--- title: Z-Image-i2L canonical_url: "https://www.modelscope.cn/models/DiffSynth-Studio/Z-Image-i2L" md_url: "https://www.modelscope.cn/models/DiffSynth-Studio/Z-Image-i2L.md" repository: DiffSynth-Studio/Z-Image-i2L chinese_name: "Z-Image-i2L (Image to LoRA)" last_updated: 2026-01-30 license: "Apache License 2.0" base_model: - Tongyi-MAI/Z-Image base_model_relation: adapter parameters: 1.6B tensor_type: - BF16 library_name: - pytorch - safetensors frameworks: - Pytorch downloads: 7322 stars: 69 --- # Z-Image-i2L > Z-Image-i2L - DiffSynth-Studio 在 ModelScope 开源的模型。i2L (Image to LoRA) 模型是我们以疯狂的思路设计的模型结构。模型的输入为一张图片，输出为这张图片训练出的 LoRA 模型。本模型基于我们之前的 Qwen-Image-i2L（模型、技术博客），进一步完善并迁移到 Z-Image，着重增强了模型的风格保持能力。 DiffSynth-Studio/Z-Image-i2L 是 ModelScope 魔搭社区上的 1.6B 参数机器学习模型，采用 Apache License 2.0 许可，基于 Tongyi-MAI/Z-Image 构建。 - **Repository**: DiffSynth-Studio/Z-Image-i2L - **License**: Apache License 2.0 - **Parameters**: 1.6B - **Base model**: Tongyi-MAI/Z-Image - **Downloads**: 7322 - **Stars**: 69 - **Last updated**: 2026-01-30 Source: https://www.modelscope.cn/models/DiffSynth-Studio/Z-Image-i2L --- ## 模型介绍 i2L (Image to LoRA) 模型是我们以疯狂的思路设计的模型结构。模型的输入为一张图片，输出为这张图片训练出的 LoRA 模型。本模型基于我们之前的 Qwen-Image-i2L（[模型](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-i2L)、[技术博客](https://modelscope.cn/learn/3343)），进一步完善并迁移到 [Z-Image](https://modelscope.cn/models/Tongyi-MAI/Z-Image)，着重增强了模型的风格保持能力。 为保证生成的图像质量，我们建议按以下参数使用本模型产生的 LoRA 模型： * 使用负向提示词 * 中文：`"泛黄，发绿，模糊，低分辨率，低质量图像，扭曲的肢体，诡异的外观，丑陋，AI感，噪点，网格感，JPEG压缩条纹，异常的肢体，水印，乱码，意义不明的字符"` * 英文：`"Yellowed, green-tinted, blurry, low-resolution, low-quality image, distorted limbs, eerie appearance, ugly, AI-looking, noise, grid-like artifacts, JPEG compression artifacts, abnormal limbs, watermark, garbled text, meaningless characters"` * `cfg_scale = 4` * `sigma_shift = 8` * 仅在正向提示词侧启用 LoRA，在负向提示词侧关闭 LoRA，这会提升图像质量 在线体验：https://modelscope.cn/studios/DiffSynth-Studio/Z-Image-i2L ## 效果展示 Z-Image-i2L 模型可用于快速生成风格 LoRA，只需输入几张风格统一的图像。以下是我们生成的结果，随机种子都是 0。 ### 风格1：水彩绘画 输入图像： |![](./assets/style/1/0.jpg)|![](./assets/style/1/1.jpg)|![](./assets/style/1/2.jpg)|![](./assets/style/1/3.jpg)| |-|-|-|-| 生成图像： |a cat|a dog|a girl| |-|-|-| |![](./assets/style/1/image_0.jpg)|![](./assets/style/1/image_1.jpg)|![](./assets/style/1/image_2.jpg)| ### 风格2：写实细节 输入图像： |![](./assets/style/5/0.jpg)|![](./assets/style/5/1.jpg)|![](./assets/style/5/2.jpg)|![](./assets/style/5/3.jpg)|![](./assets/style/5/4.jpg)| |-|-|-|-|-| 生成图像： |a cat|a dog|a girl| |-|-|-| |![](./assets/style/5/image_0.jpg)|![](./assets/style/5/image_1.jpg)|![](./assets/style/5/image_2.jpg)| ### 风格3：缤纷色块 输入图像： |![](./assets/style/2/0.jpg)|![](./assets/style/2/1.jpg)|![](./assets/style/2/2.jpg)|![](./assets/style/2/3.jpg)|![](./assets/style/2/4.jpg)|![](./assets/style/2/5.jpg)| |-|-|-|-|-|-| 生成图像： |a cat|a dog|a