# What's New

See the latest OpenArt feature releases, product improvements.

## SMART SHOT - Your Idea, Fully Directed

Describe your scene. Smart Shot builds the Shot Plan - then generates a cinematic video with multiple shots, real camera work, and consistent characters.

## INTRODUCING GPT IMAGE 2

Readable text, cinematic shots, consistent characters, and production-ready edits — ChatGPT Image-2 does it all.

## SEEDANCE 2.0 IS HERE

The most powerful video generation model yet—now available to all users!

## OpenArt Suite | A New Era of Characters & Worlds

OpenArt Suite, The Sweetest Update Yet!

### Unified Workspace: Everything in one place.
- Image, Video, Character, and Audio tools now live in a single creation panel
- Move between workflows (Video → Audio → Lip Sync) without switching pages or re-uploading

### Smoother Creation Flow: Create faster with less friction.
- Drag & drop assets across tools from one shared library
- Your inputs and settings stay saved so you can iterate without starting over

### Easier to Get Started: Less tool hunting. More creating.
- Clear categories guide you to the right workflow
- Consistent layouts and model labels make tools easier to understand

### Characters & Worlds: Build once. Reuse everywhere.
- Save characters, objects, backgrounds, and styles
- Reference them directly in prompts (e.g., @Character, @Image)

## Kling 3.0 & Kling 3.0 Omni Is Changing The AI Video Game!

Kling 3.0 & Kling 3.0 Omni is LIVE on OpenArt!

- Kling 3.0 is built on Kling VIDEO 01 and Kling VIDEO 2.6, Kling 3.0 VIDEO uses a deeply integrated unified training framework to deliver more native multimodal input and output. It introduces native audio, enhanced element consistency, and support for multi-shot narratives, breaking through previous duration limits for longer, more coherent video generation.
- Kling 3.0 Omni is an all-in-one multimodal system enabling unified input and output across video, audio, and voice. It supports voice-driven characters, direct audio-visual generation, and storyboard-based workflows. By combining native audio with advanced element consistency control, Kling 3.0 Omni enables more natural multimodal creation and extended generation durations.

## OpenArt AI Image & Video Beginner Course!

Dream Big With AI! A Creative AI Course For Beginners.

What do you want to achieve in 2026? ✨
Learn AI image & video creation from scratch with OpenArt’s 101 Beginner Course. See it first. Then achieve it.

## Kling 2.6 Motion Control is now on OpenArt!

Kling 2.6 Motion Control Driving Performance Like No Other!

### Key Highlights:
- Precise character motion driven by a reference video
- Perfectly synced full-body & complex motions
- High-fidelity hand and gesture control
- Prompt-controlled scenes & background details

## Introducing Character 2.0

Consistent Characters Solved!
- Works well for every type of character not just human characters
- 10x more consistent than before, including complex details
- Only one-reference image needed, leave the rest to us
- Character creation more cost-efficient and faster
- Compatible with both Nano Banana/Pro and Seedream 4.0/4.5

## One Prompt 15 Second Multiple Shots With Wan 2.6

Wan 2.6 Is Live On OpenArt!

Wan 2.6 is quickly becoming one of the most discussed AI video models among creators, filmmakers, and content teams. As interest in advanced video generation grows, more people are asking what is Wan 2.6 and how it differs from earlier AI video systems.
- Stable motion across frames
- Consistent character appearance
- Structured scene progression
- Improved camera movement
- Better alignment between audio and visuals

## Kling 2.6 Has Native Audio! Move Over Veo 3 & Sora 2!

Kling 2.6 introduces audio–video co-generation for the very first time.
- Voices that sync flawlessly with the character. Natural, native, and instantly immersive.
- When superb visuals are paired with natural voiceovers, matching sound effects, and immersive ambient sounds, the 2.6 model generates coherent looking & sounding outputs as an entire experience more than a video clip.
- Generate an entire experience. More than a video clip! With coherent looking & sounding output, the 2.6 model opens up narrative possibilities, and makes you "See the Sound, Hear the Visual."
- A fraction of the cost compared to Veo 3.1 & Sora 2.