tencent cloud

LLM Service TokenHub

Image Generation Model Invocation Overview

Unduh
Mode fokus
Ukuran font
Terakhir diperbarui: 2026-11-09 20:19:18
Diterjemahkan oleh AI

Overview

The TokenHub image generation models on the large model service platform provide capabilities such as text-to-image, reference-to-image, and image editing, covering model series including Hunyuan and Vidu. This document serves as a quick navigation and selection guide for each model.
Note:
For detailed parameters, request examples, and response fields of each API, refer to the corresponding call guide. For billing information, see TokenHub Model Pricing.

Model List

Hy Image Generation Series

For details, see the Hy Image Generation API Guide.
Model Name
model Parameter Value
Supported Capability
API Type
Brief Description
Hy-Image-3.0
hy-image-v3
Text-to-image/reference-based image generation
Sync
Supports automatic prompt rewriting, 37 preset sizes, and custom watermark footnotes.
Hy-Image-3.5-preview
hy-image-v3.5-preview
Text-to-image/reference-based image generation/multi-turn editing
Sync
Supports multimodal input, multi-turn editing context, external search enhancement, and automatic size determination by area tier.

WAND Image Generation Series

For details, see the WAND Image Generation API Guide.
Model Name
Model (API Parameter)
Supported Capability
Prompt Limit
Resolution
Aspect Ratio
WAND-Vega-Image-1.0-Lite
wand-vega-image-lite
Text-to-image/reference-based image generation
2000 characters
1K / 2K / 4K
Supports common aspect ratios of 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, and 21:9. For details, see the preset size list.
WAND-Vega-Image-1.0-Flash
wand-vega-image-flash
Text-to-image/reference-based image generation
2000 characters
1K / 2K / 4K
WAND-Vega-Image-1.0-Pro
wand-vega-image-pro
Text-to-image/reference-based image generation
2000 characters
1K / 2K / 4K

Vidu Image Generation Series

For details, see the Vidu Image Generation API Guide.
Model Name
model Parameter Value
Supported Capability
API Type
Brief Description
Vidu-Image-q2
vidu-image-q2
Reference-based image generation / text-to-image / image editing
Asynchronous
Supports 0 to 7 reference images to maintain subject consistency, with direct output in 1080p / 2K / 4K ultra-high definition.

Seedream Image Generation Series

Model Name
model Parameter Value
Supported Capability
API Type
Brief Description
Seedream-Image-v5.0-pro
seedream-image-v5.0-pro
Reference-based image generation/text-to-image generation
Sync
Flagship high-precision image generation, precise coordinate editing
Seedream-Image-v5.0-lite
seedream-image-v5.0-lite
Reference-based image generation/text-to-image generation
Sync
Lightweight and fast, real-time online search, cost-effective image generation
Seedream-Image-v5.0-flash
seedream-image-v5.0-flash
Reference-based image generation/text-to-image generation
Sync
High-speed image generation model with faster output and lower cost

Kling Image Generation Series

For details, see the Kling Image Generation API Guide.
Model Name
model Parameter Value
Supported Capability
API Type
Brief Description
Kling-Image-v3
kling-image-v3
Text-to-image generation/image-to-image generation (single-image reference)
Asynchronous
Generates 2K/4K ultra-high-definition images, with further enhanced realism and detail consistency.
Kling-Image-o1
kling-image-o1
Text-to-image generation/image-to-image generation (multi-image reference)
Asynchronous
Multimodal reasoning image generation engine, integrated generation and editing, locks subject consistency with 10 images.
Kling-Image-v3-omni
kling-image-v3-omni
Text-to-image generation/image-to-image generation (multi-image reference)/series image generation
Asynchronous
Omnipotent reference-based image generation, cinematic narrative expression, and support for series image generation.

HiDream Image Generation Series

Model Name
model Parameter Value
Supported Capability
Input Limit
Size Constraint
Brief Description
HiDream-O1-Image-1.5
hidream-image-o1-1.5
Text-to-image generation (synchronous)
5000 characters
7 preset sizes, native 2K
A primary text-to-image model that excels in text rendering, complex layouts, long prompt comprehension, and multi-subject control, suitable for scenarios such as e-commerce hero images, marketing posters, brand materials, and film storyboards.
HiDream-O1-Image-Edit-1.5
hidream-image-o1-1.5-edit
Image-to-image generation / image editing (synchronous)
5000 characters; 1 to 6 reference images
7 preset sizes, native 2K
Edit with natural language instructions without masks. Multiple reference images can lock the appearance of characters, products, or IPs, making the model suitable for product retouching, background replacement, poster revision, and character extension.

Bantuan dan Dukungan

Apakah halaman ini membantu?

masukan