Clear answers

AI Long Video FAQ

What the current 30-second and 60-second production workflow supports today.

Frequently Asked Questions

What is AI Long Video?

AI Long Video is a production workspace for text-to-video and image-to-video generation, with project-based shot organization and presets for 30-second and 60-second sequences.

Does it generate one continuous 30-second clip?

Not with the current connected API. The 30-second preset creates two ordered 15-second shots. Native 30-second rendering will be enabled only when a production-ready API is available.

How does the 60-second mode work?

It prepares four 15-second shots inside one project sequence. Each shot can be reviewed or regenerated independently.

Can I create video from text?

Yes. Describe the subject, action, camera movement, lighting, and style, then choose the duration and output settings.

Can I animate an image?

Yes. Upload a JPG, PNG, or WebP image up to 8 MB and use it as the opening frame for a generated shot.

Which resolutions are available?

The current production lanes support 720p and 1080p output.

Can I start free?

Yes. New visitors receive starter credits for an initial 720p generation. Longer sequences and higher-resolution production require sufficient credits.

How are long sequences priced?

Credit usage is calculated per component shot. A 30-second sequence costs two 15-second renders; a 60-second sequence costs four.

Can I use the output commercially?

Commercial use depends on your content, source assets, and applicable model/provider terms. Do not upload or generate material you do not have the right to use.

How do I keep characters consistent?

Repeat identity, wardrobe, lighting, location, and color-grade details across prompts, and keep each shot focused on one main action.

Ready to try?

Start with a single shot, then move into a structured long-video sequence.

Open Studio →