慕雪的小助手正在绞尽脑汁···
慕雪小助手的总结
DeepSeek & LongCat

引言

阿里巴巴通义实验室于2025.11.26开源了Z-Image图像生成模型，擅长写实摄影及中英文渲染。该系列包含多个版本，其中Turbo版已发布模型权重，Edit版和Base版即将上线。模型支持多模态输入，具备高精度语义理解能力，适用于广告、设计、内容创作等场景。开源版本可在ModelScope平台下载，为开发者提供灵活、高效的图像生成解决方案，推动AI视觉创作生态发展。

开源地址：https://modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo/

可以直接在魔搭社区登录后，在线测试Z-Image模型文生图效果。本文介绍如何在mac上本地部署这个模型。注意：你的mac至少需要有32GB内存才能够部署Z-Image。

下载ConfyUI

前往github：https://github.com/Comfy-Org/desktop，下载最新的测试版本0.5.11的mac安装包（只有最新版本才能正常部署Z-Image）。可以用下面的两个地址直接下载安装

下载完成后，拖拽ComfyUI到Application文件夹即可安装完成。首次打开时，ComfyUI需要初始化python环境，请确保你的mac上安装了homebrew和uv，保证能够正常初始化环境。因为我的电脑上本来就有uv环境，所以整个初始化环节非常顺利。

具体的安装和初始化教程可以参考：https://docs.comfy.org/zh-CN/installation/desktop/macos

前期的这些引导步骤全都选择默认就可以了，对于萌新来说没必要修改这些设置

image.png

image.png

image.png

这里有一个小点可以考虑修改，那就是这里的pypi安装镜像源，这里官方给的是错误的情况，会出现一个红x，请选择你当前网络环境中能够正常访问的镜像源来使用。

1
2
3
4
5
6
7
8
PyPI 镜像
阿里云：https://mirrors.aliyun.com/pypi/simple/
腾讯云：https://mirrors.cloud.tencent.com/pypi/simple/
中国科技大学：https://pypi.mirrors.ustc.edu.cn/simple/
上海交通大学：https://pypi.sjtu.edu.cn/simple/

Torch 镜像
阿里云: https://mirrors.aliyun.com/pytorch-wheels/cu121/

image.png

安装完成之后，就会进入桌面的UI页面，这就说明基本环境OK了

image.png

下载Z-Image模型并设置工作流

根据文档：https://comfyanonymous.github.io/ComfyUI_examples/z_image/里面的教程，下载三个模型文件，分别放到对应的目录下：

这个目录在mac上，默认是~/Documents/ComfyUI/models，找到这个目录，把下载的三个模型文件放入文件夹即可。

这是一个默认的路径，如果你修改过，可以在~/Library/Application Support/ComfyUI/extra_models_config.yaml文件里面查看本地模型路径是哪一个

image.png

配置工作流

使用需要配置ConfyUI的工作流，作为小白的我完全不会配置，直接抄作业！

把https://comfyanonymous.github.io/ComfyUI_examples/z_image/网站上的图片，拖拽到ConfyUI里面，就可以导入工作流了！

