注意：我的模型经过 locon 训练，所以需要安装LoCon 支持。https://github.com/KohakuBlueleaf/a1111-sd-webui-locon
PS：有好点子可以留言，如果你下载了Lora，希望能留言告诉我您的使用感觉和困惑，好让我能够学习。（求5星好评，让更多人能够用到。）
PS: Leave a comment if you have any good ideas. If you have downloaded Lora, I hope you can leave a comment telling me how you feel about using it and how confused you are so that I can learn.
我的Ko-fi网址，里面有一些我做的图片，欢迎来看看。
My Ko-fi site, which has some pictures that I made, feel free to come and have a look.
【Note: 支持性捐助仅适用于经济独立的人群，任何人都可以下载图片但没有那么高清。Supportive donations are only available to those who are financially independent. All can download the images but not in as much high resolution.】
【PS：感谢每一个帮我买可乐的朋友，投喂1欧元=7元钱，可以一个月内下载所有我做的2K+的高清图片。PS: Thanks to everyone who helped me buy a coke by throwing in 1 euro = 7 dollars to download all the 2K+ HD images I made for a month.】
我的图例，均由下列tags生成/my pictures are all from prompts below.
正向词：Prompts
{best quality}, long(v1.0)/LONG(v2.0), chinese ink painting, super huge dragon, solo, <lora:泼墨中国龙-molong:0.9>, <lora:Moxin_Shukezouma:0.75>, <lora:shuimobysim-Moxin_1010:0.3>, very detail, mountain, clouds and mist, greyscale,
负向词：Negative Prompts
NSFW, bad anatomy,bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worstquality, low quality, normal quality,jpegartifacts,signature, watermark, username,blurry,bad feet, blue eyeball, stamps,（自己调试/Debug by yourself）
Euler a 采样方式=Euler a
Steps=30 采样次数=30
CFG scale=7 相关性=7
Model= Anything4.5/Stable Diffusion v1.5
Description
只能说真的不好弄，这一版算是有了点雏形了。
毕竟现有的模型无一幸免，只要输入dragon就必然会受到影响。
一定要写上提示词里的那三个词，当然如果想创新，当我没说。
It can only be said that it is really difficult to handle, and this version has a little prototype.
After all, none of the existing models are spared, as long as the dragon is input, it will inevitably be affected.
Be sure to write the three words in the prompt. Of course, if you want to innovate, pretend that I didn't say it.
FAQ
Comments (29)
总算有像样的龙了。
请你喝可乐。
谢谢
大佬 这个lora使用的是哪个主模型？
可能是暴鲤龙
@enjuster173 暴鲤龙是哪个啊好哥哥 我没搜到
@1448042976367 用realistic或者Anything4.5都可以。也可以自己融合几个模型用。C站上就根据你的需求，2D/2.5D/3D的模型你随便找个下载量高的就可以。
@1448042976367 暴鲤龙不是模型是神奇宝贝
@Aseer好的 谢谢大佬
@enjuster173 好吧哈哈哈哈哈
老哥 稳！
Can you share the generation data for your sample images? I'm having a lot of difficulty with getting good results. 😢 Which model did you use for the gold dragon? Thanks so much!
I would add the data in the image. and the model you should ues is the high rank of Civitai list. those models are fine.
大佬，为啥我装了那个locon支持后没有可以选择的地方，具体使用方式有教程吗？直接调用lora好像没有效果
https://github.com/KohakuBlueleaf/LyCORIS 这个网址阅读教程。另外locon之类的插件属于代码层的，只要安装上了就行，没有调用一说。如果你不安装，控制台会提示你无法使用我的这个模组，然后直接跳过，相当于没用。安装了之后，就会和用其他lora模组一样，什么都不会发生，正常使用而已。
@Aseer 我都安装了，使用lora它没报错也没起作用。我控制变量试过了，lora一点用没有器起...
@Aseer 好了，我确认了，是我的locon没有起作用，我研究一下怎么弄
@Aseer 感谢，自己去github搜了一个locon插件就能用了，不知道为什么用您链接里的那个插件无效
@xingjian 可能是我的链接里那个过期了。毕竟是一个月前locon刚出的时候放上去的链接。
with or without lora i get almost the exact same result, on same seed, same prompt (with triggers) .. 🤷
Try some other one. No matter good or bad result. There must have some different in the same prompt tags. If not check carefully cause there must some problems happened. Plugin. Reference method or some other things.
@Aseer u r correct, console spits out an error:
D:\py2-0 no xformers 14_05\stable-diffusion-webui\models\Lora\chinese_dragon_祥龙20230414版.safetensors: AssertionError
Traceback (most recent call last):
File "D:\py2-0 no xformers 14_05\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 253, in load_loras
lora = load_lora(name, lora_on_disk)
File "D:\py2-0 no xformers 14_05\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 220, in load_lora
raise AssertionError(f"Bad Lora layer name: {key_diffusers} - must end in lora_up.weight, lora_down.weight or alpha")
AssertionError: Bad Lora layer name: lora_te_text_model_encoder_layers_0_mlp_fc1.hada_w1_a - must end in lora_up.weight, lora_down.weight or alpha
this error only occurs with your lora so far
@Blurmatico change the NAME please. Apparently, lora's filename is confusing your computer.
@Aseer same error: loading Lora D:\py2-0 no xformers 14_05\stable-diffusion-webui\models\Lora\chinese_dragon.safetensors: AssertionError/s]
Traceback (most recent call last):
File "D:\py2-0 no xformers 14_05\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 253, in load_loras
lora = load_lora(name, lora_on_disk)
File "D:\py2-0 no xformers 14_05\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 220, in load_lora
raise AssertionError(f"Bad Lora layer name: {key_diffusers} - must end in lora_up.weight, lora_down.weight or alpha")
AssertionError: Bad Lora layer name: lora_te_text_model_encoder_layers_0_mlp_fc1.hada_w1_a - must end in lora_up.weight, lora_down.weight or alpha
@Blurmatico Landing on Civitai's Discord. Then send your debug to the help channel. There is a problem with your SD settings, it should not be just me, you can't use lora.
@Aseer i tried different loras, all work and none throws any errors, no idea why dragon lora is not working
@Blurmatico did you installed Lycoris/locon?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.