The LoRA is able to create a photo realistic red cat.
这个 LoRA 能够创建逼真的红色猫照片。
The trigger words for this LoRA are
这个 LoRA 的触发词是
red cat
The training image have a resolution of 1024 x 1536 pixel. The related aspect ratio is 3:2. I downscaled them, so that one side should have a length of 1024 pixel.
训练图像分辨率为 1024 x 1536 像素。相关宽高比为 3:2。我将它们缩小,以便其中一边的长度为 1024 像素。
I used in total 19 of my best images.
我总共使用了 19 张我的最佳图片。
Training settings was 训练设置是
19 Images 19 张图片
38 buckets 38 个桶
2 repeats 2 次重复
Batch size 2 批处理大小 2
250 epochs 250 个周期
2500 learning steps 2500 训练步数
My first tests shows that the quality of the created images are depending on the model. Some models are better with respect to right anatomy than others.
我的初步测试表明,创建图像的质量取决于模型。有些模型在解剖结构正确性方面表现更好,而另一些则不然。
The LoRA is able to create a photo realistic red cat.
这个 LoRA 能够创建逼真的红色猫照片。
The trigger words for this LoRA are
这个 LoRA 的触发词是
red cat
The training image have a resolution of 1024 x 1536 pixel. The related aspect ratio is 3:2. I downscaled them, so that one side should have a length of 1024 pixel.
训练图像分辨率为 1024 x 1536 像素。相关宽高比为 3:2。我将它们缩小,以便其中一边的长度为 1024 像素。
I used in total 19 of my best images.
我总共使用了 19 张我的最佳图片。
Training settings was 训练设置是
19 Images 19 张图片
38 buckets 38 个桶
2 repeats 2 次重复
Batch size 2 批处理大小 2
250 epochs 250 个周期
2500 learning steps 2500 训练步数
My first tests shows that the quality of the created images are depending on the model. Some models are better with respect to right anatomy than others.
我的初步测试表明,创建图像的质量取决于模型。有些模型在解剖结构正确性方面表现更好,而另一些则不然。