Skip to main content

Vidu Q4 reference to video with a character pack

Vidu Q4 Preview can take up to 15 reference images in one generation, enough for a character's views, outfit, prop, scene, expressions and poses. Here is which pack file to put in each slot and how to point at them in the prompt.

We have not made an example with Vidu Q4 yet. This page maps the pack to Vidu's published limits; the nine examples on this site were made with Kling 3.0.

What Vidu Q4 allows

Checked 2026-10-11
  • Reference to video takes 1 to 15 reference images, plus up to 3 audio references of 3 to 12 seconds (only the voice is used, not the words).
  • In the prompt, refer to images by their order: image 1, image 2 and so on.
  • Each image must be between 1:5 and 5:1 in aspect ratio.
  • Output runs 3 to 16 seconds, from 540p up to 4K.
  • Through the fal and WaveSpeed APIs the same model takes up to 12 reference images, written as [@reference_image_1], [@reference_image_2] and so on in the prompt. Slots 13 to 15 below only fit in Vidu's own app.

Sources: Vidu Q4 Preview in ComfyUI: Image and Reference to Video · fal: Vidu Q4 Reference-to-Video API · Vidu Launches Q4 Preview (PR Newswire)

The 15 slots

Upload in this order so the image numbers in your prompt stay the same for every shot. The overview sheet, the artwork and the two video first frames are left out.

  1. image 102_turnaround_views/view_front.pngFace and front of the outfit
  2. image 202_turnaround_views/view_side.pngProfile and hair from the side
  3. image 302_turnaround_views/view_back.pngHair and outfit from behind
  4. image 401_character_reference/full_body.pngHeight and proportions
  5. image 503_outfits/outfit_work.pngThe job outfit
  6. image 604_props/prop_role.pngThe product or tool
  7. image 705_scenes/scene_workspace.pngThe location
  8. image 807_expressions_poses/expression_neutral.pngExpression: neutral
  9. image 907_expressions_poses/expression_smile.pngExpression: smile
  10. image 1007_expressions_poses/expression_surprised.pngExpression: surprised
  11. image 1107_expressions_poses/expression_determined.pngExpression: determined
  12. image 1207_expressions_poses/pose_working.pngPose: working
  13. image 1307_expressions_poses/pose_presenting.pngPose: presenting
  14. image 1407_expressions_poses/pose_preparing.pngPose: preparing
  15. image 1507_expressions_poses/pose_greeting.pngPose: greeting

You do not have to fill all 15. A suggestion: slots 1 to 5 for identity, then the prop and scene when the shot needs them, and the one expression or pose closest to the action.

Point at the slots in the prompt

Prompt template

image 1, image 2 and image 3 are the front, side and back of the same character, [name]: [skin, eyes, hair]. Body proportions as in image 4. She wears the outfit from image 5 and holds the [product] from image 6, in the room from image 7, with the expression from image 9. [Action]. [Camera], single continuous shot. No extra people, no text or logos.

The pack's two video first frames are not references. If you use Vidu's image-to-video mode instead, start from one of them.

Start with a free character

Every character's full 19-image pack is free: eight starter characters need no account, the rest a free sign-up. All nine example ads use pack images only.

Browse free characters