文：MOSS 故事板/布局/裁贴/换脸 + LLM 提示词节点（9 图、H3 格式）；零依赖，MIT。

Twilight1971 /prompt-generator-ollama

Windows image-to-prompt app using local Ollama vision models

phibbyrizz /ComfyUI-Prompt-Studio

Turn reference images and simple ideas into production-ready image prompts and MiniMax H3 video scripts inside ComfyUI.

sundny8 /visual-reverse-engineer

Image and video prompt reverse engineering: Visual DNA, reference consistency, style analysis, and structured image JSON.

MrDouZheng /text-to-image-prompt-reverse-engineering-replication

终极无敌文生图反推提示词｜参考图反推与图片复刻，由 ChatGPT 6 Astra Ultra 生成。Ultimate text-to-image prompt reverse engineering, image-to-prompt and reference image replication. 中英说明 / Chinese & English guide.

cooky-dance /HoverPrompt

Free Chrome/Edge image-to-prompt for designers, creatives, product & AI film/video. Own API key or Ollama (keys encrypted, on-device only). Optional cloud 10/mo + 20 gift. CLI: account credits + drive extension auto-scan & prompts.

QingYunA /picpocket

Chrome side-panel extension that turns any image on the web into an AI prompt — save, reverse into Subject · Style · Lighting · Composition, and generate. Local-first, BYOK.

runapi-ai /midjourney-mcp

RunAPI Midjourney MCP server for image and video generation: create tasks, poll results, and check pricing across 3 model variants from Claude Code, Codex, Cursor, and VS Code.

TravorShelby /content-to-prompt

Agent Skill for turning reference media into reusable prompt packs, shotlists, video packaging prompts, thumbnail prompts, and content systems.

NayutaViz /PromptPaw

PromptPaw 是一款面向 Chrome 与 Microsoft Edge 的本机浏览器扩展。选择网页中的图片后，它会调用你配置的视觉模型，生成可编辑的中文、English 和 JSON 提示词，并可把提示词与参考图带到 ChatGPT 或 Gemini——只填入，不自动发送。PromptPaw is a browser extension that turns selected web images into editable Chinese, English, and JSON prompts using your configured vision model, then sends the prompt and reference image to ChatGPT or Gemi

sebyrockcostantino /click2prompt

Estensione Chrome gratuita: click destro su qualsiasi immagine e ottieni il prompt per ricrearla con l'IA. Nessun account, nessun server.

pixelgraple /KREA2-Vision-Suite

Free, local-first Discord Vision interrogation with three grounded prompts, optional KREA2 guidance, and local or Vast GPU models.

dingge001 /promptary

Reverse-engineer any web image into a ready-to-use AI art prompt. Local-first Chrome extension, bring your own API key