AI-assisted storyboard and video generation tool. Uses Gemini for generating storyboard text and frames, Vertex AI Veo for generating transition clips, and ffmpeg for stitching the final video. Built-in logs and gallery management.

Curated, original high-craft prompts for AI video ads (Seedance 2.0 / Veo 3 / Kling / Runway). Companion to HeyDreaming.

Open-source, bilingual AI video-prompt skill — rewrite ideas into model-ready text-to-video prompts. A portable Agent Skill (Claude Code, Codex, OpenClaw, Hermes); generate via Atlas Cloud — Seedance 2.0, Kling, Veo, Hailuo, Wan, Vidu, Gemini Omni, Grok Imagine.

AI Image & Video Generator powered by Google Gemini & Veo 3.1. Create images, videos, stickers, slides, and convert PDFs to editable PPTX. 100% client-side, no backend. | Gemini + Veo 3.1 驅動的 AI 圖像與影片生成器，支援簡報轉 PPTX。

Open-source Veo video generator — production-ready Next.js SaaS for text-to-video, image-to-video, and multi-image editing powered by Google Veo. Stripe billing, credits, NextAuth, and Prisma out of the box.

Local-first AI creative pipeline for persona-based image/video generation. Identity preservation, visual engines, quality scoring, autopilot mode. Gemini + VEO 3.1.

Reliability toolkit for Google Flow — HAR forensics, fan-out analysis, eng brief. Not a bypass tool.

Runnable Node.js examples for the Google Flow API by useapi.net — generate Veo 3.1 video, Gemini Omni Flash audio-native video, and Nano Banana / Imagen 4 images through a simple REST API.

Build clean, structured video prompts for Seedance and other text-to-video models (Kling, Runway, Veo) from simple inputs.

MCP server for kie.ai — 45+ image, 70+ video, 20+ audio models with built-in Averiguare model intelligence. Dual-mode (stdio + HTTP) for Claude Code & Cowork.

API-key-free MCP server for Google Gemini: Gemini-CLI backend (ask, web search, deep research, code/file/URL analysis, structured output) + web-UI image (Nano Banana) & video (Veo) generation. 15 tools.

Claude skill: write production-ready UGC video prompts and render them via official APIs (Seedance/Kling/Veo/Sora/Hailuo)

Type one sentence, get a 60-second pitch video. An agent orchestrates Gemini 3.1 Pro, Nano Banana 2, Veo 3.1 Fast, Lyria 3 and Gemini TTS through a wizard-driven editor — async background renders, share link by email.

Turn one concept into a structured, shot-by-shot prompt sequence for text-to-video models (Seedance, Kling, Runway, Veo). Storyboard your AI video in seconds.

Runnable Node.js examples for the PixVerse API by useapi.net — drive your own PixVerse account over REST: native PixVerse V6 / C1 video (audio, multi-shot, 900+ effects) plus the frontier models PixVerse hosts (Seedance 2.0, Kling V3, Veo 3.1, Sora 2, Grok Imagine) and images (Nano Banana, GPT Image, Seedream, Qwen). Text/image-to-video.

Agentic music-video studio using Gemini 3 Flash, Managed Agents, Veo, and Lyria

Agent-first short-form AI video generation CLI and MCP server for Sora, Veo, xAI and Seedance

Runway API examples (useapi.net) — one Runway account, REST access to Runway's own Gen-4.5 / Gen-4 / Aleph video + Frames images and the frontier models Runway hosts: Veo 3.1, Sora 2, Kling, Seedance 2.0, Wan, FLUX.2, Nano Banana, GPT Image — plus Act-Two, lip-sync, and Topaz 4K upscale. Drives your own account, no per-call metering.

Server-side PoYo examples for Veo 3.1 Official video generation workflows.

Runnable examples for the MiniMax (Hailuo) API by useapi.net — one account, REST access to Hailuo 01 / 02 / 2.3 video plus the frontier models MiniMax hosts: Midjourney V7, Veo 3.1, Sora 2, Nano Banana, GPT Image and Seedream. Multi-account load-balanced, no per-call metering.