zhipu-ai/z-image models

each::sense is in private beta.
Eachlabs | AI Workflows for app builders

zhipu-ai/z-image

Generate stunning visuals with Z-Image. A powerful text-to-image model excelling in Asian aesthetics and complex scenes.

Models

A text-to-image endpoint with LoRA support, powered by Tongyi-MAI’s ultra-fast 6B Z-Image Turbo model for efficient, high-quality image generation.

z-image-turbo-lora
Z Image | Turbo | Lora

Generates images from text combined with edge, depth, or pose inputs using Tongyi-MAI’s ultra-fast 6B Z-Image Turbo model for precise and high-quality results.

z-image-turbo-controlnet
Z Image | Turbo | Controlnet

LoRA training for Z-Image models, allowing quick style and identity fine-tuning with stable, high-quality results.

z-image-trainer
Z Image | Trainer

Generates images from text combined with edge, depth, or pose inputs using custom LoRA and Tongyi-MAI’s ultra-fast 6B Z-Image Turbo model for fast, high-quality, and controllable image creation.

z-image-turbo-controlnet-lora
Z Image | Turbo | Controlnet | Lora

Z-Image Turbo is an ultra-fast 6B-parameter text-to-image model developed by Tongyi-MAI, designed for rapid and high-quality image generation.

z-image-turbo-text-to-image
Z Image | Turbo | Text to Image

Creates images from text and reference images with custom LoRA support, powered by Tongyi-MAI’s ultra-fast 6B Z-Image Turbo model for rapid, high-quality generation.

z-image-turbo-image-to-image-lora
Z Image | Turbo | Image to Image | Lora

Generates images from text and reference images using Tongyi-MAI’s ultra-fast 6B Z-Image Turbo model for fast, high-quality visual results.

z-image-turbo-image-to-image
Z Image | Turbo | Image to Image
FREQUENTLY ASKED QUESTIONS

Dev questions, real answers.

Z-Image is available on Eachlabs, allowing for pay-as-you-go image generation.

Yes, it excels at both photorealism and stylized art like anime and traditional illustration.

Yes, it understands both English and Chinese prompts with high accuracy.