base model-基础模型

BDSM、sex toys-性虐待、性玩具

sex positions-性爱姿势

clothing-服装

photography style-摄影风格

Other porn-其它色情

porn star-色情明星

character,cosplay-人物、角色扮演

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.

-

范例图片有使用面部修复、放大、局部重绘，你可能无法生成与我相同的图片。

The sample pictures use face restoration, enlargement, and partial redrawing. You may not be able to generate the same picture as me.

--

"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.

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0.4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4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 0.4 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 4 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

--

需要增加阴部的真实感和细节时，可使用这些有许多阴部照片训练的lora:內射、假屌、陰部穿孔、潮吹、肛塞、一線鲍、淫水丝、分開陰部

When you need to add realism and detail to your vagina, Use these loras with lots of pussy photos to train:creampie、dildo、Pussy Piercing、squirting、butt plug、cleft of venus、pussy juice string、spread pussy

-

flat chest,平胸(negative-负面:medium breasts,large breasts)

--

2023/12/31

V4基于V3增加” Futanari、Fluffity、小孩(童话故事)、可爱风格、(兽交)。”

V4不一定比V3版本更好，我是因为出于有趣而增加其他主题到模型中。

V4可以更容易生成非人类和可爱风格。

不包括 VAE，推荐"vae-ft-mse-840000-ema-pruned"(颜色较鲜艳)或orangemix.vae (颜色较浅)。

V4 adds "Futanari, Fluffity、, children (fairy tales), cute style, (bestiality)" based on V3.

V4 is not necessarily better than the V3 version, I added other themes to the model just for fun.

V4 makes it easier to generate non-human and cute styles.

Excluding VAE, recommend "vae-ft-mse-840000-ema-pruned" (brighter color) or orangemix.vae (lighter color).

--

2023/12/4

V3增加多个具有庞大培训数据却很少人下载的模型(培训图片大部分为数十万张至上百万张。

V3 adds multiple models with huge training data but few people download it (most of the training images range from hundreds of thousands to millions of images).

Clip 跳過層:1~2

Clip skip:1~2

--

2023/08/23

FULL-V2-inpainting-可透过局部重绘生成，子宫脱垂(uterine prolapse)或肛门脱垂(anal prolapse、rectal prolapse)。

--

2023/08/12

V2增加子宫脱垂(uterine prolapse)和肛门脱垂(anal prolapse)、rectal prolapse

增加Gape60的合并，提示词可参考Gape60的培训数据。

1.培训lora请使用FP32或FP16版本

面部局部重绘可使用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".

--

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。

2.如果您喜欢我的工作想请我喝咖啡：Paypal

3.模型不包含vae,推荐使用orangemix.vae

4.提示词可参考danbooru。

5.避免散景（景深、散景、模糊）

负面提示放入:(depth of field, bokeh, blurry:1.4)

--

2023/08/23

FULL-V2-inpainting-can be generated through partial repainting, uterine prolapse or anal prolapse, rectal prolapse.

--

2023/08/12

V2 Increased uterine prolapse and anal prolapse、rectal prolapse.

Added the combination of Gape60, the prompt words can refer to the training data of Gape60.

1.Please use the FP32 or FP16 version for training lora.

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".

--

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.

--

2. If you like my work and want to buy me coffee: Paypal

3.The model does not contain vae, it is recommended to use orangemix.vae

4.For prompt words, please refer to danbooru.

5.How to avoid Bokeh:
Negative prompts to put in: (Depth of Field, Bokeh, blurry:1.4)