Leonardo.Ai Release Notes

Feature Release: Veo 3 & Veo 3.1 , the new state-of-the-art video model, now on Leonardo.Ai

Introduction

Leonardo.Ai brings best-in-class video generation with Veo 3 and Veo 3.1 by Google.

Veo 3 delivers enhanced realism, improved physics, and native audio generation -including dialogue - so you can create fully realised videos without post-production. Veo 3.1 builds on this foundation with sharper realism, smarter motion, enhanced expression, and greater creative control over how your story unfolds.

Read on to find out why they're great for video creation and story telling, the differences between the models, and how to get the best results out of them.

What’s the Difference Between Veo 3 and Veo 3.1?

Veo 3.1 builds on Veo 3 with additional creative control and improved realism. Faster versions of each model are available with Veo 3 Fast and Veo 3.1 Fast, for more affordable and rapid ideation.

Veo 3 Includes:

• Text-to-Video generation
• Image-to-Video (Start Frame support)
• Native audio generation (including dialogue)
• Strong prompt adherence
• 4, 6, or 8 second duration options
• 720p and 1080p resolution (same token cost)
• Veo 3 Fast mode (lower cost, faster generations)

Veo 3.1 Includes Everything in Veo 3, Plus:

• End Frames: Upload an image to define how your video ends. This allows precise control over the final shot and improves scene continuity. Note that when using an End Frame, a Start Frame is required.
• Enhanced Image-to-Video Fidelity: Improved realism, better motion quality, stronger depth and consistency
• Smarter Physics & Expression: More natural human movement, improved emotional detail, more believable gestures and reactions.

Core capabilities of the Veo 3 suite of models

• Native Audio Generation: Audio is generated automatically with Veo videos. You can add audio cues directly in your prompt, for example :
  • “The sound of an ice cream truck plays in the background.”
  • “The captain turns and says, ‘We set sail at daybreak.’”
  • audio: sound of keyboard typing and soft ambient AC hum
  • Note that audio cannot currently be turned off.
• Multi-Modal input support: You can combine text prompts and image prompts (start and end frames where applicable).

How to generate videos with Veo 3

1. From the home page, navigate to the AI Video Creation tool by clicking Video beneath the prompt bar or in the left side bar
2. Click the Models menu in the side bar
3. Select Veo 3 Fast, Veo 3, Veo 3.1 Fast or Veo 3.1 from the Models menu.
4. Enter your text prompt, and click Generate. To get the most out of your videos, check out this blog for tips on mastering prompts for Veo models.

Optional: Add a start and end frame (where applicable).

Veo 3 Image to Video - Using a Start Frame

You can now have even more control over your Veo 3 outputs by using an image as a start frame. Combined with your prompt, Veo 3 will use your image as the starting point of the video, letting you achieve the exact aesthetic you want and guiding your scene in the right direction.

Learn more about creating videos with start and end frames.

Tips for creating seamless videos with Start and End frames:

• Create your Start Frame, then explore fresh perspectives and angles along the way with Nano Banana via our Inline Editor. Nano Banana also helps maintain character consistency across scenes, ensuring you achieve perfect end frames. (Alternatively use the End Frame as your jumping off point to create a suitable Start Frame)
• Craft moody, cinematic shots with Lucid Realism, then bring them to life with Start–End Frame video transitions.
• Longer videos may offer smoother but potentially slower transitions. Choosing a shorter duration may offer much faster but potentially less smoother transitions - consider subtler transitions for shorter videos.
• Avoid having extremely different Start and End frames (such as different settings or extreme changes and transformations). Veo 3.1 is best used for clean actions within a specific scene or context. If fancier morphing or scene transitions are required, consider using Kling 2.1 Pro instead.

Frequently Asked Questions

Original source Report a problem

Feature release: Nano Banana, a state of the art model for editing and generating images.

About Nano Banana

Nano Banana is the mysterious AI image model that took the AI world by storm. Created by Google, it’s known formally as Gemini 2.5 Flash Image. Now, Leonardo.Ai also offers Nano Banana Pro (Gemini 3.0 Pro Image). Read on to find out why these models are so special, and how to use them.

Why Nano Banana is such a great model

1. It's great for precise, controlled instructional edits to specific parts of images.
2. It's great at photorealistic editing and photo restoration
3. It's great at colorizing drawings (e.g inked comics, manga panels)
4. It has great contextual understanding. Give it a hypothetical question and it will imagine something as realistic as possible (e.g 'What would happen if a volcano erupted with slime instead of lava?') You can be abstract, and it will interpret its own way

How to use Nano Banana

There are two ways to create or edit with this model, depending on your objective.

