raojiacui/prompt-lens

反推出AI视频的提示词，并配有音频分析功能，可提取视频中的台词文案，并且一句话就可剪辑出你要的视频

What it solves

PromptLens helps AI video creators overcome creative blocks and the difficulty of writing effective prompts. It allows users to reverse-engineer the visual style, scenes, and actions of existing AI videos to learn how to replicate or adapt successful creative ideas for their own content.

How it works

Users upload a video or image, and the tool uses AI to analyze keyframes, scenes, and movements to extract descriptive prompts. These prompts can then be modified by the user to adjust styles or characters and fed into AI video generation APIs to create new videos. The system also includes audio transcription and intelligent segmentation to help users analyze scripts and edit video clips.

Who it’s for

AI video creators, short-form content producers, and digital artists who want to analyze successful AI-generated videos to improve their own prompting and production workflow.

Highlights

  • Reverse Prompting: Automatically extracts prompts from uploaded videos or images using AI analysis.
  • Multi-API Support: Integrates with Zhipu AI, Google Gemini, and OpenRouter for analysis, and Kie.ai for video generation.
  • Audio Analysis: Transcribes audio and uses LLMs for intelligent segmentation of scripts.
  • Video Editing Integration: Supports basic trimming and concatenation via a self-hosted FFmpeg service.
  • Full Creative Loop: Provides a workflow from inspiration (analysis) to modification (prompt editing) to production (generation).

Related

  • Project
    op7418/guizang-product-video-skill

    The repository provides an AI‑driven “skill” that turns a software project’s recent updates into a short promotional video. It extracts changelog items, re‑uses the product’s UI components, writes copy, animates with GSAP/Three.js, synthesises music and sound effects, and finally exports an MP4 plus an editable video project. The skill is installed via the Vercel Skills CLI and works with Claude Code, Codex, or similar AI coding assistants.

  • Project
    linzzzzzz/openclip

    An automated AI pipeline that extracts engaging highlights from long videos and livestreams, providing transcription, AI analysis, and automatic clip generation with subtitles and covers.

  • Project
    harry0703/MoneyPrinterTurbo

    MoneyPrinterTurbo is an open-source tool that turns a simple topic or keyword into a complete AI-generated short video, handling scriptwriting, footage selection, voiceover, subtitles, and music automatically, with support for batch generation and direct publishing to social platforms.

  • Project
    ashbuilds/payload-ai

    A Payload CMS plugin that brings LLM‑driven content generation, proofreading, translation, and voice/image creation into the CMS. Supports multiple AI providers, per‑field prompts, access control, and custom model integration. Install via `pnpm add @ai-stack/payloadcms`, configure in `payload.config.ts`, and add the Lexical editor feature to fields. Advanced options include multi‑tenant secret handling, custom media upload, and a resolver for reference images.

  • Project
    SamurAIGPT/Clip-Anything

    A multimodal AI tool that extracts specific moments from videos using natural language prompts by analyzing visual, audio, and sentiment cues.