AI Video Models
Generate high-quality videos from text or images using state-of-the-art AI video models.
Veo 3.1
Google's advanced video generation model for cinematic text-to-video and image-to-video output.
Generate realistic, cinematic video clips from a text prompt or a reference image. Supports 720p, 1080p, and 4K resolution with multiple aspect ratios.
Seedance 2.0
ByteDance's latest video generation model with native audio-video generation, text-to-video and image-to-video output.
Generate cinematic video clips with synchronized native audio from a text prompt or reference image. Up to 15 seconds at up to 1080p, with six aspect ratios including 16:9, 9:16, and 21:9.
Why Use These Video Model Pages?
Understand Each Model
Learn the actual capabilities, limitations, and best use cases for each video model before spending credits.
Real Output Tradeoffs
Compare motion quality, prompt adherence, and output resolution across models instead of guessing from a label.
Faster Workflow
Each model page shows the right settings and prompt patterns so your first generation has a higher chance of hitting the mark.
Frequently Asked Questions
What AI video models are available?
Currently we offer one video model page: Seedance 2.0 by ByteDance. More video models will be added as they become available through our platform.
How do credits work for video generation?
Video generation costs more credits than image generation because of the higher compute requirements. Each Seedance 2.0 video generation costs 10 credits. Exact credit usage is shown in the tool interface before you generate.
What video formats and resolutions are supported?
Seedance 2.0 outputs MP4 video files at 720p resolution. Supported aspect ratios include 16:9 (landscape), 9:16 (portrait), and 1:1 (square). Clip duration is up to 10 seconds.
Can I use generated videos commercially?
Yes. Videos generated through our platform carry a commercial license. You can use them for marketing, social media, product demos, and other commercial projects. Review our terms of service for the full details.
How is video generation different from image generation?
Image generation produces a single still frame from a prompt. Video generation produces a sequence of frames with consistent motion across time. This requires significantly more compute, which is why generation takes longer and costs more credits.