vidu/vidu-image-lite_reference2image
Input 0-14 reference images or text descriptions. Supports reference-based image generation, text-to-image, and image editing with precise rendering of Chinese and English text, pixel-level restoration of UI/chart design details. Suitable for creating posters, infographics, etc.
Inference Service Provider
The inference service for vidu/vidu-image-lite_reference2image is provided by Vidu.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image | Output Modality | Image |
Playground | Unsupported | Function Calling | Unsupported |
Structured Output | Unsupported | Web Search | Unsupported |
Prefix Continuation | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Model Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Maximum Input Length | - | Maximum Output Length | - |
Context Length | - |
Model Pricing
This page only shows the original price of model calls, excluding limited-time promotions. Please visit the Model Studio console for promotional pricing.
China (Beijing)
| Billing Item | Price (CNY) | Unit |
|---|---|---|
Image generation (1080P) | 0.3125 | Per image |
Image generation (2K) | 0.34375 | Per image |
Image generation (4K) | 0.40625 | Per image |
Rate Limits
China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 300 |
Number of concurrent tasks | 5 |
For a single Alibaba Cloud Model Studio API key, the following Vidu reference image generation models share a concurrency limit of 5: vidu/vidu-image-pro_reference2image, vidu/vidu-image-lite_reference2image, vidu/vidu-image_reference2image, vidu/viduq3-fast_reference2image, vidu/viduq2-pro_reference2image, and vidu/viduq2-fast_reference2image. This means that the total number of running tasks for these models cannot exceed 5.