大家好，我是B站UP主：言萧的AI画室，
主页链接：言萧的AI画室的个人空间_哔哩哔哩_bilibili
Youtube: https://www.youtube.com/channel/UCRXIcSgbbvPAYXKVnFEp2HQ
此模型是老王炼制，B站UP：大咦把狼
本人仅为代发布模型，以下内容由老王编写：
实验性质的大模型，不挂LORA直接跑，对提示词还比较敏感，主要是针对建筑，室内这些乱七八糟的。
底模是基于CHILLOUT弄的，其实效果挺一般的，主要是线不直，只能看看大感觉，你们拿着自己玩玩。
我把我练的几个LORA ，都给灌进去了。
所以，你们要是用这个大模型，要挂我的LORA 的话，直接全部降权重，否则直接跑出古神图。
I found a new AI tool Shakker, a best image to image tool. You can try it via https://www.shakker.ai ,it can help you:
-Remix: Upload a picture. Just switch the prompts, and you can create stunning images in the same style.
-Style Transfer: Shakker not only extracts the style,but also switches among various styles.
Besides, Shakker also offers Object Control,Composition Control,Collage Redrawing etc.
Description
FAQ
Comments (9)
Can you do a safetensor please?
sry, ingnore that before, safetensor now~
Safetensor, please
sry, ingnore that before, safetensor now~
Something wrong? special settings? I tried the safetensor but the output images looks washed out with or without VAE. Can't replicate similar image like the demo... They're still good architecture images but does not look like the one you posted. Have to add another lora to darkened them a bit.
i have seen those images you post, can't tell what's the problem, those images are totally render with text to image without Lora, if you download those demo iamges, you can use image info to see all the data, and that is all i use, btw, i use 840000 vae
and try v0.2, i fixed something
@YanXiao_AI Maybe the cause is I was using a fork of Auto1111 called Vlad's diffusion (SD.Next) first time I tried your model. When I tried your models the other day in Auto1111, it indeed looks more like your demo. Haven't tried to grab your demo and put into UI to see metadata... because Civitai didn't display metadata so I assume you enter them manually. And a question, why did you removed the model or all my posted images? This page is empty now.
Usually when you upload newer version, keep old version at another tab... I saw other authors do that here. You removed the old version? Anyway nice works. Thanks for sharing
@nnq2603 yes, i removed the early version because i found i do miss something during the transfer from ckpt into safetensor model , so it occurs some mistakes, i didn't remove your pictures, maybe it's linked to the model page~, anyway , the new version produces much better results, and thank you very much for those pictures you posted~
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.