As a standalone Image Generation model

1. Head to the AI creation page.
2. Select ‘Nano Banana’ or 'Nano Banana Pro' from the Models menu.
3. Optional: Select the image guidance icon in the prompt bar to add up to 6 reference images to guide your generation. You can describe how they should come together in the prompt.
4. Click Generate.

Editing and refining your Images

From here, you can continue to iterate on your images with the Inline Editor. Simply click on your chosen image to open it, and make a descriptive change.

Frequently Asked Questions

Why is it called Nano Banana?
Are Nano Banana and Gemini 2.5 Flash Image the same thing?
How do I get access to Nano Banana and Nano Banana Pro?
Can I use Nano Banana for free?
How much does Nano Banana cost?
How many reference images can be used with Nano Banana?
How many images can I generate at a time with Nano Banana?

Original source Report a problem

Overview

Phoenix is Leonardo.Ai's foundational image generation model available in Phoenix 0.9 and Phoenix 1.0.

Here's what you can expect from Phoenix:

• Prompt adherence, maximized: Expect image outputs that are high on fidelity. Phoenix faithfully follows your prompt, even for long, detailed instructions.
• Coherent text in images: Phoenix is capable of rendering coherent text in a wide variety of contexts - including reasonably long strings of text and even sentences.
• Rapidly ideate with Iterate: Edit with short, everyday phrases using our Iterate feature, to achieve perfect image generations, faster.

How to Generate Images with Phoenix

1. From the home page, navigate to the AI Creation tool by clicking Image beneath the prompt bar or in the side bar.
2. From the Models menu in the left side bar, choose Phoenix 1.0 or Phoenix 0.9
3. Enter your prompt and click Generate.

Frequently Asked Questions

How can I use Phoenix on the web app?

To use Phoenix on the web app, navigate to the image generation page. On the upper right, be sure to have Legacy Mode toggle turned off. Under Preset, choose Leonardo Phoenix.

Which web subscription will give me access to the Leonardo Phoenix Model?

The Leonardo Phoenix model is available on any of the web subscriptions like Free plan, Essential plan, Premium plan, and Ultimate plan.

Which API plan will give me access to the Leonardo Phoenix Model?

The Leonardo Phoenix model is available on all API plans including the Basic API Plan, Standard API Plan, Pro API Plan, and Custom API Plan.

Are there minimum API usage requirements to access the Leonardo Phoenix model via API?

No, there are no minimum API usage requirements to access the Leonardo Phoenix model via API.

Original source Report a problem

Feature Release: Lucid Origin, a new model built by Leonardo.Ai.

Overview

Generative AI is evolving fast - and Lucid Origin from Leonardo.Ai is here to raise the standard. With great diversity, more dynamic range, and trained for Full HD renders, Lucid Origin sets a new benchmark for aesthetic fidelity. Built to impress, it breaks through many common limitations of AI image generation and is designed to deliver beautiful, authentic, and reliable visuals. Read on to find out what makes Lucid Origin it so special, how to use it, and top tips for getting the best outputs.

About Lucid Origin

Developed by a team of researchers with backgrounds in both machine learning and the visual arts, the model blends technical rigor with human judgment and taste to consistently produce images that are aesthetically refined, diverse, and versatile.

Lucid Origin is the go-to model for creators seeking power and precision, thanks to:

• Increased Vibrancy: Lucid Origin delivers imagery saturated with color, striking visual depth, and a sense of energy that feels truly alive. Every frame is bold, expressive, and stands out.
• Increased Diversity: Unlock a wider spectrum of creative possibilities. Generate characters, cultures, and perspectives with authenticity and inclusivity to tell richer stories.
• High Definition: Experience stunning Full HD native output, with crystal-clear details - perfect for professional-grade content.
• Styles & Aesthetics: Whether you want hyper-realism, hand-drawn charm, or anything in between, Lucid Origin achieves styles to fit any mood, genre, or creative vision.
• Text Rendering & Graphic Design: Clean text, sharp layouts, and polished graphic design elements come naturally. Ideal for branded content, promos, and visually driven storytelling.
• Prompt Adherent: What you ask for is what you get. Lucid Origin responds precisely to your prompts, delivering intentional and reliable results with minimal guesswork.

How to use Lucid Origin

1. Navigate to the AI Creation page and choose Lucid Origin from the Models menu
2. Enter your prompt and select your preferred Generation Mode and Image Dimensions in the left sidebar.
3. Click Generate.

