模型介紹為中英雙語，中文使用者可以關閉翻譯。
--
PornMaster_SDXL_Illustrious_noob_Pony_t2i_工作流下載(Workflow Download)
PornMaster Simple 4X Magnification Workflow
--
--
Stable Diffusion WebUI Forge - Neo
--
Creating Photorealistic Images With AI: Using Stable Diffusion
SDXL 1.0 藝術研究。(SDXL 1.0 Artistic Studies)
--
v7之前的版本为sd1.5 "Amateur系列"检查站。
Versions prior to v7 were the sd1.5 "Amateur Series" checkpoints.
--
My other checkpoints and Lora.
--
我已將模型上傳至runninghub。
I have uploaded the model to runninghub.
PornMaster-Pro-SDXL-V7-VAE
https://www.runninghub.ai/model/public/1981749531459108865/?inviteCode=rh-v1304
PornMaster-Pro-SDXL-V7-VAE-inpainting
https://www.runninghub.ai/model/public/1981757608040243202/?inviteCode=rh-v1304
PornMaster-Pro-SDXL-V8-VAE
https://www.runninghub.ai/model/public/2008921333920436225/?inviteCode=rh-v1304
PornMaster-Pro-SDXL-V8-inpainting
https://www.runninghub.ai/model/public/2043676887620259841/?inviteCode=rh-v1304
--
AUTOMATIC1111:
Check "Clip skip SDXL" in the settings to enable the Clip function.
勾选设定中的"Clip skip SDXL"，可使Clip功能生效。
ENSD:31337
Eta 噪點種子偏移（ENSD）
(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)
--
如果你的WEBUI无法显示某些版本的LORA:请到"设定"，然后勾选"Always show all networks on the Lora page(otherwise, those detected as for incompatible version of Stable Diffusion will be hidden)"
--
不要問我如何安裝的問題與comfyui如何使用。
客製化lora:我的Telegram ID:@iamddtla0620
我的微信ID:iamddtla
我的line ID:iamddtla
時間寶貴，請直接說明來意，例如:訂製lora.
Do not ask me questions about how to install it or how to use ComfyUI.
Customized lora: My Telegram ID: @iamddtla0620
My WeChat ID: iamddtla
My Line ID: iamddtla
Time is precious, please state your intention directly, for example: customized LORA.
--
面部局部重绘可使用adetailer.
高解析度放大可使用"ultimate SD upscale".
For partial facial redrawing,use adetailer.
High resolution upscaling can be done using "ultimate SD upscale".
--
Adhere to the Fair AI Public License, ensuring that any derivative works are also open source.
遵守Fair AI Public License，確保任何衍生作品也是開源的。
Description
FAQ
Comments (33)
Great model - but why is it over 10GB?
Because the full version is a complete version without pruning, the other versions have smaller capacity because they have been pruned.The model most people publish is usually a trimmed version.
@iamddtla Thanks. I'm not training Loras - so which version should I download? Is there any difference in quality between the v6 full and the v6 32fp version?
I don't mind the size - I have more than enough storage - just curious :)
@tcpstackmaster971 They cannot generate the same pictures, please download and play by yourself.
@tcpstackmaster971 You can just use the FP16 version, unless you want to train with that model or merge it. If you only use it to generate images, it doesn't matter, see my "Cheatsheet" posts:
https://civitai.com/images/2893083
https://civitai.com/images/2887273
https://civitai.com/images/2897987
I find the FP32 Model great to train realistic, working Loras - thx for this one, thumbs up!
Yes, and can be trained well naked, breasts, pussy.If you want, you are also welcome to show your lora's work.
