Kisaki
1, blender (render img) + tile -> initial img
2. inpainting + tile + Kisaki LoRA -> change character
3. (inpainting + PS) x N -> cloud and plane under feet
4. i2i + tile + detail ...
tsuhonki posts
GAP-mix v0.3 融合模型 CHECKPOINT MERGE
融合模型，大部分为二次元模型，融合有少量 2.5D 和真实感模型。对雪糕、袜、裸足、低视角有一定的特化。
Merged model, with some specification for thig...
2023-06-28 01:05:33 +0000 UTC View Post
Kisaki 制作流程 / creating process
首先，通过文生图生成一张图，具体参数可以下载原图查看
First, generate an image using txt2img. Please download the original image to view specific parameters.
2023-06-15 10:53:09 +0000 UTC
View Post
Kisaki
Test the stability when mixing with other models.
测一下和其它模型混合的稳定性
txt2img (2 LoRA + 1 LyCORIS) -> inpainting (1 LoRA + 2 LyCORIS) -> tile + img2img (1 L...
2023-06-09 06:44:11 +0000 UTC View Post
乱融模型弄出来的 / The result of randomly merging checkpoints
MBW 乱融模型，本来是想融个雪糕特化进去，结果意外的出了裸足...
Randomly merge checkpoints with MBW, which was originally intended to incorporate a model for white so...
2023-06-02 10:47:59 +0000 UTC View Post
利用 ControlNet Reference Only 保留人设 / Preserve character design using ControlNet Reference Only
比如，我们先做出了这样一张图 / For example, if we first make a image like this
我...
2023-05-26 15:28:13 +0000 UTC View Post尝试用 AI 识图配文 / Attempt to use AI to recognize the image and then add some texts.
图中配的文章为 AI 生成，通过 Visual GLM 识别图片，然后使用 GPT 生成文章。
The text accompanying the image is AI-generated. The image is recognized using Visual GLM, and...
吞噬地球的巨大少女 / Giantess Girl Eating Earth
最近出的流程最简单的一张图了，大致 t2i -> inpainting -> i2i + tile -> inpainting -> upscale -> i2i + tile
This one has the most simplified process of recent image...
又一张多步合成图 / Another img by multi-step synthesis
底图 / Base image:
2023-05-18 09:11:07 +0000 UTC
View Post
一种合成工作流 / A Workflow for Composition
English version is in the second half of the article.
先放效果 / First, let's see the result：
2023-05-17 09:48:14 +0000 UTC
View Post
Tips for using ControlNet Tile / ControlNet Tile 使用技巧
English version is in the second half of the article
最近试了试新的 ControlNet 1.1 中的模型，发现 tile 模型改图/修图/放大非常强。
2023-05-06 08:27:22 +0000 UTC
View Post
New Model Test 新模型测试
最新训练的一个新模型 jvdaniang_v10，还在测试，等 checkpoint 基本挑好了，我就先放上来。这张图是文生图且仅使用了这个新模型，没有任何后处理，没...
2023-05-01 14:52:49 +0000 UTC View Post
Some work-in-progress images 一些正在做的图
Warning: These images are still work-in-progress and most of them have not been carefully selected or upscaled in high resolution. Some may be regenerated or fixed by inpainting. 2023-04-23 13:03:15 +0000 UTC View Post
fufu (just a try, really strange 只是试了试非常怪)
随便乱玩，试了试 fufu，要笑死我了，太怪了
Just a try with fufu, really funny :)
2023-04-13 14:18:43 +0000 UTC View PostHow to synthesize a shrunken city 怎样合成缩小城市
Please read the FAQ first
中文版本在文章后半部...
Some work-in-progress images 一些正在做的图
Warning: These images are still work-in-progress and most of them have not been carefully selected or upscaled in high resolution. Some may be regenerated.
警告 2023-04-10 13:44:46 +0000 UTC View Post
Giantess Youmu Reproducing Guide 巨大妖梦复刻教程
Please read the FAQ first
中文版本在文章后半部分
Frequently Asked Questions about Creating Giantess Pictures using AI / 用 AI 生成巨大娘图片的常见问题
中文版本在文章的后半部分
1. What are you using to generate these images?
I'm using 2023-04-09 01:30:12 +0000 UTC
View Post
Tutorial on using control-seg to generate micro cities / 使用 ControlNet 语义分割生成小城市的教程
First, please download the color_coding_semantic_segmentation_classes.xlsx file in the attachment.
Giantess Youmu 巨大妖梦
Tried a horizontal version of images.
尝试了一下横版的图片
2023-04-07 11:41:52 +0000 UTC View Post