Leonardo.ai
Image and video generation with a canvas, Motion animation and third-party video models
Leonardo.ai is a web and mobile creative platform for image generation, image editing on a canvas, short video clips and custom model training. Since Canva acquired it in 2024, it has added third-party video models (Kling 3.0, Veo 3.1, Hailuo) next to its own Motion 2.0 animation tool. Its API moved to pay-as-you-go credits in 2026.
- 19 creators using
- 1 news item tracked
- 2022 first launched
- Freemium pricing
- Easy learning curve
What Leonardo.ai can do
- Infinite canvas Yes
- AI agent Not confirmed
- Node / flow builder Partial
- Public API Yes
- MCP server Not confirmed
17 of 26 capabilities confirmed
| Capability | Supported | Details |
|---|---|---|
| Text to image | Yes | |
| Image editing | Yes | Canvas inpainting and outpainting |
| Text to video | Yes | Video tool; Veo 3.1, Kling 3.0, Motion 2.0 |
| Image to video | Yes | Motion 2.0 (Fast by default from a generated image) or uploaded start frame, paid plans only for uploads |
| Video to video | Not confirmed | |
| Native audio in video | Partial | Some models (Veo 3, Kling 3.0) add sound; depends on the model chosen |
| Lip-sync | Not confirmed | |
| Voice / TTS | Not confirmed | |
| Music & SFX | Not confirmed | |
| Upscaling | Partial | Motion 2.0 video upscaling from 480p to 720p |
| Character consistency | Partial | Consistent Character Engine |
| Camera control | Partial | Motion Controls for camera moves, Motion 2.0 only; prompt-only camera moves are inconsistent |
| Custom training | Yes | Custom models on paid plans |
| Third-party models | Yes | Serves Kling, Veo, Hailuo, Seedance and others alongside Leonardo models |
| Capability | Supported | Details |
|---|---|---|
| Infinite canvas | Yes | AI Canvas (inpainting, outpainting) and Realtime Canvas |
| Node / flow builder | Partial | Blueprints (reusable multi-step workflows) run through the API |
| AI agent | Not confirmed | |
| Chat assistant | Not confirmed | |
| Team collaboration | Partial | Team features on higher tiers |
| Capability | Supported | Details |
|---|---|---|
| Public API | Yes | REST API, pay-as-you-go credits |
| MCP server | Not confirmed | |
| Mobile app | Yes | iOS and Android apps |
| Desktop / local | No | |
| Open source | No |
| Capability | Supported | Details |
|---|---|---|
| Free tier | Yes | Daily token allowance; generations are public |
| Commercial use | Yes | Commercial rights on paid plans |
Yes Partial No Not confirmed by the vendor
What makes Leonardo.ai different
- 01
Canvas-first editing (AI Canvas for inpainting and outpainting, plus a realtime mode) in the same tool as image and video generation
- 02
Several model families under one account, including Leonardo's own Lucid and Motion 2.0 alongside third-party video models such as Kling 3.0 and Veo 3.1
- 03
Custom model training on paid plans, so a single visual style can be reused across a set of stills
- 04
Generated images on paid plans are commercially usable, and free-plan output is public
- 05
Free tier with a daily token reset, so it can be tested without a card before committing to a paid plan
About Leonardo.ai
Leonardo.ai runs on a token allowance. Each image or video costs tokens that depend on the model, resolution and speed setting, and the free plan gives a small daily token allowance. The platform has its own Lucid models and Motion 2.0 video model, and it also serves models from other companies. Most of those are added and retired on short notice: Motion 1.0 was removed on June 17, 2026, Veo 3 on June 29, 2026, and Sora 2 on July 9, 2026 after provider-side changes.
For filmmakers the useful parts are concept art, mood boards, key art, animatic stills and 5-second motion clips from a still frame. Video is short and not a sequence tool. Motion Controls (camera moves) only work with Motion 2.0, and prompt-only camera directions give inconsistent results. Custom model training on paid plans can hold a look across a set of stills, which helps a visual style stay locked across a short project.
