whatmodel.sh / video / ZeroScope v2 576w

ZeroScope v2 576w

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

ZeroScope v2 576w is an open-weights video model from cerspense, released June 2023. Licence: cc-by-nc-4.0.

27.3±3.0#85 of 93 video modelsfrom 4 benchmark results across 3 sources

$ how it compares

The video models ranked either side of ZeroScope v2 576w, out of 139 with a score, then more from cerspense.

#modelscorewhereRAMreleased
124Cosmos-1.0-Autoregressive-5B-Video2World NVIDIA31±5comparison only2025-01
125NOVA-0.6B T2V BAAI29±3local~9.3GB2024-12
126ZeroScope v2 576w cerspense27±3local~7.9GB2023-06
127Hotshot-XL Hotshot27±2local~10GB2023-10
128Lumiere (T2V) Google27±4comparison only2024-01
more from cerspense
138ZeroScope v2 XL (576w → XL pipeline) cerspense24±2local~15GB2023-06

see all video models · find the ones that fit your machine

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #61 of 68 · 96% of its score · 4 tests

Trails Hotshot-XL here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
VideoPhy (human, SA=1 & PC=1)11.9% ✎▄▄▄·▄▄█····▄ beats 2/7medium · avg 48%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%sharp
VideoPhy (auto-evaluator average)34.0% ✎▅·▃▅··▃█···▃ beats 3/9medium · avg 56%▇▇▇▇▇▇▇▇ 19%at its level
ChronoMagic-Bench-150 GPT4o-MTScore (time-lapse metamorphosis)45.8% ✎▄·▄█▄▄▄·▄·▄█ beats 0/10medium · avg 71%▇▇▇▇▇▇ 16%at its level
FETV manual video quality (mean of static and temporal quality)3.62 / 5 ✎█·····█····█ beats 1/2very easy · avg 4.63 / 5▇▇▇▇▇▇ 15%at its level · small run

$ where to run it

Other ways to run it

  1. Run it as published · needs ~7.9 GB, NVIDIA only · from huggingface.co/cerspense (official)
    python -c "import torch;from diffusers import DiffusionPipeline;from diffusers.utils import export_to_video;p=DiffusionPipeline.from_pretrained('cerspense/zeroscope_v2_576w',torch_dtype=torch.float16);p.enable_model_cpu_offload();export_to_video(p('Darth Vader is surfing on waves',num_inference_steps=40,height=320,width=576,num_frames=24).frames[0],'zeroscope.mp4')"

Official weights and documentation: huggingface.co/cerspense ↗

$ how the score was worked out · VideoPhy / VideoPhy-2 officia… 65%, ChronoMagic-Bench: A Benchmar… 16%, FETV: A Benchmark for Fine-Gr… 15%

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

sourceresultsshare of the scorelicence
VideoPhy / VideoPhy-2 official repository leaderboards2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 65%MIT
ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation1▇▇▇▇▇ 16%CC-BY-4.0
FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation (arXiv:2311.01813v3)1▇▇▇▇▇ 15%CC BY 4.0
prior · pull toward the middle▇ 4%
weighted average= 27.3

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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