All Images Here Are Generated By AI.
All Models
>PornMaster-Fantasy
Generate AI Images. Simple and Easy
Model Description by Creator
客製化lora:我的Telegram ID:@iamddtla0620
我的微信ID:iamddtla
我的line ID:iamddtla
时间宝贵，请直接说明来意，例如:订制LORA.
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.
--
--
"inpainting"版本的模型为局部重绘使用的模型，不是用于生成图片。
The "inpainting" version of the model is a model used for partial redrawing, not for generating images.
--
不包括 VAE，推荐"vae-ft-mse-840000-ema-pruned"(颜色较鲜艳)或orangemix.vae (颜色较浅)。
Excluding VAE, recommend "vae-ft-mse-840000-ema-pruned" (brighter color) or orangemix.vae (lighter color).
--
我在我的上模型测试超高速产生图片的方式:
(可能1秒生成图片。)
使用LCM-LoRA作为产生图片的加速器，权重设定0.7效果最佳，在取样器Euler a的情况下，只需10步骤可产生清晰图片。
(CFG设定2以下。)
使用"inpainting"模型做局部重绘，相同方法可以高速去除衣服。
I'm testing a way to generate images super fast on my model:
(It is possible to generate a picture in 1 second.)
Using LCM-LoRA as an accelerator to generate images, the weight setting of 0.7 has the best effect. In the case of the sampler Euler a, only 10 steps can be used to generate clear images. (CFG is set to 2 or less.)
Use the "inpainting" model to do local repainting. The same method can remove clothes at high speed.
--
LCM Sampler download,LCM取样方法下载
--
2023/11/18:
V2没有FULL版本。
V2 does not have a FULL version.
PornMaster-fantasy-V2版本来自PornMaster-Amateur-V6与PornMaster-Anime-V2的合并，触发词可参考这两个模型中的说明。
部局部重绘可使用adetailer或sd-face-editor.
使用"sd webui cutoff"可避免颜色溢出污染其它元素。
高解析度放大可使用"ultimate SD upscale".
The PornMaster-fantasy-V2 version comes from the merger of PornMaster-Amateur-V6 and PornMaster-Anime-V2. For trigger words, please refer to the instructions in these two models.
For partial facial redrawing,adetailer orsd-face-editor can be used.
Use "sd webui cutoff" to avoid color overflow contaminating other elements.
High resolution upscaling can be done using "ultimate SD upscale".
--
flat chest,平胸(negative-负面:medium breasts,large breasts)
--
--
FP16版本适合电脑低阶配备。
FP32版本适合电脑中阶配备。
FULL版本适合电脑高阶配备。
"inpainting"版本的模型为局部重绘使用的模型。
--
范例中的"and"，你也可已使用"逗点"，这是我个人习惯的提示词方式。
1.建议Clip跳过层设定为1~2，取样方法Euler a或DPM++ SDE Karras。
2.影响脸部的lora不要使用”面部修复”，例如:cum on face,AHEGAO,tongue out
3.不包括 VAE，但我推荐默认的"vae-ft-mse-840000-ema-pruned"。
4.如果您喜欢我的工作想请我喝咖啡：Paypal
5.可用的艺术家姓名。
https://stablediffusion.fr/artists
https://stablediffusion.fr/artist
7.避免散景（景深、散景、模糊）
负面提示放入:(depth of field, bokeh, blurry:1.4)
--
The FP16 version is suitable for low-end computer equipment.
The FP32 version is suitable for mid-level computer equipment.
The FULL version is suitable for high-end computer equipment.
The "inpainting" version of the model is used for partial repainting.
--
For the "and" in the example, you can also use "comma", this is the prompt word method I am used to.
1.It is recommended to set the clip skip 1~2, the sampling method Euler a or DPM++ SDE Karras.
2.VAE not included but I recommend the default"vae-ft-mse-840000-ema-pruned".
3.If you like my work and want to buy me coffee: Paypal
4.My English is not good, I use Google Translate to talk to you.
5. Available artist names.
https://stablediffusion.fr/artists
https://stablediffusion.fr/artist
