Brood, a reference-first AI image editor for macOS
References-first beats prompt engineering, but macOS-only and requires API keys.

Click-through Ghost Mode overlay beats PureRef, but macOS-only limits reach.
Digital creatives (designers, illustrators, 3D artists, writers) working on Apple Silicon Macs
PureRef · Moodboard.app
It is still in beta, and there is much room for improvement. It is provided for free, so if you were looking for something like this, please feel free to use it.
References-first beats prompt engineering, but macOS-only and requires API keys.
Drop images on a canvas instead of writing prompts — genuinely different from Midjourney.
Single canvas that lets you chain prompt → image → short-video steps is the clearest selling point — it actually maps to how agencies iterate on concepts. The UI shows practical controls (seed, aspect, duration hints) and multi-provider routing under one roof, which cuts context switching. That said, this is a crowded space (Runway/Replicate/large vendors do parts of this) and the page leaves questions about model provenance, failure modes, and output consistency.
Reference-first canvas with real-time proposal copilot, but macOS-only and early-stage.
Multi-shot narratives and reference consistency beat one-prompt-one-clip rivals, but execution unclear.
The pitch hooks on text-to-video plus a multi-frame reference workflow — upload up to nine keyframes and it claims high consistency, which is the one thing most consumer video AIs struggle with. The landing page sells handy presets (ads, viral trends, holiday cards) and a studio tier, but there’s little technical proof or sample output on the page, so the claims (99.8% consistency) feel like marketing until you see artifacts, length limits, and pricing details.