VideoGenReview

What each AI video model's release notes say changed

Which AI video models take a reference video?

Several notes take video, not only pictures, as a reference: Firefly for composition from July 2025 and for camera motion from December, Wan 2.2 Animate and Kling's Motion Control for a performance, and Wan 2.7 mixing images and videos in April 2026. From 4 source pages, read 2026-09-25; no maker pays to be listed.

The entries by dateOne dot per dated entry.The entries by date2025-07-17Adobe Firefly Video, Firefly Video Model2025-11-10Wan, Wan 2.22025-12-16Adobe Firefly Video, Firefly Video Model2025-12-22Kling AI, Not named in the note2026-04-03Wan, Wan 2.7
Fig. 1 One dot per dated entry.
Entries that answer this question, oldest first, read 2026-09-25.
DateLineVersionWhat changed
17 July 2025Adobe Firefly VideoFirefly Video ModelA reference video can pass its composition to a new generation
10 November 2025WanWan 2.2Wan 2.2 Animate moves a character photo with the performance from a reference video
16 December 2025Adobe Firefly VideoFirefly Video ModelA start frame can be paired with a reference video whose camera motion the generation recreates
22 December 2025Kling AINot named in the noteMotion Control in the API takes a reference image and a reference video together
3 April 2026WanWan 2.7Wan 2.7 reference-to-video mixes up to five image or video references and clones a voice timbre

Inclusion rule. Entries whose note bears directly on the question. Order. By date, oldest first; undated rows last.

What the reference video lends differs from note to note. Firefly takes its layout or its camera path; Wan 2.2 Animate and Kling's Motion Control take a performance, the movement of a body and a face; Wan 2.7 treats video as one more kind of reference for how a subject looks.

Copying a performance has its own question page, and pictures used as references are counted on the reference-images page.

1In the makers' words

Adobe Firefly Video, 17 July 2025

Upload a reference video, describe your vision, and Firefly will generate a new video that transfers the original composition to your generation

Adobe Blog, new Firefly video capabilities

Wan, 10 November 2025

Users simply upload a character photo and a reference performance video, and the model transfers the expressions and actions from the video onto the character in the image

Alibaba Cloud Model Studio, newly released models

Adobe Firefly Video, 16 December 2025

With Firefly Video Model, you can now upload your start frame image, along with a reference video showing the camera motion you want to recreate.

Adobe Blog, Firefly video tools update

Kling AI, 22 December 2025

both reference images and reference videos need to be uploaded simultaneously

Kling AI, API updates
  • 12/22/2025
    Motion Control in the API takes a reference image and a reference video togetherKling AI, API updates / since 2025-12-22 / checked 2026-09-25

Wan, 3 April 2026

Supports hybrid referencing of up to 5 mixed image/video inputs and audio timbre cloning.

Alibaba Cloud Model Studio, newly released models

References and consistency · When did AI video models get camera controls? · Which AI video release notes claim better motion?

2Notes read

3Using the models, not reading about them

Release notes such as “Which AI video models take a reference video?” matter once a pipeline runs the models; SceneMixer's guides describe how it does:

Image and video models take a description as a list of things to put in the frame.

SceneMixer, Describe the Cause, Not the Result: The One Rule Behind Good Sheets and Good Shots (read 2026-10-13)

Wan 3.0 is Alibaba Cloud's video generation model on the Model Studio platform, called through an asynchronous submit-then-poll API, in two tiers: the standard wan3.0-video and the faster wan3.0-video-prime.

SceneMixer, Wan 3.0 for AI Short Drama (2026): Parameters, Reference Limits, Moderation Rules and the 30-Second Take (read 2026-10-13)