ShipAny Blog

Blog

Read about our latest product features, solutions, and updates.

ERNIE-Image vs Z-Image vs Qwen-Image-2: Which Open-Source Text-to-Image Model Performs Better?

Baidu recently open-sourced the text-to-image model ERNIE-Image, and ComfyUI added support for it very quickly. According to the official introduction

4月 20, 2026
Z-Image Team

ComfyUI实践指南:手把手教你玩转ERNIE-Image!

最近,全新文生图开源模型——ERNIE-Image正式与大家见面了。它基于 8B 参数的 DiT 架构,在复杂指令跟随、文字渲染和结构化图像生成方面表现突出,覆盖了从写实摄影、设计感图像到风格化表达在内的多种视觉风格,因此尤其适合海报、漫画、多面板布局等需要较强控制能力的内容生产场景。 [ERNIE

4月 20, 2026
Z-Image Team

ComfyUI Practical Guide: A Hands-on Walkthrough for ERNIE-Image!

Recently, the new open-source text-to-image model ERNIE-Image officially made its debut. Built on an 8B-parameter DiT architecture, it stands out in c

4月 20, 2026
Z-Image Team

百度最新开源的文生图模型 ERNIE-Image 与 Z-Image/Qwen-Image2 孰强孰弱(真实质感/文本渲染/自然风光/尺寸兼容/显存占用/推理速度)

最近百度开源了文生图模型 ERNIE-Image,ComfyUI 也在第一时间进行了支持,官方介绍该模型具有如下特点: - 自带提示语增强:可将简短的用户输入扩展为更丰富的结构化描述 - 文本渲染:在处理密集、长篇幅且对布局要求较高的文本时表现尤为出色,因此是海报、信息图表、用户界面图像和其他文字密

4月 20, 2026
Z-Image Team
ernie-image comfyui 怎么用?一篇讲清安装部署、模型下载和工作流配置

ernie-image comfyui 怎么用?一篇讲清安装部署、模型下载和工作流配置

**ComfyUI 第一时间支持了 ERNIE-Image 模型**。 这件事真正有意思的地方,不只是多了一个可用模型,而是 ERNIE-Image 终于可以更顺畅地进入 ComfyUI 工作流:从安装、权重加载,到参数调试、模板复用,再到正式出图,整条链路都更清晰了。 如果你想解决的是这些问题:

4月 20, 2026
Z-Image Team
ernie-image comfyui 怎么用?一篇讲清安装部署、模型下载和工作流配置

ernie-image comfyui 怎么用?一篇讲清安装部署、模型下载和工作流配置

**ComfyUI 第一时间支持了 ERNIE-Image 模型**。 这件事真正有意思的地方,不只是多了一个可用模型,而是 ERNIE-Image 终于可以更顺畅地进入 ComfyUI 工作流:从安装、权重加载,到参数调试、模板复用,再到正式出图,整条链路都更清晰了。 如果你想解决的是这些问题:

4月 20, 2026
Z-Image Team
ERNIE-Image Explained: How Baidu’s Open Text-to-Image Model Improves Text Rendering and Structured Generation

ERNIE-Image Explained: How Baidu’s Open Text-to-Image Model Improves Text Rendering and Structured Generation

Today’s text-to-image race is no longer just about who can generate the most eye-catching visuals. Once AI image generation enters real design workflo

4月 19, 2026
Z-Image Team
ERNIE-Image详解:百度开源文生图模型如何突破文字渲染与结构生成

ERNIE-Image详解:百度开源文生图模型如何突破文字渲染与结构生成

当下的文生图竞争,已经不只是比谁出图更惊艳。真正进入设计、内容生产和商业落地环节后,行业更在意的是几个更难的问题:图片里的字能不能写对,复杂指令能不能被稳定执行,多元素画面能不能排得清楚,海报、信息图、漫画分镜这类结构化任务能不能真正交付。 从百度官方博客披露的信息来看,ERNIE-Image 的价

4月 19, 2026
Z-Image Team
How to Install LTX-2 GGUF Models in ComfyUI: Files, Paths, and Setup Steps

How to Install LTX-2 GGUF Models in ComfyUI: Files, Paths, and Setup Steps

Install LTX-2 GGUF models in ComfyUI with the required files, model paths, node setup, and common fixes so you can get quantized video workflows running correctly.

