Vidu Reference-to-Video Q1
Open and Advanced Large-Scale Video Generative Models.
What it does
Vidu Reference-to-Video Q1, in practice.
- Maintains visual identity of characters and objects
- Preserves style and appearance across frames
- Supports multiple reference subjects
Run Vidu Reference-to-Video Q1
from $0.60/secParameters
What you can set.
| Parameter | What it does | Options |
|---|---|---|
seed | The random seed to use for the generation. | default |
images | Reference images for video generation. Requirements: 1. Accept 1-3 images; 2. Images can be URLs or Base64 encoded; 3. Supported formats: PNG, JPEG, JPG, WebP; 4. Minimum size: 128x128 pixels; 5. Aspect ratio: less than 1:4 or 4:1; 6. Maxim | |
prompt | Text prompt: A textual description for video generation, with a maximum length of 1500 characters. | |
aspect_ratio | The aspect ratio of the output video. Defaults to 16:9, accepted: 16:9 9:16 1:1. | 16:9 9:16 1:1 |
movement_amplitude | The movement amplitude of objects in the frame. Defaults to auto, accepted value: auto, small, medium, large. | auto small medium large |
FAQ
Short answers.
How much does Vidu Reference-to-Video Q1 cost?
Pricing starts at $0.60 per second of video at the base resolution; higher resolutions and longer durations cost more. An 8-second clip at the base tier is about $4.80. Usage is billed per request from your balance — no subscription.
Does Vidu Reference-to-Video Q1 run uncensored here?
No. Vidu applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Vidu Reference-to-Video Q1 for everything else it does well.
What does Vidu Reference-to-Video Q1 take as input?
It is a image-to-video model. Open and Advanced Large-Scale Video Generative Models.
How do I use it?
Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.
Related