The model was trained on approximately 1600 images of various types. To ensure versatility, it was trained on multiple styles, and secondary images were assigned lower probabilities.
Approximately 25% of the main data consisted of fursuits. The rest were images of various different styles.
NSFW training was conducted, but the interweaving of different concepts and the varying learning difficulty make it unreliable compared to dedicated models.
Due to the limitations of the device's memory, the training resolution was set at 512.
The intensity can range from approximately 0.2 to 1.5.
Some display images:
Sampler
er_sdr can obtain more detailed images.
euler/a is more stable.
If you want to obtain better details/quality, use multi-level sampling and switch the sampler.
Training tool: OneTrainer
Rank: 48
If you wish to continue training this model with new data, this setup should allow you to do so; other parameters should not hinder the training process.
If you need better, smoother fur textures, you can use the raw model.
如果你需要更好更细腻的皮毛纹理,可以使用raw模型
====
模型在约1600张多种类型的图像上训练，为了泛用性在多种风格上训练，但次要图像使用更低的概率。
主要数据中大约25%是fursuit。其它是各种不同风格的图像。
进行了NSFW训练，但是不同概念之间相互交错和学习难度不同，与专用模型相比并不可靠。
受限于设备显存，训练分辨率为512。
强度可以在大约0.2~1.5生效。
采样:
er_sdr 获得更多细节
euler/a 更稳定
如果你想获得更好的细节/质量,使用多级采样和切换采样器.
训练工具:OneTrainer
rank:48
如果你想在此模型上使用新数据继续训练,这应当能能让你继续,其它参数应该不会阻止训练
Description
Perform longer training on a larger-scale dataset.
However, the different concepts are interwoven with each other and the learning difficulty varies. The model training might be overly intense and a lower intensity might be needed.
===
在更大规模的数据集上进行更久的训练
但是不同概念之间相互交错和学习难度不同,模型训练有些过度,可能需要低一点的强度.
FAQ
Comments (2)
非常好lora，让我的福瑞🧠被激活。另外，这个lora有没有什么后续更新计划？我有个朋友让我问一下会不会加入🐻或者🐷体型的福瑞的数据集（真的是朋友要问）。
也许会更新，但短期不会，我觉得目前基本训练到极限了，我已经尝试了几次从头开始训练和中途调整概念数据量了，更多训练也没得到好结果。
因为不同概念之间相互交错和学习难度不同，会出现有的没学到有的已经过拟合，只训练部分又会导致严重遗忘，短期内不会准备太多新图像进行数据平衡。
现在可以让你朋友使用相关体型英语+体毛。
为了更好效果添加更多胖体型身材数据可以，我看到了会留意下，但为了避免语义污染不会直接使用单词beer。