Canva unveils Craft, its first frontier design-focused image model, claiming #2 on DesignArena
HeyAmit_ · x · 2026-10-23
Canva introduced Craft, its first frontier image generation model built specifically for design, claiming the #2 spot among image labs on DesignArena's global leaderboard.
Unlike typical prompt-to-pixels models, Craft plans the composition first—deciding where elements go, what deserves attention, and which text must appear—before rendering, tackling the hard problem of exact layout and text. The companion Magic Layers feature turns any result into an editable design in one click, closing the gap between generating a picture and producing something usable.
More from Multimodal
- FAPL From HKUST and Tencent Makes Video DiTs Actually Use MLLM Latents — tencent · 2026-10-23
- Oxford-NUS survey unifies video understanding and generation under world modeling lens — Shengqiong Wu · 2026-10-23
- Open-source ComfyUI node boosts batch diversity by coupling initial noise, no extra steps — Current-Ad-198 · 2026-10-23
- Fudan's Code2Video-Compass benchmarks 15 MLLMs on code-based video generation across 2,104 tasks — Fudan-University · 2026-10-23
- Krea2Edit detail loss resists every fix: samplers, upscale passes, LoRAs all fail — taurine_bitch · 2026-10-23
- Creator says SeeDance 2.5 generation cost is the only bottleneck for great AI video — AIandDesign · 2026-10-23