[LoRA] Wide-angle upward shot/extremeangle 广角仰拍

模型介绍：
欢迎大家使用本模型。如果你喜欢我的工作，欢迎在ko-fi上为我买杯咖啡☕

Everyone is welcome to use th models! If you like my work, feel free to buy me a coffee on ko-fi ☕.

如您有模型定制或其他合作、咨询需求，请联系Wechat: pomelonioi。请简单注明来意，时间宝贵不闲聊哈，谢谢理解！

If you have any model customization or other collaboration and consultation needs, please contact Wechat: pomelonioi . Kindly provide a brief description of your inquiry, as there's limited time and no time for casual chats. Thank you!

This is a model with a slight wide-angle lens effect from an upward shooting perspective. Shooting from bottom to top at an extreme angle creates a distortion effect, making the lower part appear wider and the upper part narrower.

The higher the Lora weight and the steeper the upward shooting angle, the more pronounced the distortion effect becomes. The resulting image appears more grandiose and delivers a strong visual impact. This effect is well-suited for capturing tall buildings and natural landscapes. It also adds a striking visual impact to portrait photography, creating the impression of "long legs," "shoes close to the lens," and "a very tall person with a small face."

Currently, the perspective shifts are achieved using tags like "from below" or "from above," but these terms are too vague, only slightly offsetting the view "up" or "down." They do not provide the desired sense of extending the image or the necessary distortion effect, especially when shooting from an extremely low angle, placing the lens on the floor, or aiming it at the feet and shoes.

1. Base Model: Inkshadow Moyourenzaoren
2. Trigger Word: extremeangle
3. Recommended Weight: 1.0 or 0.75
4. When generating characters, the model with a high weight tends to produce full-body images, so remember to use adetailer. Half-body images also work well. There are no particular restrictions when generating buildings and landscapes.

这是带有一点点广角镜头效果的仰拍视角模型，从下而上的仰拍视角会造成下宽上窄的畸变效果。

Lora权重越高、仰拍角度越大、畸变效果越明显、画面更显高大宏伟、给人的视觉冲击力也越强。它既适合高大建筑、自然风光的呈现；又会给人像摄影带来强烈的“大长腿”、“鞋子怼镜头”、“人很高、脸很小”的视觉冲击。

目前视角的切换都是用from below、from above等tag，而这些词的含义过于泛泛，只是稍微“往下”或者“往上”偏移一点，无法得到我想要的画面延伸感，也没有该有的畸变效果，更别说这种镜头放在地板上、怼在脚和鞋子上拍摄的极低视角了。

1. 训练底模：墨幽人造人v1040
2. 触发词：extremeangle
3. 建议权重：1.0或者0.75
4. 生成人物时模型高权重倾向于全身图，一定要记得开adetailer；半身图亦有不错的效果；生成建筑和风景时无所谓；

为了更好地让新司机上路，作为老司机的Muggle在鹅群（891417811）放了自制抽卡机（wildcards），包含日常穿搭、职业制服、搞怪戏服、节日礼服等数百套风格；

此外，如果你会Openpose，我还准备了300个用于控制人物姿势的Controlnet骨架图（站姿、坐姿、躺姿）方便又实用；主流插件也都整理好了，等你来取。

海外用户请加TG群 https://t.me/+bm9GZdmvf3dmMWM9
Join my TG group to chat https://t.me/+bm9GZdmvf3dmMWM9

~~~~~~~~~~~~~~~~~~~~~~~o(*￣︶￣*)o~~~~~~~~~~~~~~~~~~~~~~~

示例提示词和参数：
Prompt: <lora:extremeangle-000002:1>,extremeangle,1 girl,moyou,(looking at viewer:1.3) ,snowy mountain,(skiing:1.1), coat,  gloves,<lora:调细节添加-2~2 add_detail:0.1> ,princess, <lora:图图的嗨丝（极光5D黑色连裤袜）_v1.0:0.8>

Negative prompt: dedicated_to_artificial_humans_v1.0, (bad-hands-5:1.4)

Steps: 40, Size: 1024x1728, Seed: 582343974, Model: moyourenzaoren_v1040 , Sampler: DPM++ 2M SDE Karras, CFG scale: 7