image.png

为了避免这个原始的网站失效，这里贴出来完整的json工作流配置，可以用这个json来导入。

完整工作流json配置（未修改） 
1
{"id":"92112d97-bb64-4b44-86f2-ea5691ef8f6e","revision":0,"last_node_id":27,"last_link_id":51,"nodes":[{"id":8,"type":"VAEDecode","pos":[1209,188],"size":[210,46],"flags":{},"order":9,"mode":0,"inputs":[{"localized_name":"Latent","name":"samples","type":"LATENT","link":51},{"localized_name":"vae","name":"vae","type":"VAE","link":45}],"outputs":[{"localized_name":"图像","name":"IMAGE","type":"IMAGE","slot_index":0,"links":[16]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.75","Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":9,"type":"SaveImage","pos":[1454.93896484375,190.9700164794922],"size":[976.0567626953125,1060.9766845703125],"flags":{},"order":10,"mode":0,"inputs":[{"localized_name":"图片","name":"images","type":"IMAGE","link":16},{"localized_name":"文件名前缀","name":"filename_prefix","type":"STRING","widget":{"name":"filename_prefix"},"link":null}],"outputs":[],"properties":{"cnr_id":"comfy-core","ver":"0.3.75"},"widgets_values":["ComfyUI"]},{"id":15,"type":"Note","pos":[71.95149993896484,192.96051025390625],"size":[319.26513671875,197.89625549316406],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[],"properties":{},"widgets_values":["The \"You are an assistant... <Prompt Start> \" text before the actual prompt is the one used in the official example.\n\nThe reason it is exposed to the user like this is because the model still works if you modify or remove it."],"color":"#432","bgcolor":"#653"},{"id":17,"type":"VAELoader","pos":[71.22825209024009,614.4132208648346],"size":[270,58],"flags":{},"order":1,"mode":0,"inputs":[{"localized_name":"vae名称","name":"vae_name","type":"COMBO","widget":{"name":"vae_name"},"link":null}],"outputs":[{"localized_name":"VAE","name":"VAE","type":"VAE","links":[45]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.75","Node name for S&R":"VAELoader"},"widgets_values":["ae.safetensors"]},{"id":13,"type":"EmptySD3LatentImage","pos":[530,620],"size":[315,106],"flags":{},"order":2,"mode":0,"inputs":[{"localized_name":"宽度","name":"width","type":"INT","widget":{"name":"width"},"link":null},{"localized_name":"高度","name":"height","type":"INT","widget":{"name":"height"},"link":null},{"localized_name":"批量大小","name":"batch_size","type":"INT","widget":{"name":"batch_size"},"link":null}],"outputs":[{"localized_name":"Latent","name":"LATENT","type":"LATENT","slot_index":0,"links":[17]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.75","Node name for S&R":"EmptySD3LatentImage"},"widgets_values":[1024,1024,1]},{"id":7,"type":"CLIPTextEncode","pos":[420,400],"size":[425.27801513671875,180.6060791015625],"flags":{},"order":6,"mode":0,"inputs":[{"localized_name":"clip","name":"clip","type":"CLIP","link":44},{"localized_name":"文本","name":"text","type":"STRING","widget":{"name":"text"},"link":null}],"outputs":[{"localized_name":"条件","name":"CONDITIONING","type":"CONDITIONING","slot_index":0,"links":[6]}],"title":"CLIP Text Encode (Negative Prompt)","properties":{"cnr_id":"comfy-core","ver":"0.3.75","Node name for S&R":"CLIPTextEncode"},"widgets_values":["blurry ugly bad"],"color":"#322","bgcolor":"#533"},{"id":18,"type":"CLIPLoader","pos":[80,460],"size":[270,106],"flags":{},"order":3,"mode":0,"inputs":[{"localized_name":"CLIP名称","name":"clip_name","type":"COMBO","widget":{"name":"clip_name"},"link":null},{"localized_name":"类型","name":"type","type":"COMBO","widget":{"name":"type"},"link":null},{"localized_name":"设备","name":"device","shape":7,"type":"COMBO","widget":{"name":"device"},"link":null}],"outputs":[{"localized_name":"CLIP","name":"CLIP","type":"CLIP","links":[43,44]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.75","Node name for S&R":"CLIPLoader"},"widgets_values":["qwen_3_4b.safetensors","lumina2","default"]},{"id":16,"type":"UNETLoader","pos":[80,60],"size":[270,82],"flags":{},"order":4,"mode":0,"inputs":[{"localized_name":"UNet名称","name":"unet_name","type":"COMBO","widget":{"name":"unet_name"},"link":null},{"localized_name":"数据类型","name":"weight_dtype","type":"COMBO","widget":{"name":"weight_dtype"},"link":null}],"outputs":[{"localized_name":"模型","name":"MODEL","type":"MODEL","links":[42]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.75","Node