1月 10, 2026
Z-Image Team
Run Z-Image Turbo on 6GB-8GB VRAM: Quantized Models, Setup, and Performance

Run Z-Image Turbo on 6GB-8GB VRAM: Quantized Models, Setup, and Performance

Run Z-Image Turbo on low VRAM GPUs with quantized models, setup steps, format differences, and realistic performance expectations for 6GB to 8GB cards.

1月 5, 2026
Z-Image Team
How to Train Better LoRA Models with Z-Image: Dataset, Captions, and Settings

How to Train Better LoRA Models with Z-Image: Dataset, Captions, and Settings

Learn how to improve LoRA training with better datasets, caption strategy, core settings, and common mistakes to avoid when training models with Z-Image.

12月 31, 2025
Zimage.run Team
How to Set Up LTX-2 in ComfyUI: Models, Workflow, and Download Links

How to Set Up LTX-2 in ComfyUI: Models, Workflow, and Download Links

Set up LTX-2 in ComfyUI with the required models, workflow steps, download links, and VRAM guidance. A practical setup guide for getting video generation running faster.

1月 8, 2026
Z-Image Team
TADA: 1:1 Alignment Makes Speech Generation 5x Faster

TADA: 1:1 Alignment Makes Speech Generation 5x Faster

--- title: "TADA: 1:1 Alignment Makes Speech Generation 5x Faster" date: 2026-03-11

3月 12, 2026
Z-Image Team
TADA:1:1 对齐让语音生成快 5 倍

TADA:1:1 对齐让语音生成快 5 倍

--- title: "TADA:1:1 对齐让语音生成快 5 倍" date: 2026-03-11

3月 12, 2026
Z-Image Team
Fish Audio S2-Pro:用自然语言控制语音情感的 TTS 模型

Fish Audio S2-Pro:用自然语言控制语音情感的 TTS 模型

Fish Audio S2-Pro:开源 TTS 新模型

3月 11, 2026
Z-Image Team
Fish Audio S2-Pro: A TTS Model with Emotion in Speech Controlled with Natural Language

Fish Audio S2-Pro: A TTS Model with Emotion in Speech Controlled with Natural Language

Fish Audio S2-Pro: Open Source TTS Model

3月 11, 2026
Z-Image Team
Use OpenClaw to Tweet from VPS Without Getting Banned: Headed Browser + Xvfb Solution

Use OpenClaw to Tweet from VPS Without Getting Banned: Headed Browser + Xvfb Solution

You have a VPS (Virtual Private Server) and want to automate Twitter posting. But here's the problem: - ❌ Twitter API requires approval and has many r

3月 10, 2026
Z-Image Team
使用Openclaw在服务器发推特不被封?用有头浏览器 + 虚拟显示完美绕过反爬检测

使用Openclaw在服务器发推特不被封?用有头浏览器 + 虚拟显示完美绕过反爬检测

你有一台 VPS 服务器,想实现 Twitter 自动发推。 但问题来了: - ❌ Twitter API 需要审核,限制多

3月 10, 2026
Z-Image Team
FireRed-Image-Edit 1.1 Tops Open-Source Rankings with 7.94 Score, Surpassing Alibaba's Qwen

FireRed-Image-Edit 1.1 Tops Open-Source Rankings with 7.94 Score, Surpassing Alibaba's Qwen

> The open-source image editing landscape has a new SOTA champion. **TL;DR**: Xiaohongshu (RED) released FireRed-Image-Edit-1.1 on March 3rd, achievin

3月 10, 2026
Z-Image Team
小红书 FireRed-Image-Edit-1.1 刚开源就登顶!7.94 分干翻阿里 Qwen-Image-Edit-2511

小红书 FireRed-Image-Edit-1.1 刚开源就登顶!7.94 分干翻阿里 Qwen-Image-Edit-2511

> 开源图像编辑领域,SOTA 易主了。 **TL;DR**:小红书 3 月 3 日刚发布 FireRed-Image-Edit-1.1,在 5 个权威 Benchmark 上全面超越阿里 12 月发布的 Qwen-Image-Edit-2511,以 7.943 分刷新开源图像编辑模型纪录。身份一致

