Waifu Painting (JWW)版本v3 LoHa Epoch 20 (Underfitted model) (Underfitted model)

Only for SD2.x models such as Waifu Diffusion 1.5, will not work SD1.x models such as Anything, AOM, Counterfeit, and etc.

A painting style LoRA trained on Waifu Diffusion 1.5 beta2, with training data from images of paintings of John William Waterhouse (69 files gathered from wikipedia) with almost no tagging.

Trained with noise offset = 0.1, so it will conflict with other LoRA without noise offset.

Also, it doesn't generate pure landscape well, as John William Waterhouse is purely a "waifu" and mythology painter, all of his paintings contain human subjects (I've tried to fix this problem with v2).

Training parameters:
For v1: Learning rate is 1e-5 for both unet and text_encoder, scheduler constant with warmup. Image repeat = 10.

For v2: Same learning rate, but with augmented data. I cut out the parts of paintings that only have background (for example: https://files.catbox.moe/ad6tyo.png) and add them to the training sets.

For v3: Instead of cutting background part to new images, I erased the subject instead. But it doesn't seem to work well.

描述:

Set the weight to 9 or 10. When prompting without waifu, 5 or 6. Truth me, hehe

Install (or update) this extension: https://github.com/KohakuBlueleaf/a1111-sd-webui-locon
Ironically, Kohaku LoHa didn't work in Additional Network, but native Automatic1111 LoRa prompt :)) So put it in stable-diffusion-webui\models\Lora folder.

A LoHa trained with very small learning rate (1e-6). Waifu style of original model (WD1.5) is virtually unchanged, but background style becomes painting style. But I still cannot generate pure nature background without people.

训练词语: painting by john william waterhouse