HunyuanImage-3.0-Instruct

It is a native multimodal autoregressive model designed for image generation, supporting both text-to-image and image-to-image (TI2I) tasks. It features a unified architecture for multimodal understanding and generation, achieving performance comparable to leading closed-source models. The model includes two main variants: HunyuanImage-3.0 (text-to-image) and HunyuanImage-3.0-Instruct (enhanced with reasoning capabilities for intelligent prompt improvement and creative editing).

Key Features:

  • Unified Multimodal Architecture: Integrates text and image modalities within an autoregressive framework, enabling contextually rich and semantically accurate image generation.
  • Largest Open-Source Image Generation MoE Model:  Total parameters: 80 billion (13 billion active per token). Employs Mixture of Experts (MoE) with 64 experts.
  • Supported Tasks:
    • Text-to-Image (T2I): Generates images from text prompts.
    • Image-to-Image (TI2I): Edits or modifies existing images based on instructions (e.g., "modify logo style using reference image").
    • Multi-Image Fusion: Combines multiple input images into coherent outputs.
  • Intelligent Reasoning:  HunyuanImage-3.0-Instruct includes CoT (Chain-of-Thought) reasoning and prompt self-rewrite capabilities to enhance sparse or vague prompts. Enables context-aware editing (e.g., adding/removing elements, style transfers).
  • Hardware Requirements:  GPU: ≥8×80GB VRAM 

Announce Date: 28.01.2026
Parameters: 80B
Experts: 64
Activated at inference: 13B
Developer: Tencent
Transformers Version: 4.50.0
License: tencent-hunyuan-community

Public endpoint

Use our pre-built public endpoints for free to test inference and explore HunyuanImage-3.0-Instruct capabilities. You can obtain an API access token on the token management page after registration and verification.
Model Name Context Type GPU TPS Status Link
There are no public endpoints for this model yet.

Private server

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

  • maximize endpoint performance,
  • enable full context for long sequences,
  • ensure top-tier security for data processing in an isolated, dedicated environment,
  • use custom weights, such as fine-tuned models or LoRA adapters.

Recommended configurations for hosting HunyuanImage-3.0-Instruct

Prices:
Name vCPU RAM, MB Disk, GB GPU Price, hour
teslaa100-3.32.384.160 32 393216 160 3 $7.35 Launch
h100nvl-2.24.192.240 24 196608 240 2 $8.17 Launch
rtx5090-6.44.256.160 44 262144 160 6 $8.86 Launch
h200-2.24.256.160 24 262144 160 2 $9.40 Launch
h100-3.32.384.160 32 393216 160 3 $11.72 Launch
Prices:
Name vCPU RAM, MB Disk, GB GPU Price, hour
teslaa100-6.44.512.160.nvlink 44 524288 160 6 $14.06 Launch
h200-3.32.512.240 32 524288 240 3 $14.33 Launch
h100nvl-4.32.384.480 32 393216 480 4 $16.23 Launch
Prices:
Name vCPU RAM, MB Disk, GB GPU Price, hour
h200-6.52.896.640 52 917504 640 6 $28.36 Launch

Related models

HunyuanImage-3.0

Need help?

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.