tsuhonki posts
Posts: 32
Files: 111
Kisaki
1, blender (render img) + tile -> initial img2. inpainting + tile + Kisaki LoRA -> change character3. (inpainting + PS) x N -> cloud and plane under feet4. i2i + tile + detail tweaker LoRA -> filter and add some details5. upscale6. PS -> adjust color and shadow + depth of field
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 thighhighs, socks, barefoot, low angle. Most merged models are anime models.下载链接 Download link: https://ci...
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.所用到的两个 LoRA 模型可以在 civitai 上下载，Lyco 模型为别人的私模，由于作者不允许外传...
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 LoRA) -> upscale
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 socks, but unexpectedly ended up with bare feet...
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我们想保留这样的人设做另外一张图，直接把这张图放进 ControlNet 选 Reference Only 预处理器，权重调到 1We want to preserve this character design and create another image. We ca...
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 then text is generated using GPT.画像に添えられた文章はAIによって生成されており、Vi...
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 + tileThis one has the most simplified process of recent images: t2i -> inpainting -> i2i + tile -> inpainting -> upscale -> i2i + tile.首先生成人物，这里我选择白毛红瞳...
又一张多步合成图 / Another img by multi-step synthesis
底图 / Base image:与上一个帖子类似的处理 / Almost the same processing steps as the last post.另外出了一张用不同放大算法的 / A result using different upscaling algorithm:使用了 tiled diffusion noise inversion 配合 ControlNet tile 模型
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：我自己个人平时出图基本上是文生图（叠加巨大娘模型/ControlNet）直接出图，再做局部修复/高清修复，但是对于一些特定的互动很随机。启发：在 arca ...
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。首先这是一张底图，是用最新的模型生成的。（模型我还在调，现在训练出来有两个还不错的模型，但均有着...
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，没有用 ControlNet 辅助。手的问题是目前 AI 现状还是得修...I've just trained a new mo...
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.警告：这些图还未完成，多数还未经高清修复/仔细筛选，部分可能会重新生成/局部重绘修一...
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 :)
How 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分General idea: Use inpainting to draw tiny citiesFirst, you need to use an inpainting model. Since many checkpoint models do not provide a version specifically for inpainting, using these models directly for inpainting will be very random. The...
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：这些图还未完成，多数还未经高清修复/仔细筛选，部分可能会重新生成The parameters used are the same as Flandr...
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The guide to reproduce this Giantess Youmu 巨大妖梦 | tsuhonki on Patreon复刻这张图的教程 Giantess Youmu 巨大妖梦 | tsuhonki on PatreonStable Diffusion model: AOM3A1BVAE model: kl-f8-anime2LoRA model: jvdaniang_v3Clip Skip: 2P...
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 stable-diffusion-webui and deploying locally.2. How can I view the prompt used for your images? Please download my original image, then open stable-diffusion-webui and find the "PNG Info" option...
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.From this, you can see that the color value of the sky is RGB (6, 230, 230), and the color value of the building is RGB (180, 120, 120).Using semantic segmentation in ControlNet allows for generating co...
Giantess Youmu 巨大妖梦
Tried a horizontal version of images.尝试了一下横版的图片
