AI image and video generation platform — create production-quality visuals with fine-tuned models and a generous free tier.
leonardo.ai is an AI creative platform for generating images and videos. It offers a generous free tier with 150 daily tokens, multiple fine-tuned models for different styles, image-to-image editing, upscaling, and AI video generation. Train custom models on your own data for brand-consistent output.
Used by game developers, marketers, and designers for concept art, marketing visuals, and creative exploration.
Pricing model: Freemium
Common questions about Leonardo.Ai
Leonardo.Ai launched an agent that turns one idea into related creative assets. Leonardo says it can maintain a consistent identity across characters, scenes, band photos, album art and ads.
At launch, Leonardo offered the agent at no extra cost for a limited time, with generations using existing tokens.
Read the original announcement →
FLUX 3 Video is available on Leonardo.Ai, generating picture and sound together in a single pass, with clips up to 20 seconds.
Leonardo says it keeps characters consistent across chained multi-shot sequences and supports dialogue in multiple languages, plus cinematic and documentary-style looks.
Leonardo has added MiniMax H3 for generating video with a soundtrack. Leonardo says the model uses references to keep your character and voice consistent, and positions it for work across ads, e-commerce, gaming, and UI.
Nano Banana 2 Lite is live on Leonardo.Ai, with support for image and text references.
Leonardo says it generates images in seconds with sharp detail and readable text, and handles precise edits while keeping your subject consistent.
Gemini Omni Flash is live on Leonardo.Ai. You can generate 720p video clips up to 10 seconds long from a text prompt or reference image.
Leonardo says the model produces scenes with more accurate lighting, physics, and motion, grounded in narrative logic.
Happy Horse 1.1 is live on Leonardo.Ai, with reference images to guide scenes and keep your cast consistent.
Leonardo says the update also brings smoother motion, more expressive character performances, and richer built-in audio, including tighter lip-sync, better Foley sound effects, and ambient sound.
Seedance 2.0 now has native 4K video output in Leonardo.Ai. You can still combine image, video, and text references.
Leonardo.Ai says the 4K version keeps edges sharp and fine detail intact through motion.
Leonardo.Ai has added Grok Imagine 1.5 for turning a still image into a video with synchronized sound in a single generation. Output goes up to 720p and up to 15 seconds.
Leonardo.Ai now has 3D generation powered by Rodin V2. You can turn characters into 3D models directly on the platform.
OpenAI's GPT Image 2.0 is now available on Leonardo.Ai through a partnership with OpenAI.
Leonardo says the model offers clearer layouts, improved text rendering, and professional image quality from simple prompts.
Other products to explore and follow.
The people behind Leonardo.Ai
CEO (parent-company event report)
AI image creation and precision editing inside Google Workspace — generate from a prompt or a photo, edit individual objects, refine or translate text, and work on images with your team in Docs, Slides and Drive.
AI art platform — generate images from text, train custom models, edit with inpainting, and create consistent characters.
Node-based AI workflow platform by Figma — connect 12+ AI models with professional editing tools and share as simple apps.
Generate and edit images with ChatGPT — create illustrations, logos, mockups, and photorealistic visuals from text prompts.
Describe a web app in plain language and get a working full-stack build — UI, database, and deployment — then iterate by chatting with the AI.
A generative media platform and inference API for running fast image, video, and audio AI models at scale.
