Arcads clone static ad vs Sume Avatar Video product image

Arcads' /clone-static-ad command recreates a static ad as a video ad with your own assets. Sume has no clone command; the closest route is Avatar Video, where you pass your product photo as product_image and direct the setting with a scene prompt.

Arcads facts are from its MCP help article (June 26, 2026); Sume facts are from Generate avatar video, read 2026-10-01.

Which Sume inputs replace the static ad?

Avatar Video takes a ready avatar via avatar_handle, and exactly one of script or video_inputs. Omit product_image for a productless video; include it to bring in your product. scene: { "type": "prompt", "prompt": "..." } gives scene direction, and scene.type: "photo" with an image_url gives a photo reference.

What formats can the video take?

What rules apply to my image URLs?

Media fields must be fetchable public HTTPS URLs. Per Media inputs, localhost, private-network, non-HTTPS and signed or private URLs are rejected before generation submission.

Does this copy the layout of the original ad?

No. The docs describe prompts and references, not layout cloning, so the original ad's composition is yours to describe in the scene prompt. See avatar video with your product and background for a worked setup.