waoowaoo

waoowaoo is an AI creative workspace for images and videos, currently in preview release. It lets users develop project briefs with a right-hand Assistant, upload reference material, and organize and inspect generated assets on a canvas. Key capabilities include: - Model-aware generation with configurable aspect ratios, durations, resolutions, and reference roles. - Supported modes: first-frame, first/last-frame, and reference-image modes, depending on the selected model. - Refinement of existing results into new versions while retaining originals. - OpenRouter configuration exposed in this preview, with access to models such as GPT Image 2, Nano Banana variants, Seedance variants, and MiniMax H3 / H3 Max. Provider availability and charges apply. - Local project data and media stored via local database and private MinIO (S3) storage; prompts and references sent to the provider for AI tasks. The application UI supports Chinese and English. Japanese and Korean are README translations only. The recommended deployment path uses prebuilt Docker images, so Node.js, MySQL, Redis, Temporal, and FFmpeg need not be installed on the host. The Compose setup includes Caddy for HTTPS (default entry: https://localhost:1443). Users add their own OpenRouter API key in the application's API configuration; provider calls are paid through the user's own account. Tech stack: Next.js 16 + React 19, MySQL + Prisma ORM, Temporal for durable execution, Redis for transport and cache, private MinIO for media storage, Tailwind CSS v4, and NextAuth.js for authentication. Starting with v0.5.0-beta.1, the distribution is licensed under Elastic License 2.0. Personal use, internal business use, modification, and redistribution are permitted subject to its terms, but providing third parties with hosted or managed access to a substantial set of features requires separate permission. This is source-available software, not OSI-approved open source.