Optional: Click the Video tab, and use your favourite Lucid Origin image as a start frame, and bring your image to life in video. Lucid Origin frames are designed to be video-ready!

Top Tips for using Lucid Origin:

You don’t need to be a prompt engineer to achieve beautiful results. Short, simple prompts still sing, but adding aesthetic cues = magic. Incorporate these directives into your prompt if you want to achieve…

• Photorealism: Lean into lighting, lens, mood - Lucid Origin understands cinematic language
• Design/Text: Use clear typographic directives (“bold sans serif headline, centered, minimal palette”).
• Illustration: Describe medium (gouache, cel-shaded, vector), colour schemes, composition cues
• Video start frames: Include motion/scene continuity hints (“medium shot, character facing left, continuous lighting”)

FAQ

What's the difference between Lucid Origin and Lucid Realism?
Can I still use Lucid Realism?
How do I get access to Lucid Origin?
How much does it cost to generate with Lucid Origin?
Can I use Lucid Origin generations in commercial projects?

Notes for API customers:

To ensure best results;

• Use 'Fast, 1440 x 1440, Large' on the frontend for generations (1.44 megapixels) for best results. You can go up to full HD.
• Up to 15 steps are recommended, more are not required.

Original source Report a problem

Introduction to Blueprints

Blueprints are Leonardo’s new way to create - a suite of ready-made AI workflows designed to help you achieve awesome results in just a click. Blueprints don’t limit creativity - they expand it. Think of them as creative fuel: a launchpad for imagination that gives you the freedom to explore, experiment, and go further than before.

Blueprints make AI accessible, stable, and intuitive, whether you’re refining your skills or just getting started. No complex setup. No endless trial and error. Just open a Blueprint, hit generate, and watch your idea come to life.

This guide will cover:

• How Blueprints work
• How to use Blueprints with a step-by-step example Blueprint workflow
• Tips to get the best results from Blueprints
• Frequently asked questions about Blueprints

How do Blueprints work?

Blueprints work by combining models, prompts, and settings into one streamlined flow that only requires simple inputs, to deliver high-quality outputs. They intuitively guide you through each step, so you can focus on expanding your creativity, not fiddling with settings.

How to use Blueprints

1. From the Leonardo.Ai homepage, select Blueprints from beneath the prompt bar (A), side bar, or pick a Featured Blueprint to get started instantly.

On the Blueprints page, you’ll see a variety of categories, and can search for specific Blueprints. Browse through them to see what’s available for your creative goal. We’ll keep adding new Blueprints, so keep an eye out!

1. Select a Blueprint. For this example workflow, let’s use the Product Photography to generate a branded image and video of our product.

Note: Blueprints may output images, videos, or a combination of both. To check the outputs, expand the Blueprint Description.

1. Enter your inputs. The Blueprint will guide you through each simple step.

For this Blueprint, we’ll follow Step 1 by uploading our product image, and click Next to move to the next input.

For Step 2, we'll specify where we want our product to appear.

For the optional Step 3, we'll provide a description of the type of photo we want.

1. Hit Generate and wait for your outputs to be created. Your results will appear shortly, ready to use in your projects or refine further.

2. Click the thumbnails to view them, upscale, add them to collections, make them public/private and even share*.

*To protect user privacy when using input images, direct social sharing of results is disabled. Share a Blueprint link instead, or share a view‑only link to your outputs.

Take Blueprints further

Blueprints are your shortcut to pro results, but your cereativity doesn't have to stop here. With the Leonardo.Ai platform, you've got full control over your creative vision, and a full suite of tools to help you achieve it, the easiest being via the Inline Editor.

Click an image output to open the Inline Editor. From here, you can describe any changes you want to see or add more reference images and iterate further until you achieve the exact results you want. Your iterations are saved in your Library.

Tips to get the best results from Blueprints

Before generating:

• Browse the various categories to explore a variety of Blueprints. Remember, if there’s something you don’t like about the expected output, you can continue editing.
• Check the output/s so you know what you’ll get back.

After generating:

• Further refine by clicking on an image output to open the Inline Editor
• Use your results as inputs for other Blueprints to find your ideal workflow (build-your-own Blueprints is coming soon!)

What's Coming Next

Soon, you'll be able to build your own Blueprints, share them with the community, and access them through the Leonardo API for faster, more seamless creative workflows. Turn your favorite creative processes into repeatable systems that work the way you do.

Original source Report a problem