Skip to content

Guides

Every section we cover, with the explainers that go with it.

After the generation

Model

Model Upscaling generated video AI upscalers can fix soft generated video—but they also amplify latent-space flicker and hallucinate detail that was never in the source image.

Choosing between them

Model

Model Veo compared with Kling Google Veo 2 and Kling 1..6 compared on motion fidelity, prompt adherence, clip length, audio, and access paths—with dated evidence and the caveat that the answer moves.

Free and local

Model

Model What the free tiers actually allow Free tiers come with watermarks, resolution caps, deprioritised queues, and commercial-use restrictions. Here is what each provider's terms actually say, dated and sourced.

Prompting for motion

Model

Model How to structure an image-to-video prompt A fixed five-element image-to-video prompt template—subject, motion, camera, lighting, duration—and why the order determines what the model actually animates.

Rights, rules and disclosure

Model

Model Who owns a generated video Who legally owns AI-generated video output under US, UK, and EU copyright law, and what each major model's terms of service say about ownership.

Shot recipes

Model

Model The earth zoom-out shot How to generate an orbital earth zoom-out from a still image, with the source requirements, prompt, and diagnosis of the seam and parallax failures that expose the shot.

The models

Model

The source image

Model

Model Resolution and aspect ratio What resolution and aspect ratio each image-to-video model expects, and the distortion and softening artefacts that appear when the source image does not match.

Guides not tied to one category

25 September 2026 How Image-to-Video Generation Actually Works and How to Get a Usable Clip Image-to-video models predict pixel motion from a single still using latent diffusion with temporal attention—they do not understand the scene. Here is how the pipeline works and why the output behaves the way it does.