The 2026 change that matters most is the move of the API to separate pay-as-you-go credits. Leonardo sells best to people who want several image and video models under one subscription. It is a weaker choice for precise, long-form video or for anyone who needs predictable per-clip costs.
What's new in Leonardo.ai
-
Sora 2 and Sora 2 Pro removed from the API
Provider-side change; Leonardo points API users to veo-3.1 models instead.
Source: docs.leonardo.ai ↗ -
Motion 1.0 retired June 17; Veo 3 retired June 29
Motion 1.0 (svd) is replaced by Hailuo 2.3; Veo 3 and Veo 3 Fast move to Veo 3.1 and 3.1 Fast.
Source: docs.leonardo.ai ↗ -
API switched to pay-as-you-go credits
API access is bought as dollar credits on the API Access page, separate from web subscriptions, with a bearer key and webhooks.
Source: docs.leonardo.ai ↗ -
Video tool adds Veo 3 and Kling 3.0 with sound
The Video tab offers Motion 2.0, Veo 3 and Kling Video 3.0; Motion Controls and Motion Elements work only with Motion 2.0; watermark removal needs a paid plan.
Source: intercom.help ↗
Models available in Leonardo.ai
-
Veo 3.1 Latest $$$ Google Replaces retired Veo 3 and Veo 3 Fast (June 2026) Also: Veo 3.1 Fast
-
Seedance 2.0 $$$ ByteDance 1.0 Lite retired May 2026; 2.0 offered as the premium option Also: Seedance 1.0 Pro Fast
-
Kling Video 3.0 Latest — Kuaishou Generates sound with the video; editing on some models
-
Hailuo 2.3 Latest — MiniMax Leonardo's recommended replacement for Motion 1.0
-
Motion 2.0 Latest — Leonardo.Ai 5-second clips; Motion Controls and Motion Elements; default for image-to-video
-
$ · $$ · $$$ = relative cost against other models of the same type, on fal.ai list prices. Cost inside Leonardo.ai depends on its own plans and credits.
Key Features
- Image generation on Leonardo's Lucid models and third-party models
- AI Canvas for inpainting, outpainting and region edits, plus a realtime canvas mode
- Video tool with Motion 2.0 (5-second clips), Veo 3.1, Kling 3.0 and Hailuo models
- Motion Controls for camera moves (Motion 2.0 only) and start or end frames on some models
- Custom model training (LoRA-style) on paid plans
- Consistent Character Engine
- REST API with pay-as-you-go credits and webhooks
- iOS and Android apps alongside the web app
When to reach for it — and when to skip
Reach for it when…
- One account covers stills, canvas editing and short video with several model families
- Free tier is usable for testing, and paid output is commercially usable
- Custom model training helps keep one look across a short project
- API and webhooks are workable for batch concept art and previz pipelines
Skip it when…
- Video is short (about 5 seconds on Motion 2.0) and not built for sequences or dialogue scenes
- Hosted third-party models are removed on short notice, so a workflow that depends on one can break mid-project
- Token costs vary by model and setting, so a monthly budget is hard to predict
- Camera-move prompts are inconsistent, and Motion Controls only work with one model
Best For
✓ Ideal for
- Concept art and key-art stills that later become motion tests
- Animatic and previz stills turned into 5-second motion clips
- Custom-trained visual styles for a short film or music video look
- Studios that want stills, canvas edits and several video models under one subscription
- Teams building batch image jobs through the API
✗ Not built for
- Finished video or long takes that need dialogue, lip-sync or consistent multi-shot continuity
- Productions that need predictable per-clip costs or a long-term model roadmap
- Work that needs a visual agent or node-based pipeline builder (none found)
Working Tips from Filmmakers Using Leonardo.ai
- 01 Pick the video model before generating: Motion Controls only work with Motion 2.0, and Veo or Kling have their own settings. Check the token cost shown before you run a batch.
- 02 Animate from a generated still with Motion 2.0 Fast first, then re-run the keeper at full quality. Fast costs fewer tokens.
- 03 Set camera moves with Motion Controls, not prompt wording. Prompt-only pans and tilts are inconsistent, and tilts rarely work.
