whatmodel.sh / video / DynamiCrafter (1024)
DynamiCrafter (1024)
↗ share
+ contribute
DynamiCrafter (1024) is an open-weights video model from CUHK / Tencent AI Lab (DynamiCrafter), released February 2024.
Catalogue identity notes
DynamiCrafter image-animation model (Xing et al., ECCV 2024), 1024x576 checkpoint Doubiiu/DynamiCrafter_1024 (pinned 73398ed; repo created 2024-02-03 per the HF API). PAI-Bench Table 12 gives the version 'DynamiCrafter_1024' (16 frames, 8 fps, 1024x576). The card states no licence in its metadata, so licence is left unset. Not mapped: MechVerse's 'DynamiCrafter' (resolution/checkpoint not stated). Comparison-only.
Model information sources
$ how it compares
The video models ranked either side of DynamiCrafter (1024), out of 139 with a score.
| # | model | score | where |
|---|---|---|---|
| 127 |  Hotshot-XL | 27±2 | local |
| 128 |  Lumiere (T2V) | 27±4 | comparison only |
| 129 | DynamiCrafter (1024) | 27±4 | comparison only |
| 130 |  Open-Sora 1.2 | 27±3 | local |
| 131 |  Runway Gen-2 | 27±2 | comparison only |
$ what it's good at
image to video▃▁▂▂██▄▃▃▄▂▂ #73 of 74 * · 92% of its score · 2 tests
Beats Pika 2.2 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| PAI-Bench-G human preference arena (Overall ELO) | 734.9 ✎ | ▄······██··█ beats 0/6 | 65% |
| PAI-Bench-G physical-AI video generation (Overall) | 68.3% ✎ | ▃······▅·█▅█ beats 0/10 | 28% |
$ where to run it
No verified API or download recorded yet · add one
Weights and documentation: huggingface.co/Doubiiu ↗
$ 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 | = 26.8 |
$ 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