想问下PornMaster-Amateur和PornMaster Pro 的区别是？
首先站内绝大多数亚洲女明星lora都是基于chill训练的，但是基于非chill训练的欧美人物lora在使用chill出图的时候都会变形幼态，反过来用基于chill训练的亚洲女明星使用非chill出图的时候，也会变形白人脸。如同壁垒分明的敌对阵营、安卓和苹果一般，不能兼容。所以PMA，PM，PM-Pro，PM素人，这四大版本，哪一个适合chill系亚洲女明星lora？哪一个能兼容两大阵营lora?哪一个适配斯嘉丽龙妈歪嘴玫瑰等非chill西方lora？不能用人物Lora的话，恕我直言，情色魅力至少打5折以上。C站老色批们最大的乐趣无非弄杨幂和斯嘉丽了，东西方两大阵营。
如果要用不是在這個模型製作或是原始的SD1.5製作的亞洲人物，請使用"PRO-V4版本"。
@iamddtla 所以proV4版本是适配chill系lora，舍此以外的其他所有版本适配非chill白人lora么，看来没有一个底模能兼容安卓（chill麦橘）和苹果（非chill）啊。
@7016jayAlex 最好的效果是在哪個模型上訓練lora，就在那個模型上使用那個lora，大多數能兼容的是因為合併了很大比例的chill模型。
但是那個模型的裸體效果並不夠好。
而且大多數人都因為網路教學影片被灌輸了訓練亞洲人物要使用"chilloutmix"模型的觀念。
@7016jayAlex 我的模型並不是為了使用chilloutmix製作的lora而設計的，而是為了良好的裸體和廣泛的年齡、不同的面孔、人種設計的。
@iamddtla 这是先发优势和用户习惯，就如同安卓一样，也有不比安卓差的系统，但一旦养成了习惯，就非常难掉头，掉头成本很高，你很难抛弃原有的生态。
@iamddtla 我其实很不喜欢chill,但为了亚洲明星lora，不得不用chill。从某种角度来说，底模就是服务于明星名人lora的。最理想的状态当然是所有人都基于色情底模训练名人lora，但这很难形成趋势，毕竟政治正确。所以从市场定位的角度，个人觉得色情底模还是要混合兼容一下主流底模以方便链接更大的流量和受众。只是个人建议，如果非chill系白人lora因为基于1.5所以可以随便兼容，那么是否出一个能融合一些chill的基因的版本，让chill系lora也能使用进来呢？
@7016jayAlex 要兼容chill就要合併高比例的chill，這將會拉低模型的品質，特別是裸體和手指，那個模型已經很久沒更新沒進步了。我的模型重點是為了我自己使用方便，並且順便分享的，不是為了跟隨前幾名的模型而配合大眾。
你可以使用我的色情模型自己訓練人物lora(我的模型訓練寫實人物成功率很高)，或是你使用"PRO-V4版本"大部分的亞洲人物應該可以兼容，只是amateur版本的裸體更好。
@iamddtla Not to hijack your post but in my country I can not use Telegram. Do you have discord or whatsapp? I need to create lora for a poly group (4 girls) based in my country. Pls and thank you.
@KINGLIFER My discord ID is iamddtla. Please leave your discord method to add friends.
My discord is the exact same name as here.
@KINGLIFER I have sent a friend invitation, my name is iamddtla.
在下对于你看法，不是很赞同！并不是所有人都是老色批的！
forgive being mean, but it's true, the elaborater prompts the more confusing results you get, can not more inclination, so you have to count on the gods of randomness to give something that meets expectations, but always no. okey, for amateurs, more demands are fatal
Well I can tell you about now, but this Model really pushes all from the database and used it without any LoRAs! Hallelujah!
Hello i want to say that i really like your work and i consider downloading all of your models, my question is what version should i go for? i already downloaded pornmaster amateur FULL , all 6 models but they take a lot of space and would rather go for fp16 instead will that affect the quality? i dont want to train i just want to use the models, will fp16 be as good as the full one for making pics? thanks in advance.
Edit: After testing out fp16,fp32 and full i really don't see a difference in terms of quality they all work fine so i guess I will stick to fp16 for smaller size, btw really nice models and like your loras too 👍
fp16 is OK, there may be slight differences in some cases.
需要写masterpiece这样的质量提示词吗
你可以自己测试看看相同图片，加添"masterpiece"是否会有明显差异。
可以收费定制模型或者lora吗
定制推特上@cyber_gyaru 这个人需要多少钱
可以，請私下詢問我。
我的Telegram ID:@iamddtla0620
我的微信ID:iamddtla
我的line ID:iamddtla
FP16 V6 inpainting please!