Nano Banana Pro
Models
Nano Banana ProNano Banana Pro

Sora 2

Create videos from text prompts or images with Sora 2. Choose from the available options, then review the displayed credit cost before generating with Nano Banana Pro .

Sora 2
About

About Sora 2

Sora 2 is a video generation model that creates clips from text prompts or image inputs. Use a prompt to describe the scene, characters and camera movement, or provide an image as a visual reference. Available settings depend on the model; Sora 2 offers 10- and 15-second options.

About Sora 2
Feature overview

Key Features

Create videos from text prompts or images, with options for cinematic scenes and expressive characters.

Describe Scene Motion example

Describe Scene Motion

01

Use your prompt to guide how objects move and interact in the scene.

Describe the physical interactions you want to see, such as water splashing, fabric moving or objects colliding. The generated result depends on the prompt and may not follow real-world physics exactly. Review the video to see how consistently the movement is depicted.

Prompt

A glass sphere drops into water in slow motion, with the splash and droplets visible at the moment of impact. Show light refracting through the glass and water. Clean white and soft blue palette, scientific subject with a carefully composed frame.

A prompt idea for showing a glass sphere, water impact and light refraction.

Output example
1
Describe Character Expressions example

Describe Character Expressions

02

Use your prompt to guide facial expressions, gestures and emotional tone.

Describe how you want a character to move and express emotion. You can specify facial expressions, gestures, posture and reactions, but the result may vary and details may not appear exactly as requested. Use a clear sequence of actions to guide the scene.

Prompt

A film-strip sequence of a young woman showing four expressions: joy, surprise, contemplation and determination. Warm natural lighting, minimalist styling and a softly blurred background. Cinematic portrait framing.

A prompt idea for a character sequence with changing expressions.

Output example
1
FAQ

Frequently Asked Questions

Sora 2 FAQ

Illustrative Sora 2 Project Ideas

Illustrative Sora 2 Project Ideas

Explore creative examples
Text-to-Video ConceptA creator could use a text prompt to explore turning a video concept into a short clip. The result depends on the prompt and selected settings.
Camera Direction ConceptA filmmaker could use a prompt to explore camera movement and character expressions in a scene. Results may vary with the prompt and selected settings.
Brand Asset Animation ConceptA social media team could try using an image reference to guide a short brand-asset animation. The output depends on the prompt and selected options.

Explore more AI video models

Veo 3.1 Quality

Veo 3.1 Quality

New

Veo 3.1 offers Lite, Fast and Quality variants where available. Choose text-to-video, image-to-video or video-to-video in supported modes; reference-to-video supports up to 3 images and requires Fast at 16:9. Available aspect options are Auto, 16:9 and 9:16. The interface has no duration or resolution selector. Check the displayed credit cost before generating.

Try now
Wan 2.6

Wan 2.6

New

Wan 2.6 supports text-to-video, image-to-video and video-to-video. It offers 5-, 10- and 15-second duration options, 720p and 1080p resolutions, and multi-shot generation.

Try now
Vidu Q4

Vidu Q4

New

Animate one first-frame image or use up to 15 reference images. Choose 540p–4K and a duration of 3–16 seconds for image animation or 1–16 seconds for references. Synchronized audio is optional. Reference audio must be MP3 and 3–12 seconds long.

Try now
Kling 4.0

Kling 4.0

New

Create 3–30-second videos from text, first and last frames, or visual references. Choose 720p or 1080p and review motion, sound and credits before developing your next edit.

Try now
Kling 2.6

Kling 2.6

Kling 2.6 is designed for complex motion and interactions. Use it to explore dynamic character movement, objects interacting and fluid camera moves.

Try now
MiniMax H3

MiniMax H3

New

MiniMax H3 is a multimodal video model for text-to-video, image-to-video and reference-to-video. It offers 768p and 2K output, flexible duration options and reference audio.

Try now

Create a Video with Sora 2

Explore Sora 2 online. Sign in and check the displayed credit cost before generating.
Create a Video