hunyuan-image-3 ¶

Tier 7: 4,334 points · per image

Pricing¶

Website Pricing¶

Type	Cost
1 Image	4334 ($0.13)

All parsed rates (both currencies):

Service	Currency	Amount	Per
1 Image	USD	0.13	1 image
1 Image	POINTS	4334	1 image

Last Checked: 2026-10-22 13:26:37.285562

Bot Information¶

Creator: @empiriolabsai

Description: 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)

Extra: Powered by a server managed by @empiriolabsai. Learn more

Architecture¶

Input Modalities: text

Output Modalities: image

Modality: text->image

Technical Details¶

Model ID: hunyuan-image-3

Object Type: model

Created: 1764454998989

Owned By: EmpirioLabs AI

Root: hunyuan-image-3

API Last Updated: 2026-10-22 13:58:59.075186