3月 10, 2026
Z-Image Team
阿里开源 Qwen3.5-9B:9B 参数干翻 120B,小模型的 SOTA 时刻

阿里开源 Qwen3.5-9B:9B 参数干翻 120B,小模型的 SOTA 时刻

2026 年 3 月 2 日,阿里开源了 Qwen3.5 小尺寸模型系列。9B 版本在 GPQA Diamond 拿到 81.7 分。超过 OpenAI 的 GPT-OSS-120B(71.5 分)。13.5 倍参数差距,小模型赢了。 Apache 2.0 协议,代码和权重都能商用。一行 Ollam

3月 10, 2026
Z-Image Team
Claude Code 新功能:/loop 让 AI 自动帮你"值班"

Claude Code 新功能:/loop 让 AI 自动帮你"值班"

Claude Code 内置了 /loop 命令,会话内的定时任务调度器。 能干什么: - 自动重复执行提示词

3月 9, 2026
Z-Image Team
Claude Code + SEOMachine: The Right Way to Write SEO Articles with AI

Claude Code + SEOMachine: The Right Way to Write SEO Articles with AI

> 343 stars, 24+ marketing skills, fully automated from research to publishing. Ever faced these problems when using AI to write SEO articles? Article

3月 8, 2026
Z-Image Team
Claude Code + SEOMachine:AI 写 SEO 文章的正确姿势

Claude Code + SEOMachine:AI 写 SEO 文章的正确姿势

> 343 stars,24+ 个营销技能,从研究到发布全自动化。 用 AI 写 SEO 文章,你遇到过这些问题吗? 写出来的文章太"AI 味",一眼就被看穿。关键词密度把握不准,要么堆砌要么太少。不知道竞品写了什么,内容同质化严重。写完还要手动优化 meta、内链、可读性。

3月 8, 2026
Z-Image Team
AI Agents Can Finally Fetch Tweets Without Login! This OpenClaw Skill Makes It Zero-Config

AI Agents Can Finally Fetch Tweets Without Login! This OpenClaw Skill Makes It Zero-Config

> 343 stars, updated 2 days ago, supports Twitter + WeChat + Chinese platforms, completely free. How would you make an AI Agent read tweets? Apply for

3月 8, 2026
Z-Image Team
AI Agent 抓推特终于不用登录了!这个 OpenClaw 技能零配置搞定

AI Agent 抓推特终于不用登录了!这个 OpenClaw 技能零配置搞定

> 343 stars,2天前刚更新,支持推特+微信+中文平台,完全免费。 AI Agent 想读推特,你会怎么做? 申请 Twitter API?每月 $100+。用爬虫?分分钟被封。手动复制粘贴?那还要 AI 干嘛。

3月 8, 2026
Z-Image Team
Claude Code Essential Plugin: See What Your AI is Actually Doing

Claude Code Essential Plugin: See What Your AI is Actually Doing

> Context window filling up? What files is Claude reading? How long has that sub-agent been running? Now you can see it all. What's the most frustrati

3月 8, 2026
Z-Image Team
Claude Code 必装插件:让你看清 AI 在干什么

Claude Code 必装插件:让你看清 AI 在干什么

> 上下文快满了?Claude 在读什么文件?子 Agent 跑了多久?现在你能看到了。 用 Claude Code 写代码,最烦的是什么? **你不知道它在干什么。**

3月 8, 2026
Z-Image Team
今天刚更新!这个 5.6k Star 的开源工具让 AI Agent 能读公众号文章了

今天刚更新!这个 5.6k Star 的开源工具让 AI Agent 能读公众号文章了

Agent-Reach v1.3.0 今天发布,支持微信公众号文章搜索和全文读取,配合 OpenClaw 实现全网信息收集自动化。完全免费开源。

3月 7, 2026
Z-Image Team

Qwen3.5-9B:90 亿参数开源大模型完整指南(2026)

Qwen3.5-9B 完整指南,阿里云强大的 90 亿参数开源大语言模型。了解规格、硬件要求、部署方法和性能基准测试。

3月 3, 2026
Z-Image Team