- 04 Do not build a project on one hosted model. Check the model list before a shoot, since Motion 1.0, Veo 3 and Sora 2 were all removed in June and July 2026.
Leonardo.ai pricing in 2026
| Plan | Price | What you get |
|---|---|---|
| Free | $0 monthly |
|
| API | Pay as you go usage |
|
Prices checked against Leonardo.ai's pricing page on 9 Oct 2026. Vendors change plans often, so confirm before you buy.
Leonardo.ai vs Midjourney vs Flux vs Adobe Firefly
| Leonardo.ai | Midjourney | Flux | Adobe Firefly | |
|---|---|---|---|---|
| Price | See the vendor's pricing page | From $10/mo ($8/mo billed annually); 20% off on annual plans | Pay per image on the API, from $0.014 (FLUX.2 klein 4B). Open weights are free for non-commercial use; commercial open-weights licences are quoted by sales. | Free daily generations, or Standard from $9.99/mo (2,000 credits); Pro Plus and Premium have a 30% first-year promo ending Oct 21 |
| Infinite canvas | Yes | Partial | No | Yes |
| Node / flow builder | Partial | No | No | Not confirmed |
| AI agent | Not confirmed | No | No | Yes |
| Chat assistant | Not confirmed | No | No | Yes |
| Team collaboration | Partial | Partial | Not confirmed | Yes |
| Text to image | Yes | Yes | Yes | Yes |
| Image editing | Yes | Yes | Yes | Yes |
| Text to video | Yes | Not confirmed | Yes | Yes |
| Image to video | Yes | Yes | Yes | Yes |
| Video to video | Not confirmed | No | Partial | Yes |
| Native audio in video | Partial | Not confirmed | Yes | Not confirmed |
| Lip-sync | Not confirmed | No | Yes | Not confirmed |
| Voice / TTS | Not confirmed | No | Partial | Yes |
| Music & SFX | Not confirmed | No | Partial | Yes |
| Upscaling | Partial | Yes | Yes | Yes |
| Character consistency | Partial | Partial | Partial | Partial |
| Camera control | Partial | Not confirmed | Partial | Not confirmed |
| Custom training | Yes | Partial | Yes | Yes |
| Third-party models | Yes | No | No | Yes |
| Public API | Yes | No | Yes | Yes |
| MCP server | Not confirmed | No | Yes | Not confirmed |
| Mobile app | Yes | Not confirmed | Not confirmed | Not confirmed |
| Desktop / local | No | No | Yes | Partial |
| Open source | No | No | Partial | No |
| Free tier | Yes | No | Partial | Yes |
| Commercial use | Yes | Yes | Partial | Yes |
Each column comes from that tool's own researched page. "Not confirmed" means the vendor doesn't say.
Open the full Leonardo.ai vs Midjourney vs Flux vs Adobe Firefly comparison →Use Cases
Integrations
Tags
Creators Using Leonardo.ai
AI Filmmaker • AI Automation Specialist • Cinematic Storyteller • Generative AI Creator
AI Filmmaker - Cinematic Storyteller - Google Flow - Seedance - Pixverse - Kling - Sora - Runway - Hailuo - NanoBanana - GPT - Flux - Gemini
AI Filmmaker • Video Editor • AI Content Creator
Sources
Facts on this page were checked against Leonardo.ai's own pricing, product and changelog pages on , then cross-checked with independent coverage where vendor pages were silent. Anything we couldn't confirm is marked "Not confirmed" rather than guessed.
- Leonardo pricing page (HTTP 403 to research fetch; not verified directly) leonardo.ai
- Leonardo API deprecations and changes docs.leonardo.ai
- Leonardo API quick start (updated 2026-06-26) docs.leonardo.ai
- Leonardo help: Video (dated Feb 18, 2026) intercom.help
- Third-party 2026 pricing summary (updated Oct 9, 2026; cites July 2026 pricing) dailyaifixs.com
- Leonardo rebrand and Creative Engine API (Feb 2026 coverage) coherentmarketinsights.com
- Black Forest Labs (FLUX) pricing, used for comparison column bfl.ai
Spotted something out of date? Tell us and we'll re-check it.
Discussion
No comments yet — be the first.