Zenboard – A native macOS reference board for creatives
Click-through Ghost Mode overlay beats PureRef, but macOS-only limits reach.

Drop images on a canvas instead of writing prompts — genuinely different from Midjourney.
Designers and creatives making social content
Midjourney · Stable Diffusion · Adobe Firefly
> More models > More settings > More prompt tricks
We think creative tools should go the other direction.
We’re building Pantr AI, a visual-first AI workspace where you generate images from references on a canvas.
We believe in: Less options. More intuition.
We just opened the beta and are looking for designers, creatives, and people making social content to test it and share feedback.
If you need some more initial credits please get in touch.
Click-through Ghost Mode overlay beats PureRef, but macOS-only limits reach.
Canvas metaphor for creative agents when chat interfaces dominate.
Infinite canvas terminal with minimap—tmux tabs but actually visible.
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.
Combines an infinite canvas, scene-level controls (camera, motion, zoom), and side-by-side multi-model comparison so you can prototype a video across Kling/Runway/Pika without changing tabs. Smart touches — character consistency, built-in upscaling and background removal, and storyboard-style scenes — show clear product thinking. The idea isn’t alone in the market, but pulling many heavyweight models into one visual workspace is an audacious, useful play if the integrations are robust.
Another infinite canvas tool competing with Notion, Miro, and Heptabase without clear differentiation.