POWERED BY 7 AI MODELS

The Most Advanced AI Video Models

Access cutting-edge AI technology from OpenAI, Google, Kling, Hailuo, and Alibaba. All in one app on your iPhone.

✨ Latest Models

LATEST
Google

Veo 3.1

Google Veo 3.1 is Google DeepMind's flagship video generation model, known for realistic motion and strong prompt following. In Videz you can use it for both text-to-video and image-to-video, in 4, 6 or 8 second clips at 720p or 1080p.

Text-to-video and image-to-video
4, 6 or 8 second clips
720p or 1080p output

+2 more capabilities

3 credits per video (4, 6 or 8 seconds)
LATEST
Kuaishou

Kling v3

Kling v3 is Kuaishou's latest video model, popular for fluid character motion and dynamic camera work. Videz runs the Kling v3 Turbo Pro model for both image-to-video and text-to-video, in 5 or 10 second clips.

Image-to-video and text-to-video
5 or 10 second clips
Fluid character and body motion

+2 more capabilities

2.5 credits per video (5 or 10 seconds)
LATEST
MiniMax

Hailuo 2.3

Hailuo 2.3 is MiniMax's video generation model, strong at expressive faces, natural movement and following detailed prompts. Videz offers it for both image-to-video and text-to-video.

Image-to-video and text-to-video
Expressive facial animation
Natural, realistic movement

+1 more capabilities

2.5 credits per video
LATEST
xAI

Grok

Grok Imagine is xAI's video generation model. In Videz it animates a photo into a 6 second clip at 480p, 720p or 1080p, and it is often a good choice when other models decline a photo.

Image-to-video
6 second clips
480p, 720p or 1080p output

+1 more capabilities

2 credits per video (3 credits at 1080p)
LATEST
ByteDance

Seedance 2.0

Seedance 2.0 is ByteDance's video generation model, known for cinematic camera work and consistent subjects. Videz runs Seedance 2.0 Fast for text-to-video and image-to-video, in 4 or 8 second clips at 480p or 720p.

Text-to-video and image-to-video
4 or 8 second clips
480p or 720p output

+2 more capabilities

2.5-3.5 credits per video depending on length and resolution
LATEST
Lightricks

LTX-2

LTX Video 2 is Lightricks' fast video generation model. In Videz it creates 1080p clips of 6, 8 or 10 seconds from a prompt or a photo, with optional generated audio, and it is one of the most affordable models in the app.

Text-to-video and image-to-video
6, 8 or 10 second clips
1080p output

+2 more capabilities

From 1 credit; longer clips and audio cost more (up to about 2 credits)
LATEST
Alibaba

WAN 2.7

WAN 2.7 is Alibaba's open video generation model. Videz uses it for Camera Controls and Custom mode, so you can animate a photo with a specific camera movement in 5 or 10 second clips at 720p or 1080p. It also powers the app's 40+ one-tap video effects.

Image-to-video
15 camera movements
5 or 10 second clips

+2 more capabilities

1.5-3.5 credits depending on resolution and duration

All AI Models

LATEST
Google

Veo 3.1

Google Veo 3.1 is Google DeepMind's flagship video generation model, known for realistic motion and strong prompt following. In Videz you can use it for both text-to-video and image-to-video, in 4, 6 or 8 second clips at 720p or 1080p.

Text-to-video and image-to-video
4, 6 or 8 second clips
720p or 1080p output

+2 more capabilities

3 credits per video (4, 6 or 8 seconds)
LATEST
Kuaishou

Kling v3

Kling v3 is Kuaishou's latest video model, popular for fluid character motion and dynamic camera work. Videz runs the Kling v3 Turbo Pro model for both image-to-video and text-to-video, in 5 or 10 second clips.

Image-to-video and text-to-video
5 or 10 second clips
Fluid character and body motion

+2 more capabilities

2.5 credits per video (5 or 10 seconds)
LATEST
MiniMax

Hailuo 2.3

Hailuo 2.3 is MiniMax's video generation model, strong at expressive faces, natural movement and following detailed prompts. Videz offers it for both image-to-video and text-to-video.

Image-to-video and text-to-video
Expressive facial animation
Natural, realistic movement

+1 more capabilities

2.5 credits per video
LATEST
xAI

Grok

Grok Imagine is xAI's video generation model. In Videz it animates a photo into a 6 second clip at 480p, 720p or 1080p, and it is often a good choice when other models decline a photo.

Image-to-video
6 second clips
480p, 720p or 1080p output

+1 more capabilities

2 credits per video (3 credits at 1080p)
LATEST
ByteDance

Seedance 2.0

Seedance 2.0 is ByteDance's video generation model, known for cinematic camera work and consistent subjects. Videz runs Seedance 2.0 Fast for text-to-video and image-to-video, in 4 or 8 second clips at 480p or 720p.

Text-to-video and image-to-video
4 or 8 second clips
480p or 720p output

+2 more capabilities

2.5-3.5 credits per video depending on length and resolution
LATEST
Lightricks

LTX-2

LTX Video 2 is Lightricks' fast video generation model. In Videz it creates 1080p clips of 6, 8 or 10 seconds from a prompt or a photo, with optional generated audio, and it is one of the most affordable models in the app.

Text-to-video and image-to-video
6, 8 or 10 second clips
1080p output

+2 more capabilities

From 1 credit; longer clips and audio cost more (up to about 2 credits)
LATEST
Alibaba

WAN 2.7

WAN 2.7 is Alibaba's open video generation model. Videz uses it for Camera Controls and Custom mode, so you can animate a photo with a specific camera movement in 5 or 10 second clips at 720p or 1080p. It also powers the app's 40+ one-tap video effects.

Image-to-video
15 camera movements
5 or 10 second clips

+2 more capabilities

1.5-3.5 credits depending on resolution and duration

Why Multiple AI Models?

🎬

Best Quality

Each model excels at different styles. Choose the perfect one for your content.

⚡

Flexibility

From fast generation to cinematic quality, pick what works for your timeline.

🎨

Creative Options

Different models produce unique artistic styles and visual effects.

TRUSTED BY

Google
Kuaishou
MiniMax
xAI
ByteDance
Lightricks
Alibaba