Tencent HunyuanZ.aiVideo model matchup
HunyuanVideo I2V 1.0vs.CogVideoX1.5-5B I2V
Neither HunyuanVideo I2V 1.0 nor CogVideoX1.5-5B I2V has an LMArena rating yet.
HunyuanVideo I2V 1.0
CogVideoX1.5-5B I2V
Same prompt, both models
The first clip from a single request each, showing the first five seconds.
What to look for: Start-frame fidelity, subject identity, cloth motion, camera push-in. Sound muted, as the test protocol requires.
HunyuanVideo I2V 1.0
Run details
fal.ai. fal-ai/hunyuan-video-image-to-video. 16:9, one request, first output, prompt image-to-video-start-frame, requested 5 s, audio off, seed 908, request {"prompt":"Animate this exact image as one continuous five-second 16:9 shot. The golden retriever stays standing on the rock, slowly turns its head to the left toward the valley, then looks back at the camera. The red cape ripples continuously in the wind, the glowing particles drift to the right, and the clouds move slowly. The camera pushes in gently. Keep the dog's face, fur color, harness, cape, and the landscape consistent with the first frame. No cuts, no text, no logos, no subtitles.","image_url":"<start image sha256:7b63c2217e6a3a645b3c1f52df68751fd1f3378f4d7639dd3ca38b4ec05a77f2>","num_frames":129,"resolution":"720p","aspect_ratio":"16:9"}, configured price estimate $0.40, enforced estimate $0.40.
Generated Nov 1, 2026. Source
CogVideoX1.5-5B I2V
No clip: this task has not yet been tested for the model.
Show the prompt given to both models
Animate this exact image as one continuous five-second 16:9 shot. The golden retriever stays standing on the rock, slowly turns its head to the left toward the valley, then looks back at the camera. The red cape ripples continuously in the wind, the glowing particles drift to the right, and the clouds move slowly. The camera pushes in gently. Keep the dog's face, fur color, harness, cape, and the landscape consistent with the first frame. No cuts, no text, no logos, no subtitles.
Where is the difference?
Bar length shows the gap: for ratings full width from 60 points, for price from four times as much, for clip length from 20 seconds. Solid means clearly ahead, hatched slightly ahead, a thin grey bar level.
All data side by side
The better value is bold. For ratings only when the gap is clear.
| Metric | HunyuanVideo I2V 1.0 | CogVideoX1.5-5B I2V |
|---|---|---|
| Output | ||
| Resolution | 720p | bis 1360 px lange Seite; kurze Seite mindestens 768 px |
| Longest clip | n/a | 6 s |
| Access | ||
| Weights | open | open |
| Parameters | 13B | 5B |
| Routes | local | local |
| Released | Mar 6, 2025 | Nov 8, 2024 |
| Status | available | available |
Prices: public API price of the documented standard configuration; resolution and sound can change it
Is there a better choice?
Text to video 1,516, Place 1 of 23. $0.51 per 5 s clip.
HunyuanVideo I2V 1.0 vs. Gemini Omni 1.1 FlashSources and method
Show 2 sources and the method
Ratings come from the LMArena: people see two videos for the same prompt without knowing which model made them and pick the better one. Many such picks add up to a rating, higher is better. Text to video and image to video are separate lists and are never added together.
“Ahead” means one model stays clearly higher even with the rating’s uncertainty. “Slightly ahead” means its value is higher but the gap is not certain yet. Otherwise both count as level. Places count only the models of our comparison.
Prices and clip lengths come from the providers’ documentation. From a factor of 1.25 a model counts as cheaper or longer, below that as about the same.
- HunyuanVideo I2V 1.0, specifications, checked Nov 1, 2026
- CogVideoX1.5-5B I2V, specifications, checked Nov 1, 2026
Compare another matchup
More matchups
Related video model comparisons
Compare HunyuanVideo I2V 1.0 and CogVideoX1.5-5B I2V with other important video models.