# China Video AI Capabilities

China Video AI is a browser-based workspace for creating and editing images and videos with selectable AI models.

## Creation modes

- **Image to video:** provide an image, describe the motion or scene, and generate a video with a supported model.
- **Text to video:** describe a subject, action, setting, and visual direction to generate a video.
- **Video to video:** provide a source clip and prompt to transform it when the selected model supports that workflow.
- **Text to image:** create an image from a prompt.
- **Image editing:** provide an image and describe the requested revision with a supported image model.

Some models support additional controls such as reference images, first and last frames, duration, resolution, or generated audio. These controls are model-specific; use the creation interface to confirm current support.

## Typical workflow

1. Open a creation mode and choose an available model.
2. Enter a prompt and attach supported source media or references.
3. Review settings and the estimated credit cost shown before submission.
4. Submit the task, check its status, and download the result when ready.

The model, duration, resolution, reference inputs, and audio settings can affect output and cost. Start with a small generation when evaluating a new workflow. Account access, plan benefits, and content restrictions are described in the live [pricing](https://chinavideoai.com/pricing), [terms](https://chinavideoai.com/terms-of-service), and [acceptable use policy](https://chinavideoai.com/acceptable-use-policy).

## Related pages

- [Image to video](https://chinavideoai.com/image-to-video)
- [Text to video](https://chinavideoai.com/text-to-video)
- [Video to video](https://chinavideoai.com/video-to-video)
- [Text to image](https://chinavideoai.com/text-to-image)
- [Image editor](https://chinavideoai.com/image-editor)
- [Model comparison](https://chinavideoai.com/chinese-ai-video-models)