Pick Vidu 2.0 if…
You want budget, fast turnaround, or multi-character scenes.
Pick HunyuanVideo 1.5 if…
You want avatar gen, custom characters, or research.
Specifications
Maker
Shengshu Tech
Tencent
Source Type
Closed Source
Open Source
License
Commercial
Tencent Open (check terms)
Architecture
U-ViT (DiT hybrid)
DiT + 3D Causal VAE
Parameters
Undisclosed
8.3B
Max Resolution
1080p
720p
Max Duration
10s
6-10s
FPS
24
24
Native Audio
No
No
ComfyUI Support
No
Yes
Fine-tunable
No
Yes
Min VRAM
Cloud only
24GB (RTX 4090)
Cost / Second
~$0.04
$0.06
Inputs
T2V, I2V
T2V, I2V, Avatar
On Floyo
No
Yes
Strengths & Trade-offs
Vidu 2.0
Strengths
- +Fastest gen (<10s)
- +55% cheaper than avg
- +multi-entity consistency
Trade-offs
- -Less known outside Asia
- -shorter clips
Best For
- →Budget
- →fast turnaround
- →multi-character scenes
HunyuanVideo 1.5
Strengths
- +Efficient 8.3B params
- +~75s on 4090
- +Avatar + Custom variants
Trade-offs
- -Short output
- -720p max
- -no audio
Best For
- →Avatar gen
- →custom characters
- →research
- →consumer GPU
Run these models on Floyo
Browser-based ComfyUI. No setup, no GPU required.
Audio/FoleyHunyuanVideo 1.5
HunyuanVideo Foley (Lifelike Audio)
I2VHunyuanVideo 1.5
HunyuanVideo 1.5 Image to Video