# AI video and image glossary

URL: https://dreambench.ai/glossary

Plain definitions of the words behind AI video and image tools. Each entry says what the term means, how it works, where it breaks and what DreamBench does with it, with diagrams of its own. Append ".md" to a page’s address for its Markdown copy.

- [What is outpainting?](https://dreambench.ai/glossary/outpainting): Extending a picture past its edges with new content that matches the scene.
- [What is inpainting?](https://dreambench.ai/glossary/inpainting): Filling a chosen area of a picture with new content, the way AI removes objects and text.
- [What is a transparent background?](https://dreambench.ai/glossary/transparent-background): Pixels with no color of their own, stored in an alpha channel, so the page behind shows through.
- [What is image upscaling?](https://dreambench.ai/glossary/image-upscaling): Making a picture larger with more pixels, the extra detail predicted so it stays sharp.
- [What is background removal?](https://dreambench.ai/glossary/background-removal): Separating a photo’s subject from what is behind it, with segmentation or matting models.
- [What is image to video?](https://dreambench.ai/glossary/image-to-video): AI video that starts from a still picture, the motion generated from a prompt.
- [What is text to video?](https://dreambench.ai/glossary/text-to-video): AI that turns a written prompt into a video clip, every frame invented from the words.
- [What is temporal consistency in AI video?](https://dreambench.ai/glossary/temporal-consistency): How well an AI video keeps things the same from frame to frame, without flicker or drift.
- [What is AI video editing?](https://dreambench.ai/glossary/ai-video-editing): Changing what is in a real video with a generative model, while its motion and timing stay.
- [What is motion transfer?](https://dreambench.ai/glossary/motion-transfer): AI that takes the movement from one video and gives it to a different character.
- [What is video inpainting?](https://dreambench.ai/glossary/video-inpainting): Filling a region of a video so it fits every frame, which is how AI removes objects and people.
- [What is first and last frame in AI video?](https://dreambench.ai/glossary/first-and-last-frame): AI video that opens on one picture and ends on another, with the motion between them generated.
- [What is reference to video?](https://dreambench.ai/glossary/reference-to-video): AI video that keeps a character, product or place from your pictures recognizable in a new shot.
- [What is character consistency in AI video?](https://dreambench.ai/glossary/character-consistency): Keeping a character recognizably the same person in every shot of an AI video, not just within one clip.
- [What is multi-shot video?](https://dreambench.ai/glossary/multi-shot-video): An AI video of several shots joined by cuts: planned as a shot list, generated shot by shot, cut into one film.
- [What is native audio in AI video?](https://dreambench.ai/glossary/native-audio): Sound a video model makes with the picture: dialogue, effects and ambience on one timeline.
- [What is AI lip sync?](https://dreambench.ai/glossary/lip-sync): A mouth moving in time with speech: made with the voice from a prompt, or redrawn to fit an audio track.