Style | Fantasy Effect - Blaze and Breeze (OTCG)

Buy us a cup of coffee and we’ll spill the beans.

https://www.buymeacoffee.com/CoSubcreation

Or Fanbox

https://co-subcreation.fanbox.cc/

Or爱发电

https://afdian.net/a/Co_Sub_creation

Your support is the fuel that powers our world-building. Your ideas are the bricks that shape our world-making!

あなたの応援で、世界は生まれ変わる！あなたのアイデアが、世界を作り上げる原動力になるよ！

您的支持将成为创造世界的动力，您的想法将成为构建世界的基石！

If you have any ideas, suggestions, or questions during use, you can ask them on Discord ↓

ご利用中に何かアイデアや提案、質問がございましたら、Discordにてお問い合わせいただけますようお願いいたします↓

使用中有任何想法&建议&问题，可以去Discord提问↓

https://discord.gg/tVpJMhjUwx

If you’re new to LoHa, please read this:

This model was trained with LoHa, so you need to install the WebUI extension. Trust me, it’s worth it.😉

GitHub - KohakuBlueleaf/LyCORIS

LoHa model path: models/Lora

Usage: Click on the 🎴 button under “Generate” in the WebUI, choose the Lora tab, select the model, and adjust the weights. It’s as easy as pie.🍰

第一次使用LoHa请看：

本模型训练使用了LoHa，需要安装WebUI的扩展。

GitHub - KohakuBlueleaf/LyCORIS

LoHa模型路径: models/Lora

使用：点击WebUI“生成”下面的🎴，选择Lora 选项卡，选择模型，更改权重。

Recommended parameters:

推荐参数：

Model: MIX-Pro-V3

Vae: kl-f8-anime2

Clip skip: 2

weight:0.6

Sampler: DPM++ 2M Karras

Steps: 20

Highres fix: Enabled

Upscaler: SwinIR 4x

Upscale: 2

Highres steps: 15-25

Denoising strength: 0.3

Size: 512x512|448x640|640x448

CFG Scale: 7

Preferred Prompts:

推荐提示词：

Prompt:

1girl,solo,floating,otcg, <lora:Style_FantasyEffects_BlazeandBreeze (OTCG)_v1.0:0.6>

Negative Prompt:

EasyNegative, badhandv4

EasyNegative | Stable Diffusion TextualInversion | Civitai

badhandv4 - AnimeIllustDiffusion | Stable Diffusion TextualInversion | Civitai

Instructions:

说明：

This model supports most cel-shaded and flat-colored base models; it may produce weird results with thick-painted or 2.5D base models; it does not support real-life images.

支持大部分赛璐璐、平涂底模；用厚涂系、2.5d底模，有概率出奇怪的东西；不支持三次元。

If the face is distorted when drawing a full-body image, you can import img2img fix it.

画全身如果脸崩，可以导进图to图重绘一下。

The default color will be reddish-golden, if you want other colors, add color prompt.

默认颜色会偏红金，想要其他颜色加提示词。

Adding too many prompt words requires increasing the model weight accordingly, but too high weight will make you behold the eldritch horrors and lose your grip on reality. Like this↓Beware of the unspeakable things that lurk in the shadows.😱

加太多提示词需要相应提高模型权重，但权重过高会导致san值狂掉。如比这样↓

If you want an abstract background that looks like you had a trip on magic mushrooms, you may try using a higher weight.

如果你想要一个像吃了毒蘑菇一样的抽象背景也许可以尝试使用更高的权重。

Of course, you can also use it to create an atmosphere for Legendary creatures, like this↓

当然也可以用它做神兽的氛围图，比如这样↓