ai-boost/awesome-image-video-prompts

Copy-ready prompts for the leading AI video and image models, each with its real output and source. Plus agent recipes for editing video.

Awesome Image & Video Prompts is a curated collection of ready-to-use prompts for AI video and image generation models. Each prompt comes with its real output (a preview image or GIF) and a link to its original source, so you can see exactly what the prompt produced and where it came from.

What's inside:

  • Video prompts (102 entries) — organized by model: Wan 3.0, MiniMax H3, Seedance 2.5, Gemini Omni Flash, Kling 3.0, Veo 3.1, Veo 3, and Sora 2. Each entry includes the verbatim prompt, a preview, the source (a model maker's guide or a creator's X post), and the number of likes the post received.
  • Image prompts (33 entries) — grouped by style: posters and editorial layouts, photo-to-art conversions, photo realism, portraits, illustration, phone/UI mockups, maps, and collage.
  • Agent recipes for editing video (5 entries) — step-by-step workflows, like re-shooting an uploaded clip from new camera angles while keeping the action identical.
  • Guides and skills, plus a section on 3D with agents.

What makes it useful:

  • Copy-ready prompts — every prompt is quoted verbatim from its source, so you can copy it directly into a model.
  • Real examples — click any thumbnail to watch the original video with sound.
  • Annotations — each entry includes a short explanation of why the prompt works (e.g., how it splits a 15-second video into timed beats, or how it keeps a character consistent across scenes).
  • Tags — entries are tagged (e.g., portrait, handheld, night, character-consistency) so you can browse by theme.
  • Online gallery — search, filter, and copy prompts at agentcraft.dev.
  • Bilingual — available in English and Chinese.

History: The project was formerly called Awesome-GPTs; the original GPTs list still lives in a legacy file. The video sections follow the Artificial Analysis video arena ranking, and creator posts are sorted by likes.

In short: it's a well-organized, source-linked library of proven prompts for AI video and image tools, with real outputs to show what each prompt can do.

Related

  • Project
    kaomei/stickman-video-director

    An open‑source AI Skill that turns a simple topic into a full stick‑figure video plan—script, storyboard, and ready‑to‑use Gemini Omni Flash prompts—across four curated visual styles, enabling fast creation of educational or story shorts for platforms like YouTube, TikTok, and Instagram.

  • Project
    PyAV-Org/PyAV

    PyAV is a Python library that provides direct, low-level access to FFmpeg, allowing developers to programmatically manipulate media files, streams, and frames within their Python applications.

  • Project
    diffusionstudio/editor

    A video editing platform that treats projects as code, allowing AI agents to programmatically edit, transcribe, and render videos while providing a visual interface for manual refinement.

  • Project
    feitangyuan/onetake

    onetake is a Claude‑compatible AI skill that generates single‑take product launch or demo videos. It rebuilds UI in HTML, uses a library of measured motion primitives, adds realistic motion blur and room‑based sound, and automatically scores continuity with an oracle. Installable via a git clone, it works with Python, Node, and optional Whisper/TTS for narration. Non‑commercial use is free; commercial use requires a paid Pro license.