Canva's new Craft image model plans layouts first and splits images into editable layers
alex_verem · x · 2026-10-25
@alexprompter shares 7 prompts for Canva's new image model Craft: it plans the layout before drawing, renders readable text, and can split any image into editable layers. Available via Dream Lab in Canva. A practical guide to treating it as a $63K/year graphic designer.
More from Multimodal
- MiniMax H3 & Z-Image Turbo Turn Out a Studio-Quality Photoreal Portrait — No-While1332 · 2026-10-25
- N17's outputs dubbed 'The N17 School of Abstract Expressionism' — snikolov · 2026-10-25
- FastSDCPU release brings Flux 3 Image Klein OpenVINO support, 2-4 step image gen on CPU — simpleuserhere · 2026-10-25
- "Smoothest transition ever": AI video demo stirs tool guesses — aitrendz_xyz · 2026-10-25
- Lonecatone's MOSS control nodes break in latest ComfyUI 0.42.5 — HQuasar · 2026-10-25
- One prompt, four approvals: Claude produces a 78-second cartoon explainer video — alex_verem · 2026-10-25