Poe API
Hunyuan-Image-3
Hunyuan Image 3.0 is Tencent’s next‑generation open‑source text-to-image model that uses a large multimodal Mixture-of-Experts architecture to unify image understanding and generation in one system. It produces high-fidelity, often photorealistic images with strong prompt adherence, multilingual text rendering, and intelligent world-knowledge reasoning that can enrich sparse prompts with appropriate visual details.
Note: Uploading attachments is not supported.
Parameter controls available:
1. Image Settings
Size / Aspect Ratio
- Default: 1024x1024 (Square 1:1)
- 768x1024 (Portrait 3:4)
- 1024x768 (Landscape 4:3)
- 1024x1536 (Tall Portrait 2:3)
- 1536x1024 (Wide Landscape 3:2)
- 512x512 (Small Square 1:1)
Quantity
- number of images to generate. select from 1 to 4. (default: 1)
Quality & Generation
- Inference steps. Number of denoising steps for quality, select from 10 to 50. (default: 28, higher = better quality but slower)
- Guidance scale. Set to how closely to follow prompt, select from 1.0 to 20. (default: 7.5)
Customization
- Negative prompt. Type things to avoid in generated images
- Seed. Random seed number for reproducible generation with fixed seed (e.g., 42)
Powered by a server managed by @empiriolabsai. Learn more
- OFFICIAL
Build with Hunyuan-Image-3 using the Poe API
Start by creating an API key, for use with any bot on Poe:
See the full documentation for comprehensive guidance on getting started.
More from EmpirioLabs AI
New
DeepSeek-V4-Pro-EL
New
DeepSeek-V4-Flash-EL
New
HappyHorse-1.0-EL
New
MiMo-V2.5
New
MiMo-V2.5-Pro
Seed-2.0-Code
Seedream-5.0-Lite-EL
Qwen3.6-Max-Preview
Gemini-3.1-Flash-TTS
Seedance-2.0-Fast-EL