whatmodel.sh / video / Wan2.1-I2V-14B-720P
Wan2.1-I2V-14B-720P
↗ share
+ contribute
Wan2.1-I2V-14B-720P is an open-weights video model from Alibaba, released February 2025. Its published size is 14B parameters. Licence: apache-2.0.
Catalogue identity notes
Alibaba Wan2.1 image-to-video 14B checkpoint at 720P (Wan-AI/Wan2.1-I2V-14B-720P, pinned 8823af4), released 25 Feb 2025 with Wan2.1. PAI-Bench Table 12 gives the version 'Wan2.1-I2V-14B-720P' (81 frames, 16 fps, 1280x720). Distinct from the catalogued T2V wan-2-1-14b and the API-only wan-2-1-i2v-plus / -turbo. Comparison-only: local route not verified in this pass.
Model information sources
Release date ↗ · Weights licence ↗
14B as named by Alibaba (model name); text and image encoders and VAE separate.
$ how it compares
The video models ranked either side of Wan2.1-I2V-14B-720P, out of 139 with a score, then more from Alibaba.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 76 |  MAGI-1 24B | 48±4 | comparison only | ||
| 77 |  Kandinsky 6.0 Video Pro | 48±7 | local | ||
| 78 | Wan2.1-I2V-14B-720P | 48±4 | comparison only | ||
| 79 |  Cosmos-Predict2-2B-Video2World | 48±8 | comparison only | ||
| 80 | Wan 2.1 14B | 47±2 | api $0.24/sec +local | ||
| more from Alibaba | |||||
| 2 | Wan 3.0 Prime | 80±7 | api $0.14/sec | ||
| 4 | Wan 3.0 | 79±2 | api $0.10/sec | ||
| 9 | HappyHorse 1.1 | 76±3 | api $0.14/sec | ||
$ what it's good at
image to video▁▁▂▂██▄▃▃▄▂▂ #56 of 74 * · 92% of its score · 2 tests
Beats HunyuanVideo 1.5, Wan 2.2 A14B, LTX-2 here, though they rank higher overall. Trails Hailuo 01 (MiniMax video-01 / I2V-01) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| PAI-Bench-G human preference arena (Overall ELO) | 976.0 ✎ | ▄······██··█ beats 2/6 | 69% |
| PAI-Bench-G physical-AI video generation (Overall) | 80.8% ✎ | ▃······▅·█▅█ beats 6/10 | 23% |
$ where to run it
No verified API or download recorded yet · add one
Weights and documentation: huggingface.co/Wan-AI ↗
$ how the score was worked out · PAI-Bench: A Comprehensive Be… 92%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 PAI-Bench: A Comprehensive Benchmark For Physical AI (arXiv:2512.01989v1) | 2 | 92% |
| prior · pull toward the middle | 8% | |
| weighted average | = 48.1 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json