TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

Z Image i2l

By Z.ai
Z-Image i2L is a 1.61B-parameter Image-to-LoRA model built on Alibaba Tongyi’s Z-Image architecture. Given one to a handful of images, it directly outputs LoRA weights under an Apache-2.0 license, running on 16 GB GPUs and producing LoRAs in under about 10 seconds. Compared with Qwen-Image i2L, it focuses on stronger style preservation and roughly 20 percent less detail loss, making it well suited to artists, e-commerce design and fast personalized style transfer workflows.
New Image Gen 4
Released: January 27, 2026

Overview

Z-Image i2L is Alibaba Tongyi’s 1.61B-parameter Image-to-LoRA model that converts one or a few style-consistent images into ready-to-use LoRA weights in under about 10 seconds, greatly improving style and detail retention over Qwen-Image i2L.

About Z.ai

Z.ai (formerly Zhipu AI) is a Chinese AI company developing large language models (GLM series), combining reasoning, coding, and agent capabilities, and offering open models and APIs.

Company Size: 500
Location: Beijing, Beijing, CN
Website: chat.z.ai
View Company Profile

Tools using Z Image i2l

No tools found for this model yet.

Last updated: February 3, 2026
0 AIs selected
Clear selection
#
Name
Task