I just made a new Telegram Group and Discord group drop in for chats, questions, feedbacks or just to share your work. 欢迎加入纸飞机和Discord群组。
喜欢我的作品吗？🎨 我会持续免费分享更多优质内容✨，欢迎支持一下，请我喝杯咖啡吧！💖 Like my work? 🎨 I share all my work for free ✨, so support me by buying me a coffee 💖!
Ko-fi: ko-fi.com/catlover1937
Please do not redistribute without consent. 如非作者同意禁止搬运。
RH体验地址：https://www.runninghub.ai/post/2059781120304173057/?inviteCode=cptpovgo
2025-05-27
🚀 Hello great people!
Image-to-Image Workflow V3.0 is finally here 🎉
Before we dive into the updates, I wanna quickly explain what this workflow is actually made for 👀
This workflow is for lazy people like me 😎
You find a cute / beautiful image on Instagram, Xiaohongshu, Pinterest, or wherever you browse... (not judging if you're scrolling some XXX sites at work 💀) and want to recreate the same vibe with your own AI girl.
That’s exactly what this workflow is built for ✨
Just slot in your favorite character LoRA, hit generate, and boom — hands-free & prompt-free generation 🔥
💖 A list of Moody Gals (character LoRAs) can be found through the collection link (more are coming).
━━━ V3.0 Updates ━━━
⚙️ Adjusted some preset stats
✨ Minor optimizations for newer Moody Releases models
🛠️ Added automatic detailer module
🎭 Added manual masked detailer module
🌊 Re-organized the workflow layout into a cleaner waterfall-style flow
⚡ Added more QoL improvements inspired by my latest workflows
Enjoy & cheers 🍻
🚀 大家好！
Image-to-Image 工作流 V3.0 终于来了 🎉
在介绍更新内容之前，我想先重新说明一下这个工作流到底是干嘛用的 👀
这个工作流是专门为像我这种懒人准备的 😎
当你在 Instagram、小红书、Pinterest，或者其他你平时逛的网站上（上班偷偷刷 XXX 网站我也不评价 💀）看到一张很好看的图，想用自己的 AI 女友 / AI 角色重新生成同样风格的时候——
这个工作流就是为此而生的 ✨
你只需要放入自己喜欢的角色 LoRA，然后点击生成，剩下全部自动完成 🔥
无需写 Prompt，真正的 hands-free & prompt-free 体验。
💖 Moody Gals（角色 LoRA）合集可以通过这里 collection link 找到，届时会有更多的人物Lora更新哦。
━━━ V3.0 更新内容 ━━━
⚙️ 调整了一些预设参数
✨ 针对新版 Moody Releases 模型进行了小幅优化
🛠️ 新增自动细节修复模块
🎭 新增手动蒙版细节修复模块
🌊 重新整理了工作流布局，让整体结构更加瀑布流化、更直观
⚡ 加入了更多来自我最新工作流的 QoL 改进
祝大家玩得开心，干杯 🍻
2025-03-27
Whats new in V2?
New upscaler used for further attempt to eliminate the side effect of SD upscale
Add pre-processor section to adjust image contrast and brightness, which will carry forward to the end result
Improve on auto prompt detections
QoL updates as my other newer workflows
V2 有什么新内容？
使用了新的放大器（SD upscaler），进一步尝试消除 SD 放大带来的副作用 （莫名的水渍，鸡皮疙瘩，油光）
新增预处理（pre-processor）模块，可调整图像的对比度和亮度，并会影响最终输出结果
优化了自动提示词检测功能
加入了一些使用体验上的优化（QoL），整体流程更加顺手，并与我其他较新的工作流保持一致
2025-03-05
Tired of unreliable ControlNet options for Zimage or just tired of coming up with prompts?
This workflow lets you re-generate your input image while preserving the original settings, pose, and likeness—without carrying over any real identity issues. It is compatible with all of my ZIT and ZID models. (Moody Porn V10 was used during testing and is recommended.) Prompts will be generated on the fly using Florence2. You can just input an image and it re-generates the image in hands-free (brains-free too) mode.
厌倦了为 Zimage 寻找好用的 ControlNet 或者有洗图的烦恼吗？
这个工作流可以重新生成你的输入图像，同时保留原始的结构、姿势和整体相似度，并且不会带来任何真实身份相关的问题。它兼容我所有的 ZIT 和 ZID 模型。（测试时使用的是 Moody Porn V10。）提示词会在工作流中通过Florence2 自动生成，做到全自动用脚都能喂图自我生成。
Avaible ZIT Models / 可选 Turbo 模型：
https://civarchive.com/models/620406/moody-porn-mix
https://civarchive.com/models/621441/moody-real-mix
https://civarchive.com/models/2384856/moody-wild-mix?modelVersionId=2681752
Description
FAQ
Comments (15)
好玩，好用
how much vram do you need at least?
8 should be sufficient, you need 32 g of ram to be safe tough
sorry i'm a noob, but what can i do with this workflow? it outputs the same image from the input, and doesn't change anything, and there is no text input necessary, what do you use it for? i thought by i2i it meant like image editing with some text prompt for editing instructions while keeping identity etc
You are thinking about image edit, instructed image editing. This is just to generate an AI version of the orignal image.
@catlover1937 thanks, is it mainly for applying lora to change identity to fit the lora while keeping pose and setting? what people use it for? because upscaling/detailing you just can do it straight from base image
@sickdude9630 Yeah applying character Lora is one of the perfect use case for this. Or you can just use the power of prompts as well.
Another use case I can think of is one is lazy of writing prompt but want to generate a similar image they see online.
Anyway, I am sure people will have many creative ways of using this workflow.
一直报这个：
DownloadAndLoadFlorence2Model
An error happened while trying to locate the files on the Hub and we cannot find the appropriate snapshot folder for the specified revision on the local disk. Please check your internet connection and try again.
大哥这怎么解决？
Can't I modify the automatically generated prompt?
I know the concept of creating the same image, but wouldn't it be better if I could modify the generated prompt to make the best use of it?
1. You can detach prompts generator and run them separately If you have the need
2. This is image to image unlike qwen edit or flux Klein edit, the model is not going to follow exactly what you prompt unless you start a t2i
You are likely thinking of the edit models but Zimage is not. Does it make sense?
You can detach the prompt generator and run it separately if needed.
This workflow uses image-to-image, unlike edit models such as Qwen Edit or Flux2 Klein Edit. The model will not follow your prompt exactly unless you start from a text-to-image (t2i) generation.
You might be thinking of edit models, but Zimage is not one of them. The release date for Zimage Edit is still uncertain, as the Chinese government recently decided to treat AI models as a strategic resource, during the recent CCP congress plenary sessions.
Does that make sense?
An excellent workflow with enormous potential!