Reference-to-video models use one or more reference images to steer a generation — useful for keeping a character or a product consistent across clips. All 7 of them are below, ranked by the best position each holds on a Versely leaderboard.
Ranking method
Filtered to models with the reference-to-video category, sorted by best leaderboard position (unranked models after, cheapest complete job first).
Full ranking
| # | Model | Provider | Credits | Reference images |
|---|---|---|---|---|
| 1 | Seedance 2.0 | ByteDance | 22-1639 credits | — |
| 2 | Wan 2.7 Reference to Video | Wan | 10-72 credits | — |
| 3 | Gemini Omni Video | 15-74 credits | — | |
| 4 | Happy Horse 1.0 Reference to Video | Alibaba | 17-168 credits | — |
| 5 | Seedance 2.0 Fast Reference to Video | ByteDance | 39-146 credits | — |
| 6 | Kling O3 Standard Reference to Video | Kling | 45-135 credits | — |
| 7 | VEO 3.1 Reference to Video | 128-256 credits | — |
The top 5, explained
#1 — Seedance 2.0 (ByteDance) costs 22-1639 credits, discounted from a headline 44 and sits at #11 in text to video on Versely's live model rankings. It outputs up to 4k. Reference images: —.
#2 — Wan 2.7 Reference to Video (Wan) costs 10-72 credits, discounted from a headline 20 and does not currently hold a position on any Versely leaderboard. It outputs up to 1080p. Reference images: —.
#3 — Gemini Omni Video (Google) costs 15-74 credits, discounted from a headline 29 and does not currently hold a position on any Versely leaderboard. It outputs up to 4K. Reference images: —.
#4 — Happy Horse 1.0 Reference to Video (Alibaba) costs 17-168 credits, discounted from a headline 34 and does not currently hold a position on any Versely leaderboard. It outputs up to 1080p. Reference images: —.
#5 — Seedance 2.0 Fast Reference to Video (ByteDance) costs 39-146 credits, discounted from a headline 78 and does not currently hold a position on any Versely leaderboard. It outputs up to 720p. Reference images: —.
Compare these models head-to-head
More capability rankings
Frequently asked questions
What is the best reference-to-video AI model?+
Seedance 2.0 by ByteDance tops this ranking. Filtered to models with the reference-to-video category, sorted by best leaderboard position (unranked models after, cheapest complete job first). Seedance 2.0 costs 22-1639 credits and sits at #11 in text to video on Versely's live model rankings.
How is this ranking calculated?+
Filtered to models with the reference-to-video category, sorted by best leaderboard position (unranked models after, cheapest complete job first).
How many models qualify for this ranking?+
7 models with a page on Versely meet the criteria for "Best reference-to-video AI model", across 5 providers.
What's the cheapest option in this ranking?+
Wan 2.7 Reference to Video is the cheapest at 10-72 credits, against 22-1639 credits for Seedance 2.0, the top-ranked entry.
Do all of these models hold a Versely leaderboard position?+
1 of the 7 models here hold a position on at least one Versely leaderboard; the remaining 6 are unranked and listed afterward, cheapest complete job first.
Try Seedance 2.0 inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync, in your browser or on your phone.
One account for the web and iPhone.