whatmodel.sh / video / HunyuanVideo-I2V
HunyuanVideo-I2V
↗ share
+ contribute
HunyuanVideo-I2V is an open-weights video model from Tencent, released March 2025. Licence: tencent-hunyuan-community.
Model information sources
$ how it compares
The video models ranked either side of HunyuanVideo-I2V, out of 139 with a score, then more from Tencent.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 88 |  Kling 1.6 (Standard mode) | 45±5 | comparison only | ||
| 89 |  Step-Video-T2V | 45±7 | comparison only | ||
| 90 | HunyuanVideo-I2V | 45±4 | local | ||
| 91 |  CogVideoX-5B | 44±2 | api price unknown +local | ||
| 92 | Step-Video-TI2V | 44±7 | comparison only | ||
| more from Tencent | |||||
| 55 | HunyuanVideo 1.5 (I2V) | 53±2 | api $0.075/sec +local | ||
| 58 |  HY-OmniWeaving | 52±4 | comparison only | ||
| 59 | HunyuanVideo 1.5 | 52±2 | api $0.075/sec +local | ||
$ what it's good at
image to video▁▂·▂▅█▅▄▅▆▃▄ #45 of 50 · 95% of its score · 3 tests
Beats Wan 2.2 A14B, LTX-2 here, though they rank higher overall. Trails Wan 2.1 I2V Turbo here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| PAI-Bench-G human preference arena (Overall ELO) | 964.3 ✎ | ▄······██··█ beats 1/6 | 43% |
| SkyReels-Bench I2V (human rating) | 56.8% ✎ | ▄···▄······█ beats 0/3 | 37% |
| PAI-Bench-G physical-AI video generation (Overall) | 77.6% ✎ | ▃······▅·█▅█ beats 2/10 | 15% |
$ where to run it
Other ways to run it
- Run it as published · needs ~57.3 GB, NVIDIA only · from huggingface.co/tencent (official)
git clone https://github.com/Tencent-Hunyuan/HunyuanVideo-I2V && cd HunyuanVideo-I2V && conda create -y -n HunyuanVideo-I2V python==3.11.9 && conda install -y -n HunyuanVideo-I2V pytorch==2.4.0 torchvision==0.19.0 torchaudio==2.4.0 pytorch-cuda=12.4 -c pytorch -c nvidia && conda run -n HunyuanVideo-I2V python -m pip install -r requirements.txt "huggingface_hub[cli]" && conda run -n HunyuanVideo-I2V huggingface-cli download tencent/HunyuanVideo-I2V --local-dir ./ckpts && conda run -n HunyuanVideo-I2V huggingface-cli download xtuner/llava-llama-3-8b-v1_1-transformers --local-dir ./ckpts/text_encoder_i2v && conda run -n HunyuanVideo-I2V huggingface-cli download openai/clip-vit-large-patch14 --local-dir ./ckpts/text_encoder_2 && conda run -n HunyuanVideo-I2V python3 sample_image2video.py --model HYVideo-T/2 --prompt "An Asian man with short hair in black tactical uniform and white clothes waves a firework stick." --i2v-mode --i2v-image-path ./assets/demo/i2v/imgs/0.jpg --i2v-resolution 720p --i2v-stability --infer-steps 50 --video-length 129 --flow-reverse --flow-shift 7.0 --seed 0 --embedded-cfg-scale 6.0 --use-cpu-offload --save-path ./results
Official weights and documentation: huggingface.co/tencent ↗
$ how the score was worked out · PAI-Bench: A Comprehensive Be… 58%, SkyReels-V2: Infinite-length… 37%
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 | 58% |
| SkyReels-V2: Infinite-length Film Generative Model | 1 | 37% |
| prior · pull toward the middle | 5% | |
| weighted average | = 44.6 |
$ 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