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。
RH 体验地址：https://www.runninghub.ai/post/2057506560754143234/?inviteCode=cptpovgo
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。
2026-05-20
Hey lads & gents 🍻
V7.0 just dropped 🚀
✨ Minor optimizations for the newer Moody Releases models
🛠️ Added automatic detailer module
🎭 Added manual masked detailer module
🌊 Re-organized the workflow layout to feel more like a waterfall flow
⚡ Plus a bunch of QoL improvements inspired by my latest workflows
Enjoy & cheers ❤️
🇨🇳
兄弟们来了 🍻
V7.0 现已发布 🚀
✨ 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，让整体流程更像瀑布式结构
⚡ 同时加入了不少我最新工作流里的 QoL 改进
玩得开心，干杯 ❤️
2026-03-31
V6.0 ZIT Simple Dual Ksampler Enhanced WITH SDA workflow.
DEMO images were generated by moody porn v10 model.
预览图生成于 moody porn v10 model.
With the help of SDA, the new workflow works almost as well as my ZIB+ZIT workflow just with minor drawbacks of bad poses and body anatomy. This is still a very good solution for the “Diversity Collapse” problem.
Z-Image-Turbo-SDA is a highly efficient LoKr (Low-Rank Kronecker Product) adapter designed to rescue the “Diversity Collapse” problem in few-step distilled Flow Matching / Diffusion models. However, it also increases the chance of bad body anatomy.
SDA Lora support added in 1ST sampler
New upscaler used for further attempt to eliminate the side effect of SD upscale
QoL updates as my other newer workflows
在 SDA 的帮助下，这个新的工作流表现几乎和我的 ZIB + ZIT 工作流一样好，只是存在一些小缺点，比如姿势不自然和人体结构不准确。不过，这仍然是解决“多样性崩塌（Diversity Collapse）”问题的一个非常有效的方案。
用于解决少步数蒸馏 Flow Matching / Diffusion 模型中的“多样性崩塌”问题的高效 LoKr 适配器，但也会在一定程度上增加人体结构异常的概率。
增加了对SDA LORA 的支持
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）
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
2026-03-20
V5.0 ZIT Dual Ksampler Enhanced Simple workflow
V5.0 is here. Some optimization and QoL update for the Moody ZIT and ZID models better support. Added an attempt to fix some anomolies from SD upscale node.
V5.0 版本已发布。针对最新的moody模型 进行了一些优化和体验改进。尝试修复SD upscale奇怪纹路的问题。
2026-02-25
Dual K-Sampler setup with minor quality of life updates with support of my ZIT/ZID (Zimage distilled) models.
Availble 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
2026-01-20
Add separate seeds for each Ksampler so you don't have to re-run the whole flow from beginning if you just want minor changes
Use a different upscalers for better performance and quality
Included the facedetailer flow by default
Added optional SeedVR for upscaling to 4k
Added optional skin contrast filter
2026-01-13
Updated with 2 Ksamplers for better preview and optimization.
2026-01-01
Added a face detailer workflow as requested. Since some users have noted that character LoRAs are not fully compatible, my recommended workaround is to first describe the character using a text prompt, then apply the face detailer with your character LoRA to effectively perform a “face swap.”
--
As requested, here is a simplified, minimal workflow derived from my setup for the most basic Z-image AIGC tasks.
Description
FAQ
Comments (13)
It doesn't looks like 'flow like a water' to me. I mean, IMHO, a good workflow flows in one direction. There are quite a few nodes that is on the right hand side but have its output connected to some nodes on the left hand side, causing a line to ran through a long distant, which is not good.
I think workflow should go in one direction, left-to-right. More complex workflow can make use of subgraph. Each node should have adequte space between them so it's easier to understand what's going on (and node size on different machine can be vary). Also I think 'reroute' node is a good tool to archive a good looking workflow. Like for example there are quite a few nodes that relies on the CLiP encode node (especially the clip output). You can make uses of reroute node to create a bus so the lines won't be too messy.
A good workflow will looks like a good looking wiring, except that it only go one way. There shouldn't be too many of overlapping lines and or nodes.
can probably use get set node to clean up the lines. But that might introduce more dependencies for newbies. But I hear ya, next release I’ll focus on cleaning up the messiness
It seems like there are some references to ZIB, particularly Preview Image 1st. I thought this workflow used one model, as opposed to ZIB + ZIT workflow. Probably just a typo, but it confused me at first so i thought I'd point it out
thanks for spotting it, i just fixed the typo
I don't even bother testing workflows when the description page says nothing about hardware. Like I wanna spend an hour setting it up to get an OOM.
Fair enough. I don't list hardware requirements because they depend on resolution, VRAM optimization settings, and whatever modifications users decide to make after loading the workflow. I have had fella running this with a 3060 + 16gb ram setup.
What's interesting is that you're worried about wasting an hour setting up a workflow, but apparently not worried enough to spend 30 seconds reading the workflow notes, where alternative upscalers are already mentioned.
And since the workflow is provided for free, I'm not entirely sure where the expectation comes from that it should be tailored to every possible hardware configuration in advance.
If spending an hour setting up a workflow before checking your available VRAM sounds like a bad use of time, you can also spend 10 seconds asking. 🧂🧂
batch resizing? Do you mean generating multiple images at once?
@catlover1937 Yes, is it possible to create multiple images simultaneously
@cawaokaito try out my minimal workflow, that one might work, but you can also increase the batch count instead of batch size, that allows u genreate multiple images while u are away, (might be bit slower )
May I ask which workflow you use to produce the videos on your page?
I use Wan 2.2, LTX and sometimes GROK. If you are talking about this specific video on this simple workflow v7 SDA, i use the workflow from wan2.2 remix made by feihou.
非常感谢你制作如此实用的工作流,效果偏佳,难度适中,整体不乱不复杂.