> For the complete documentation index, see [llms.txt](https://docs.seaart.ai/guide-1/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.seaart.ai/guide-1/seaart-ai-basic-function/ai-video-generation/image-to-video.md). # Image to Video Image to Video turns a still image into a video. Upload the image you want to animate, describe how the scene should move, and optionally add an end frame to control how the video finishes. ### How Image to Video works Select or upload the subject image you want to animate. This image becomes the start frame of your video. Enable **Smart Prompts** to get prompt suggestions based on the current image. The prompt field cannot be left empty. Use the generated prompt as a starting point, or edit it to describe the action, camera movement, and atmosphere you want. To control the ending, add an end frame. SeaArt AI video generator then generates a transition from the start frame to the end frame. ### How to Write a prompt #### **Prompt Framework** Subject + Action + Camera + Light and Atmosphere + Audio * **Subject**: Objects appearing in the image, such as **people, objects, environmental information**, etc. * **Action**: Description of the movement of the objects, such as a **person running**, environmental changes, spatial transformations, etc. * **Camera**: Camera descriptions are **not necessary**; after describing the subject and action, SeaArt will generally generate a reasonable dynamic video based on the prompts. If you want to control the camera, you can add descriptions of the camera in the prompts, such as: **camera zoom out**, etc. * **Light and Atmosphere**: Although the image already has basic lighting and atmosphere, SeaArt can still **adjust the overall atmosphere of the video based on the prompts**. * **Audio:** Describe dialogue, ambient sound, sound effects, or music when the selected model supports audio generation. Because the image already establishes the subject and visual style, the prompt can focus on motion instead of repeating every detail. **Tips:** 1. Describe the subject accurately and keep sentences short and clear. 2. Cover the movement completely so the model knows what should change and what should stay still. 3. Add camera, lighting, or audio details only when they are important to the shot. 4. Describe audio cues such as dialogue, ambient sound, sound effects, or music when they matter to the scene. 5. Use **Prompt Magic** to expand a short prompt into a more detailed description. ### Prompt Analysis Before generating a video from an image, we need to determine what kind of video we want. For example, if we want to make the dog in the image move:
**Simple prompt:** > A dog running on the grass.
**Prompt based on the framework**: > A dog is sprinting across the grass, making quick turns and leaping with its tail held high. The camera follows closely from a low angle, adjusting its focus as the dog runs, capturing each leap and running moment. The sunlight casts a warm glow on the dog's fur, while the grass is bathed in a warm light. The blue sky and white clouds gently drift in the light breeze in the background, creating a scene full of energy and the warm atmosphere of a peaceful morning.
### **Use Start and End Frames** Image to Video uses the uploaded image as the start frame. To control how the video ends, add a second image as the end frame.
When both frames are set, SeaArt generates a video that moves from the start frame to the end frame. This is useful for transformations, before-and-after shots, and scenes that need a specific opening and closing image.
#### Tips for Start and End Frames * Choose frames with similar composition, subject placement, and lighting for a more natural transition. * When both frames are set, edit the generated prompt to focus on the transition rather than repeating the contents of the images. * Keep the transition physically plausible. Large changes in subject position, perspective, or lighting are harder to blend smoothly.