whatmodel.sh / video / CogVideoX-5B-I2V
CogVideoX-5B-I2V
↗ share
+ contribute
CogVideoX-5B-I2V is an open-weights video model from Zhipu AI (THUDM), released September 2024. Its published size is 5B parameters. Licence: cogvideox.
$ how it compares
The video models ranked either side of CogVideoX-5B-I2V, out of 139 with a score, then more from Zhipu AI (THUDM).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 83 |  LTX-2 19B Distilled | 47±8 | api $0.020/sec +local | ||
| 84 |  Cosmos-Predict2.5-14B | 47±3 | comparison only | ||
| 85 | CogVideoX-5B-I2V | 46±4 | local | ||
| 86 | Cosmos-1.0-Diffusion-7B-Text2World | 46±3 | local | ||
| 87 |  Hailuo 01 (MiniMax video-01 / I2V-01) | 46±4 | api $0.083/sec | ||
| more from Zhipu AI (THUDM) | |||||
| 91 | CogVideoX-5B | 44±2 | api price unknown +local | ||
| 113 | CogVideoX1.5-5B | 36±2 | local | ||
| 114 | CogVideoX-2B | 36±2 | local | ||
$ what it's good at
other tests4 not in a task · 94% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MindWorldBench intention accuracy (I2V mental-state reasoning) | 27.7% ✎ | ▅·▃▅·█·▃···▃ beats 5/9 | 31% |
| VideoArgus-Bench TI2V (rubric-grounded score) | 72.9% ✎ | █··▄▄▄▄····▄ beats 1/6 | 24% |
| WorldModelBench (human total) | 6.75 / 10 ✎ | ▅··▅▃···▃··█ beats 4/8 | 24% |
| MechVerse mechanical-motion I2V (WorldModelBench-judge sum) | 57.9% ✎ | ▃···▂······█ beats 0/5 | 15% |
$ where to run it
Other ways to run it
- Run it as published · needs ~12.5 GB, NVIDIA only · from huggingface.co/THUDM (official)
python -c "import torch;from diffusers import CogVideoXImageToVideoPipeline;from diffusers.utils import export_to_video,load_image;p=CogVideoXImageToVideoPipeline.from_pretrained('THUDM/CogVideoX-5b-I2V',torch_dtype=torch.bfloat16);p.enable_sequential_cpu_offload();p.vae.enable_tiling();p.vae.enable_slicing();export_to_video(p(prompt='A little girl is riding a bicycle at high speed. Focused, detailed, realistic.',image=load_image('input.jpg'),num_inference_steps=50,num_frames=49,guidance_scale=6).frames[0],'output.mp4',fps=8)"
Weights and documentation: huggingface.co/zai-org ↗
$ how the score was worked out · MindWorldBench: Evaluating Me… 31%, VideoArgus: Agentic Rubric-Gr… 24%, WorldModelBench: Judging Vide… 24% and 1 more
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 |
|---|---|---|
 MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation (arXiv:2609.39147v1) | 1 | 31% |
| VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing (arXiv:2608.05485v1) | 1 | 24% |
| WorldModelBench: Judging Video Generation Models As World Models | 1 | 24% |
| MechVerse: Evaluating Physical Motion Consistency in Video Generation Models (arXiv:2605.14843v1) | 1 | 15% |
| prior · pull toward the middle | 6% | |
| weighted average | = 46.4 |
$ 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