PornMaster_SDXL_Illustrious_noob_Pony_t2i_工作流下載(Workflow Download)
PornMaster Simple 4X Magnification Workflow
PornMaster Z-image-turbo Controlnet: Cosplay - Anime to Realistic Style
PornMaster [Flux.2 Klein 9B] - Anime to Realism Workflow
--
Stable Diffusion WebUI Forge - Neo
--
模型介绍为中英双语，中文用户可以关闭翻译。
此版本可以在写实风格与动漫风格之间切换。
可使用写实风格或动漫风格的lora。
可使用sdxl和Illustrious的lora。也可以使用部分的"pony"lora。
--
This version can switch between realistic style and anime style.
This version can use realistic or anime style lora.
Can use sdxl and lora of Illustrious.This version can also use parts of the "pony" lora.
---
我已將模型上傳至runninghub。
I have uploaded the model to runninghub.
PornMaster-Pro-noob-V6-VAE:
https://www.runninghub.ai/model/public/2004812200420274178/?inviteCode=rh-v1304
PornMaster-Realism-IL-V4-VAE:
https://www.runninghub.ai/model/public/2043980764240420866/?inviteCode=rh-v1304
--
如果在我的检查站训练某些lora效果不好时，可以在” noobaiXLNAIXL_epsilonPred11Version”或” illustriousXL_v01训练lora，这样lora在我的检查站依然可用。
If the effect of training some lora in my checkpoint is not good, you can train lora in "noobaiXLNAIXL_epsilonPred11Version" or “illustriousXL_v01", so that lora is still available in my checkpoint.
--
Sliders lora for color temperature, brightness, saturation, and contrast.
--
Add details and improve the accuracy of prompt words lora.
--
--
NoobAI-XL ControlNet-OPENPOSE.
--
My other checkpoints and Lora.
--
--
Light and color control: sd-channel-offset
--
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。
--
--
Preview images & prompts for 20,000+ Danbooru Characters:
https://www.downloadmost.com/NoobAI-XL/danbooru-character/
Preview images & tags for 6,000+ Danbooru Artists' styles:
https://www.downloadmost.com/NoobAI-XL/danbooru-artist/
Preview images & tags for 4,000+ e261 Artists' styles:
https://www.downloadmost.com/NoobAI-XL/e621-artist/
Preview images & tags for 3,000+ e621 Characters:
https://www.downloadmost.com/NoobAI-XL/e621-character/
--
简易使用方式:
至” Danbooru"或"e621”选择一张图片，将图片中的提示词全部复制，然后输入提示词即可，或是對空格添加逗號並且移除下畫線。
Easy to use:
Go to "Danbooru" or "e621" to select a picture, copy all the prompt words in the picture, and then enter the prompt words, or add commas to spaces and remove underscores.
--
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)
--
使用自然语言并且混合"danbooru"标签时，能获得更好的效果。
Better results are achieved when using natural language and mixing in "danbooru" tags.
--
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)"
--
SDXL-加速器(SDXL-accelerator):
lora權重(lora Weight):0.6~1
取样方法(Sampler)=LCM
Schedule type: SGM Uniform
CFG:1
8~14步(steps)
--
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".
Description
FAQ
Comments (26)
Can you provide the training parameters for v2.5 as in optimizer, learnrate, sampler, etc.. ? the model is by far the best when it comes to prompt but requires a character/style lora of some kind. Been trying to retrain the lora/lyrics on the newer 2.0/2.5 model but results are really bad.
To train a character or style lora, I recommend you train on the original Illustrious-v0.1 or noobAI-xl-v1.1, so that when used in my checkpoints, it will be convertible to realistic or anime style.
Hi! Your model is almost perfect! And lots of thanx for it! You are a genius! BUT! Could you implement more male faces in it? Male bodies and genitals look fine, but all faces tend to be girlish. Sorry for my bad english.
You can use lora with male face.
💀💀💀💀💀💀💀 5k
ty for making v2.5 it is a big improvement over 2.0, keep it up man! and im sry if i annoyed you earlier with questions i hope you arent mad at me :(
hey so is new realistic il v1 model actually based on illust 0.1? or its noobai based model?
illust 0.1
Even when turning on the sdxl clip skip in reForge I still get exactly the same generation on 1 and 2.
hey remember the issue with noob v1 pornmaster i had, the error? it was because i was usuing vae precision at fp 16, now at fp32 vae meaning no half vae in other words it work fine.. weird, you must have merged vae in it as fp 32
Another underrated model. It gives amazing results, and I'm not talking about lewd pictures. Amazing, vibrant, detailed backgrounds, doesn't have much problem with hands, creates good, dynamic poses (I swear, a lot of models give you almost the same boring pose every time), very nice clothes with minimal prompts... Absolutely amazing results!
打擾一下 請問您的模組的提示詞要輸入甚麼
可以跟圖片網址一樣的蹲姿 只不過我想把雙手放在膝蓋上 只知道這個是相撲蹲 可是生成結果是不關聯
我用的版本是1.8版本
https://cc.tvbs.com.tw/img/program/upload/2019/11/22/20191122153926-07f5207d.jpg
absolutely love your noob v2.5 version! and it goes great with updated 4k skin texture v6 lora trained on it! reducing loras size to 100mb helped a ton imo.. yeah it def peak rn, btw can you pls update your realistic skin epoch 20 lora too? i love to use it with your models i mentioned above but it must be outdated by now it was made quite a while ago and for pornmaster v0.1
The lora of Realistic Skin Epoch 20 was not made by me.
@iamddtla oh.. yeah it wasnt you who made it.. man im dumb xd well then sry for the confusion, keep it up dude!
@iamddtla hey, speaking of your loras.. can you pls update cosplay photo and mb realistic v2.1 too like you did update skin v6 lora? the update was simply amazing imo i think it will greatly benifit these two loras too, at least cosplay one
@makotoyuki Try "amateur cosplay photo".
@iamddtla wow ty, but wouldnt it be better to train one on v2.5 noob? illustrious has much less datasets and all, overral less of a model and not quite the same as your noob v2.5 pornmaster, i think it wont work as good on it because it as trained on your realism ilust v1
@makotoyuki Can be used with PornMaster-Realism-IL-V1 as a refiner to enhance realism.
hello i absolutely love how all your latest loras turn out! btw im curious about your SDS Film lora, its rly good for adding realism to your current illust/noob models, but its last version is for SDXL model, is it worth updating it too? its an amazing lora
I can't update it, it's a lora extraction from some film photography checkpoint.
i decided to try latest ILv1 model and man its few times more realistic than noobv2.5, how did you achieve this amazing result? and why did you pick illustriousv0.1 for that? cant noobai be trained just as realistic? i mean details and textures are AMAZING
I am "Checkpoint Merge", "noob" checkpoint no one trained good realistic style.You can use the Realism-lL-V1 as a refiner for the NOOB checkpoint.
@iamddtla pls can you make lora extract of ilv1 model? like you did with SDS film lora? it would be rly great as alternative to using the model as refiner for noobv2.5
@iamddtla yeah its good lora right, but i doubt it is extract of the model you currently have on this page, the pornmaster ILv1.. dates dont match