Skip to content
Wenimg logoWenimg

AI Video Models

Compare AI video models and create videos in one workspace. Explore Veo, Kling, Seedance, Wan, Grok and other video generation models.

Max 6 reference files / JPG, PNG, WEBP / 20MB each

Max 1 reference file / MP4 / 50MB each

0/2000

Choose an AI video model for motion, duration and control

AI video models vary by text-to-video, image-to-video and reference capabilities, as well as duration, resolution, audio and camera control. Select a model around the footage you need to deliver.

01

Create motion from a prompt

Define the subject, action, camera movement and atmosphere for a text-led video generation.

02

Animate an image

Start from a still image when the first frame, subject appearance or visual style must stay recognizable.

03

Match delivery settings

Compare duration, resolution, aspect ratio, audio support and credit cost before generating.

Available AI video models

Open a model workflow to review supported inputs, output settings and video prompt examples.

Veo 3.1 Lite

720p, 1080p, 4k

Cost-efficient Google Veo 3.1 for text-to-video, first/last-frame, and material-reference generation.

Open model

Veo 3.1 Fast

720p, 1080p, 4k

Fast Google Veo 3.1 with synchronized audio for text, first/last-frame, material-reference, and extend.

Open model

Veo 3.1

720p, 1080p, 4k

Flagship Google Veo 3.1 Quality for text-to-video and first/last-frame generation with synchronized audio.

Open model

Kling 3.0

720p, 1080p, 4k

Cinematic Kling model with optional native audio, first/last-frame control, and 3-15 second generation.

Open model

Kling 3.0 Turbo

720p, 1080p

Lower-cost Kling V3 Turbo model for rapid text-to-video and first-frame animation.

Open model

Gemini Omni Flash

720p, 1080p, 4k

Any-input video model for turning text, images, audio, or clips into grounded, editable video.

Open model

Gemini Omni 1.1 Flash

360p, 720p, 1080p, 4k

KIE Gemini Omni 1.1 Flash for fast multimodal video generation, first/last frames, and video references.

Open model

Grok Imagine Video

480p, 720p

Fast creative video model for animating text or image ideas into short, shareable motion clips.

Open model

Grok Imagine Video 1.5 Preview

480p, 720p

Image-guided video generation with flexible 1–15 second output at 480p or 720p.

Open model

HappyHorse 1.0

720p, 1080p

Audio-video generation model for text, image, reference, and editing workflows with native lip-sync.

Open model

HappyHorse 1.1

720p, 1080p

Physically realistic video generation from text, a first-frame image, or up to nine ordered reference images.

Open model

Seedance 2.0

480p, 720p, 1080p, 4k

High-fidelity multimodal video with synchronized audio, up to 4K output, and image, video, or audio references.

Open model

Seedance 2.0 Fast

480p, 720p

Faster 480p or 720p multimodal video drafts with synchronized audio and flexible reference inputs.

Open model

Seedance 2.0 Mini

480p, 720p

Lower-cost video drafts with 480p or 720p output, synchronized audio, and multimodal references.

Open model

Wan 2.7

720p, 1080p

Multi-reference video model for text-to-video, image-to-video, first-last frame control, and instruction-based editing.

Open model

Wan 3.0 Video

480p, 720p, 1080p

Alibaba Wan 3.0 for text, first/last-frame, and multimodal reference video generation up to 30 seconds.

Open model

Wan 3.0 Video Prime

480p, 720p, 1080p

Faster Alibaba Wan 3.0 Prime for text, first/last-frame, and multimodal reference video generation up to 30 seconds.

Open model

MiniMax H3

768p, 2k

MiniMax H3 for native-audio video generation from text, first/last frames, and multimodal references.

Open model