girl| |-|-|-| |![](./assets/style/2/image_0.jpg)|![](./assets/style/2/image_1.jpg)|![](./assets/style/2/image_2.jpg)| ### 风格4：鲜花少女 输入图像： |![](./assets/style/3/0.jpg)|![](./assets/style/3/1.jpg)|![](./assets/style/3/2.jpg)|![](./assets/style/3/3.jpg)| |-|-|-|-| 生成图像： |a cat|a dog|a girl| |-|-|-| |![](./assets/style/3/image_0.jpg)|![](./assets/style/3/image_1.jpg)|![](./assets/style/3/image_2.jpg)| ### 风格5：幻想世界 输入图像： |![](./assets/style/4/0.jpg)|![](./assets/style/4/1.jpg)|![](./assets/style/4/2.jpg)|![](./assets/style/4/3.jpg)|![](./assets/style/4/4.jpg)|![](./assets/style/4/5.jpg)| |-|-|-|-|-|-| 生成图像： |a cat|a dog|a girl| |-|-|-| |![](./assets/style/4/image_0.jpg)|![](./assets/style/4/image_1.jpg)|![](./assets/style/4/image_2.jpg)| ## 推理代码 安装 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)： ```shell git clone https://github.com/modelscope/DiffSynth-Studio.git cd DiffSynth-Studio pip install -e . ``` 模型推理： ```python from diffsynth.pipelines.z_image import ( ZImagePipeline, ModelConfig, ZImageUnit_Image2LoRAEncode, ZImageUnit_Image2LoRADecode ) from modelscope import snapshot_download from safetensors.torch import save_file import torch from PIL import Image # Use `vram_config` to enable LoRA hot-loading vram_config = { "offload_dtype": torch.bfloat16, "offload_device": "cuda", "onload_dtype": torch.bfloat16, "onload_device": "cuda", "preparing_dtype": torch.bfloat16, "preparing_device": "cuda", "computation_dtype": torch.bfloat16, "computation_device": "cuda", } # Load models pipe = ZImagePipeline.from_pretrained( torch_dtype=torch.bfloat16, device="cuda", model_configs=[ ModelConfig(model_id="Tongyi-MAI/Z-Image", origin_file_pattern="transformer/*.safetensors", **vram_config), ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors"), ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"), ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="SigLIP2-G384/model.safetensors"), ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="DINOv3-7B/model.safetensors"), ModelConfig(model_id="DiffSynth-Studio/Z-Image-i2L", origin_file_pattern="model.safetensors"), ], tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"), ) # Load images snapshot_download( model_id="DiffSynth-Studio/Z-Image-i2L", allow_file_pattern="assets/style/*", local_dir="data/Z-Image-i2L_style_input" ) images = [Image.open(f"data/Z-Image-i2L_style_input/assets/style/1/{i}.jpg") for i in range(4)] # Image to LoRA with torch.no_grad(): embs = ZImageUnit_Image2LoRAEncode().process(pipe, image2lora_images=images) lora = ZImageUnit_Image2LoRADecode().process(pipe, **embs)["lora"] save_file(lora, "lora.safetensors") # Generate images prompt = "a cat" negative_prompt = "泛黄，发绿，模糊，低分辨率，低质量图像，扭曲的肢体，诡异的外观，丑陋，AI感，噪点，网格感，JPEG压缩条纹，异常的肢体，水印，乱码，意义不明的字符" image = pipe( prompt=prompt, negative_prompt=negative_prompt, seed=0, cfg_scale=4, num_inference_steps=50, positive_only_lora=lora, sigma_shift=8 ) image.save("image.jpg") ```