AI video models
Text-to-video, image-to-video, talking actors and finishing tools. Compare durations, formats and credits, then make it in Advibly.
Explore the library
21 of 21 models
- ByteDanceVideo
Seedance 2.0
ByteDance's flagship video model with native audio, up to 1080p, and reference images that keep your product looking like itself.
Final product ads at 1080p - ByteDanceVideo
Seedance 2.0 Fast
A faster, lower-cost Seedance 2.0 route for everyday production at 480p or 720p, with native audio and reference images.
Everyday Seedance production - ByteDanceVideo
Seedance 2.0 Mini
The lowest-cost Seedance 2.0 tier, for drafts, storyboards and high-volume variations at 480p or 720p, with native audio.
Low-cost drafts and storyboards - ByteDanceVideo
Seedance 2.5
ByteDance's long-form Seedance model for single shots of up to 30 seconds with native audio, from text, frames or reference images.
Native-audio shots up to 30 seconds - GoogleVideo
Gemini Omni Flash
Google's multimodal video model with convincing real-world physics, which can also restyle or edit a video you already have.
Editing an existing clip - GoogleVideo
Gemini Omni Flash 1.1
Google's omni video model with native audio, start and end frames, reference images and video editing, from 360p up to 4K.
Native audio from 360p to 4K - GoogleVideo
Gemini Omni Flash 1.2
Google's newest omni video model: clips up to 15 seconds with native audio, reference images and clips, and edit, extend and upscale for footage you already have, from 360p to 4K.
15-second clips, extending and upscaling - Kling AIVideo
Kling v3
Kuaishou's cinematic video model with native audio, 1080p output, and elements that keep up to four characters or objects consistent.
Cinematic shots with recurring characters - Kling AIVideo
Kling 4.0
Kuaishou's newest video model: clips from 3 to 30 seconds at up to 1080p, from text, a start and end frame, or reference images and elements.
Long shots with recurring characters - Kling AIVideo
Kling 4.0 Flash
Kling 4.0 at 720p for about 60% of the price, with clips up to 20 seconds and video-to-video edits.
Cheaper Kling drafts and clip edits - Black Forest LabsVideo
FLUX 3
Black Forest Labs' video model for cinematic clips of up to 20 seconds from text, a start frame, or a defined first and last frame, with native audio.
Cinematic text-to-video with audio - xAIVideo
Grok Imagine Video
xAI's fast video model for clips from 1 to 15 seconds with audio, in seven aspect ratios and up to 1080p.
Fast social clips in any format - MiniMaxVideo
Hailuo 03
MiniMax's video model with native audio, reference control and output up to 2K.
2K output with reference control - MiniMaxVideo
Hailuo 03 Max
A tuned Hailuo 03 for prompt-faithful video with native audio and reference control, at about half the cost of the base model.
Prompt-faithful video at lower cost - Black Forest LabsVideo
FLUX 3 Max
FLUX 3 post-trained for closer prompt adherence and better visual quality, with native audio and clips of up to 20 seconds.
Final renders that follow the prompt closely - MiniMaxVideo
Hailuo 03 Max Turbo
Hailuo 03 Max on a faster stack for text, frame and reference workflows, at about half the cost of Max again.
Low-cost iteration from text - AlibabaVideo
Wan 3.0
Alibaba's long-form video model with native audio, clips from 2 to 30 seconds, and up to four reference images for consistent subjects.
Long clips with consistent subjects - HeyGenVideo
HeyGen Video
HeyGen's post-trained version of MiniMax H3: 5 to 15 second clips with sound, up to 2K, from text, a start frame, or references.
Low-cost clips with sound - Pruna AIVideo
P-Video Avatar
Pruna's fast talking-head model that turns one portrait and a script into a lip-synced presenter video, up to 1080p.
Affordable AI spokesperson videos - VEEDVideo
VEED Fabric 1.0
VEED's portrait-animation model for talking-head video with the most expressive lip sync and facial movement we offer.
Expressive talking-head video - VEEDVideo
VEED Subtitles
A finishing tool that burns readable, styled captions into any video in your library, with optional translation.
Captioning short-form social video
Prices are estimates from Advibly's live model configuration at $1 per credit. The composer shows the exact amount for your settings before anything is charged.
