Generation highlights
How the top models compare
Best models, by
Best Image-to-Video Models by Price
Best Image-to-Video Models by Speed
1 model waiting for enough speed data.
Best AI Models for Image-to-Video
| # | Model | Elo |
|---|---|---|
| 1 | 1162 | |
| 2 | 1065 | |
| 3 | 990 |
As of July 2026, Seedance 2.0 dominates the Image-to-Video leaderboard with an Elo of 1162 and a commanding 77.8% win rate, maintaining a significant 117-point lead over its nearest competitor. Competition for the runner-up spot is tight, with Alibaba’s Wan 2.6 (1045 Elo) holding a narrow 50-point margin over xAI’s Grok Imagine Video (995 Elo). Despite its lower ranking, Wan 2.6 presents a high-efficiency alternative, delivering competitive video quality at a 78% lower price point and over eight times the processing speed of the top-ranked Seedance 2.0.
Highlighted challenges
Celebrity Arrival
This is a strong stress test for video models because it combines identity consistency, chaotic crowd motion, handheld camera behavior, realistic lighting, and multi-step scene progression in one continuous shot. Models often struggle when a recognizable subject has to stay consistent while partially obscured, moving through a dense environment, interacting with fans, and entering a vehicle.
FAQ
What is the best AI image-to-video model?
Based on blind community voting, Seedance 2.0 is currently the #1 ranked AI image-to-video model with an Elo rating of 1162. Rankings update in real time as new votes come in.
How are AI image-to-video models ranked on Lumenfall?
Lumenfall Arena ranks AI models through blind community voting. In each matchup, two models generate from the same prompt and voters pick the better result without seeing model names. Votes are processed using TrueSkill, a Bayesian rating algorithm developed by Microsoft Research, that produces a single Elo score reflecting each model's relative quality.
What is an Elo rating for AI models?
An Elo rating is a numerical score representing a model's skill relative to other models. Under the hood, Lumenfall uses TrueSkill, which tracks two values per model: mu (estimated skill) and sigma (uncertainty). The displayed Elo is calculated as 1000 + 10 x (mu - 3*sigma), a conservative lower bound. A model must prove itself consistently across many matchups to earn a high rating.
Keep the arena honest
Cast your vote
Pick winners in blind matchups. Every vote nudges the Elo and shapes these rankings.
Cast Your VoteSuggest a prompt
Got an idea worth testing? Submit a prompt and watch the models battle it out.