A Canva-owned AI platform for generating and editing images and short video — a deep model library, ControlNet-style control, a Realtime Canvas, upscaling, and custom model training.
Last verified · 2026-10-03 · by Moe Ameen
Leonardo AI (leonardo.ai) is a generative platform for creating and editing images and short video, built for creators, marketers, designers, and game and concept artists. It launched in 2022, grew a large creator community, and was acquired by Canva in July 2024 — its Essential tier now ships bundled with Canva Business, while Leonardo keeps running as a standalone power-user tool and its models also feed several Canva AI features.
The product runs on a token-based credit system — each action costs tokens by how heavy it is — with a free daily allowance and paid monthly tiers that unlock private generation, more tokens, and higher limits. What sets it apart from a plain prompt box is everything around the prompt: a deep model library spanning Leonardo's own Phoenix and Lucid models plus hosted third-party frontier models, so you can shift between cinematic, photoreal, illustrated, and fast-draft looks without switching tools.
On top of generation sit the control and finishing features: Image Guidance for ControlNet-style pose, depth, and structure conditioning; a Realtime Canvas that re-renders a sketch as you draw; inpainting and outpainting; a Universal Upscaler; background removal; and custom model training, where paid users fine-tune a model on their own reference images to keep a character or brand style consistent across a project. Motion adds image-to-video for short clips, and a pay-as-you-go API exposes the same generation to developers.
The most useful way to connect Leonardo to [Kompozy](/) is to treat Leonardo's output as a visual ingredient that feeds Kompozy's own generation, not just as a finished file to post. Leonardo's real strength is directed, consistent imagery — a custom-trained model or an Image-Guidance pass gives you a scene, a character, or a brand style you can reproduce. But a still on its own is not a content week, and Leonardo has no captioning, no reframing, no scheduling, and no publishing.
That is where Kompozy picks it up. Bring a Leonardo image into Kompozy as a brand asset or reference and it becomes raw material for formats Kompozy builds itself: a face-locked Persona Photo that stays on-model, a brand-exact Carousel or Quote Graphic rendered through [HyperFrames](/glossary/hyperframes), a thumbnail or background behind [Persona Shorts](/glossary/persona-shorts) and HeyGen avatar video, and a [blog article plus a newsletter](/glossary/output-buckets) that carry the same visual. A [Persona Brief](/glossary/persona-brief) holds one voice and your banned words across all of it, captions burn in, each output reframes to 9:16, 1:1, and 16:9, and [autopilot](/glossary/autopilot) schedules and publishes the whole batch across the eight social platforms plus blog and email through a per-post review step. Leonardo directs the pixels; Kompozy turns them into a finished, scheduled, multi-platform campaign.
Leonardo AI is a generative platform for creating and editing images and short video, aimed at creators, marketers, designers, and game and concept artists. It offers a deep model library (its own Phoenix and Lucid models plus hosted third-party models), ControlNet-style Image Guidance, a Realtime Canvas, inpainting, upscaling, and custom model training. It launched in 2022 and was acquired by Canva in July 2024.
There is a free tier at $0 with 150 tokens that reset daily, enough to genuinely try the tool (creations on the free tier are public). Paid plans are Essential at $12/month, Premium at $30/month, and Ultimate at $60/month, with more tokens, private generation, and higher limits; annual billing saves up to 20%. Token amounts and prices change, so confirm on the live pricing page.
Yes, through its Motion feature, which turns a still image into a short video clip. It is newer and narrower than the image side and than dedicated AI-video tools; heavy relaxed video use is gated to the top Ultimate tier.
No. Leonardo generates and edits images and short video but has no captioning, per-platform reframing, scheduling, or publishing. To turn its images into finished, scheduled posts, pair it with Kompozy, which uses a Leonardo image as a source to generate carousels, face-locked persona images, captioned short-form and avatar video, a blog, and a newsletter, then publishes them across the eight social platforms plus blog and email.