name for S&R":"UNETLoader"},"widgets_values":["z_image_turbo_bf16.safetensors","default"]},{"id":11,"type":"ModelSamplingAuraFlow","pos":[390,60],"size":[315,58],"flags":{},"order":7,"mode":4,"inputs":[{"localized_name":"模型","name":"model","type":"MODEL","link":42},{"localized_name":"移位","name":"shift","type":"FLOAT","widget":{"name":"shift"},"link":null}],"outputs":[{"localized_name":"模型","name":"MODEL","type":"MODEL","slot_index":0,"links":[47]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.75","Node name for S&R":"ModelSamplingAuraFlow"},"widgets_values":[3]},{"id":3,"type":"KSampler","pos":[863,186],"size":[315,262],"flags":{},"order":8,"mode":0,"inputs":[{"localized_name":"模型","name":"model","type":"MODEL","link":47},{"localized_name":"正面条件","name":"positive","type":"CONDITIONING","link":4},{"localized_name":"负面条件","name":"negative","type":"CONDITIONING","link":6},{"localized_name":"Latent图像","name":"latent_image","type":"LATENT","link":17},{"localized_name":"种子","name":"seed","type":"INT","widget":{"name":"seed"},"link":null},{"localized_name":"步数","name":"steps","type":"INT","widget":{"name":"steps"},"link":null},{"localized_name":"cfg","name":"cfg","type":"FLOAT","widget":{"name":"cfg"},"link":null},{"localized_name":"采样器名称","name":"sampler_name","type":"COMBO","widget":{"name":"sampler_name"},"link":null},{"localized_name":"调度器","name":"scheduler","type":"COMBO","widget":{"name":"scheduler"},"link":null},{"localized_name":"降噪","name":"denoise","type":"FLOAT","widget":{"name":"denoise"},"link":null}],"outputs":[{"localized_name":"Latent","name":"LATENT","type":"LATENT","slot_index":0,"links":[51]}],"properties":{"cnr_id":"comfy-core","ver":"0.3.75","Node name for S&R":"KSampler"},"widgets_values":[379878834255418,"randomize",9,1,"euler","simple",1]},{"id":6,"type":"CLIPTextEncode","pos":[420,190],"size":[423.83001708984375,177.11770629882812],"flags":{},"order":5,"mode":0,"inputs":[{"localized_name":"clip","name":"clip","type":"CLIP","link":43},{"localized_name":"文本","name":"text","type":"STRING","widget":{"name":"text"},"link":null}],"outputs":[{"localized_name":"条件","name":"CONDITIONING","type":"CONDITIONING","slot_index":0,"links":[4]}],"title":"CLIP Text Encode (Positive Prompt)","properties":{"cnr_id":"comfy-core","ver":"0.3.75","Node name for S&R":"CLIPTextEncode"},"widgets_values":["cute anime style girl with massive fluffy fennec ears and a big fluffy tail blonde messy long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress and a white apron, it is a postcard held by a hand in front of a beautiful realistic city at sunset and there is cursive writing that says \"ZImage, Now in ComfyUI\""],"color":"#232","bgcolor":"#353"}],"links":[[4,6,0,3,1,"CONDITIONING"],[6,7,0,3,2,"CONDITIONING"],[16,8,0,9,0,"IMAGE"],[17,13,0,3,3,"LATENT"],[42,16,0,11,0,"MODEL"],[43,18,0,6,0,"CLIP"],[44,18,0,7,0,"CLIP"],[45,17,0,8,1,"VAE"],[47,11,0,3,0,"MODEL"],[51,3,0,8,0,"LATENT"]],"groups":[],"config":{},"extra":{"ds":{"scale":0.5209868481924532,"offset":[569.5286501182709,292.7689360254662]},"frontendVersion":"1.30.6"},"version":0.4}

使用

配置好工作流后，可以直接点一次run来查看效果了。如果一切正常，模型都被加载了，是能够直接运行的！

如下图所示，这里是使用了默认的提示词，生成了一个猫娘的照片，同时上面有文字信息。第一次运行用了120s，第二次运行用了92s，使用的mac是m4pro 48g

image.png

提示词如下，我们只需要修改Positive节点的prompt和Native节点的prompt就可以让Z-Image生成其他我们想要的图片了。根据官网的描述，推荐使用英文prompt，效果会更好。

1
cute anime style girl with massive fluffy fennec ears and a big fluffy tail blonde messy long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress and a white apron, it is a postcard held by a hand in front of a beautiful realistic city at sunset and there is cursive writing that says "ZImage, Now in ComfyUI"

默认情况下，生成的图片是1024x1024的，可以通过修改这个节点来修改分辨率，分辨率越低生成图片速度越快。

image.png

到这里本地部署和使用就搞定啦，至于其他微调和奇怪的用法我还没有研究过，且听下回分解……