All things migrate, universal sticker，Support nunchaku
Workflows:https://www.runninghub.ai/post/1955386628840701953?inviteCode=rh-v1172 Register for free use
https://civarchive.com/models/1793451?modelVersionId=2029628
If you find it quite good or have any questions, please send me more pictures to help me grow. Thank you for your participation. Please try to give me the kind with a white background sticker
Modification: Version V.1, hand distortion issue, automatic light tracking, automatic background fusion (see auxiliary prompt words)，Transparency of transparent and semi-transparent items
New features: Tattoo: (This pattern is tattooed on the arm), Print: (This pattern is printed on clothes), Furniture: (This sofa is placed in the corner), Face swap: (This woman is looking at the audience), Dress change: (The woman is wearing this dress), Jewelry: (This necklace is worn around the neck), Item: (This bottle of perfume is placed on the table), Shoe change: (Both feet are wearing this shoe), Remove, Expand image: (Fill in the blank area)，The character in the sticker is obedient: (This cat stretches out its hands to make a heart gesture and opens its mouth to smile)
The texture must be a white background image. Just place it where you want
Trigger word: Put it here Add auxiliary prompt words：Adaptive, automatic light adaptation, 4K, high definition, outstanding picture quality
Note: The best effect is achieved with a white background and white borders all around!
Workflows:https://www.runninghub.ai/post/1955386628840701953?inviteCode=rh-v1172 Register for free use
https://civarchive.com/models/1793451?modelVersionId=2029628
We recommend a matting plugin to help your images fit better and maintain consistency
https://github.com/XiaoHeiziGGG/put-tools/tree/main?tab=readme-ov-file
https://github.com/zml-w/ComfyUI-ZML-Image
If you need commercial customization or have any suggestions or assistance, please contact me
Description
Everything migrates, Universal Sticker, supports nunchucks
Workflow address:https://www.runninghub.ai/post/1955386628840701953?inviteCode=rh-v1172 Register for free operation
Modification: Version V.4, no longer limited to white background images, supports borderless images and various color background images, automatic high definition, hand distortion issues, automatic ray tracing, automatic background blending (see auxiliary prompt words), improved transparency and translucency of transparent and semi-transparent objects,
New features: See below for details
The border is a white background image. Just place it where you want.
Trigger word: PUT IT HERE
Add auxiliary prompt words: adaptive, auto-light adaptation, 4K, high definition, excellent image quality
Note: The best results are achieved with a white background and all surrounding white borders!
Workflow address:https://www.runninghub.ai/post/1955386628840701953?inviteCode=rh-v1172 Register for free operation
If you need commercial customization or have any suggestions or need help, please contact me
V:budabiaoa Q:123326400 mail:[email protected]
FAQ
Comments (50)
So nice, its the best lora in here!!!
Great promotion, thanks bro haha
Futurlunatic lol
Futurlunatic Will there be a V5 release in the near future?
Decide based on the situation, and we also need your help to contribute more images for the next version
那我可以说中文吗
wallen0322！弄！弄！弄！
It doesn't work properly, it doesn't tolerate faces, I did it according to the instructions, but the result is terrible, what are you doing to make the results look like I see on this page
So you just cover it as described in the introduction. Keep what you want and discard what you don't want. If there are white borders, it will have a better effect.
Spent an hour installing numskulls 27 different ways. Finally! But wait, they were not even used ;)
Haha, this is a problem with the nunchucks... If it really can't be helped, you could consider not using it.
超好玩，推荐给你！
工作流：kontext（万能贴）Put it here_V4
体验地址：https://www.runninghub.ai/post/1955386628840701953/?inviteCode=rh-v1172
You can try it here. Register for free points
This lora and the workflow look hugely useful. I have the single image path working great. could someone kindly post the English translation of the FastCanvas buttons? So far I am just guessing. I think that node will change my life once I master it.
I can only carry objects and animals, but as for the human head, there is no similarity from the word smovsem,
soyv4 so true
Thank you for your support. If it cannot be used correctly, you can consider replacing it with another node?
Futurlunatic I do not know of another node with the same functionality. It works by trial and error but it would be more useful if only I knew the meaning of the labels on the buttons. 我不知道还有另一个节点具有相同的功能。它通过反复试验来工作，但如果我知道按钮上标签的含义，它会更有用
Optimum I don't really understand... Don't you have screenshot software or mobile translation apps that can translate by taking photos? You'll remember what it's for after one use. It's very simple.
你好，出现多手指情况，如何解决呢？
你的遮罩有问题你仔细看一下。多余不想要的东西要遮住
Futurlunatic 感谢回复，目前出现了穿模的情况，请问如何缓解或者解决呢？https://ibb.co/7xfH8p3r
1, Regenerate, 2, PS crop
Futurlunatic 我尝试了regenerate，试了多次都还是穿模。请问下2，PS crop怎么操作呢？
allengexx Pulling out some of the fingers you want to leak will give different effects. It's a bit more complex, but the results are definitely good.
请问在 Load VAE 旁边的 ‘remove clothes’ 提示词无法修改，这是正常的吗？
？没啥不能修改的地方。。你可以看下
超好玩，推荐给你！
工作流：kontext（万能贴）Put it here_V4
体验地址：https://www.runninghub.ai/post/1955386628840701953/?inviteCode=rh-v1172
参考这个工作流
does it work with nunchaku?
Of course, supported
is it possible to add transparency to the mask when applying it to the main object? The size can be reduced, which is good, but sometimes you just can't see what's under it and therefore you can't apply it as accurately as possible.
Ever thought about this issue? 1. It's easy to cause AI misjudgment and unable to accurately confirm your purpose. 2. It cannot fully display the details and materials of the replaced object, after all, semi-transparent items are more difficult to confirm some details. 3. There are no such plugins available to support this feature for now.
@Futurlunatic Maybe that's not how I put it. Transparency is needed only in order to see what is there... relatively speaking, what is under the picture of the shirt that I just cut out. I have a picture of a shirt, and now I need to carefully put this shirt on the human figure. And it would be nice if at this moment I could adjust the transparency of the shirt to see the figure of a person under it, do you understand?
This transparency should not be involved in generating the final result. It's just a tool for convenience and precision.
@VecToPaz Oh oh I understand what you mean. That's something for the plugin to handle. If my LoRA continues to be liked by everyone, I'll have the plugin author do this. Thanks for your suggestion. Thank you very much.
@Futurlunatic Thank you and the author of the plugin.
@VecToPaz Just have fun everyone
Great lora, thanks for your work! What values and where should I use so the image quality doesn’t get worse? I tried to set 2.50megapixels
You can try adding a prompt, 4K, high-definition quality. kontext's output resolution should be below 2K. If that doesn't work, you can upscale it.
Great LoRA! Just to note that using Nunchaku degrades quality vs. using the FP8 Scaled.
Yes. But it's still usable for casual grinding haha
@Futurlunatic Absolutely!
can you give me your workflow?
The wf needs TTP_Expand_And_Mask node, it is from TTP_Toolset custom node, but even after installing it, it is still missing. TTP is well installed, there are other nodes of it. How to fix that ? Thanks
If you really can't install it and delete it, it's OK to make stickers with PS
大佬，流程里面的text是什么节点？我缺失了，TTP那些倒是自己搞定了。。。
TEXT就是个文本输入框而已删了就行
Details
Files
Available On (3 platforms)
Same model published on other platforms. May have additional downloads or version variants.