升级了立绘lora模型的版本,修改了训练时的分辨率和维度,可以生成更清晰的图片。
推荐分辨率:768*768.
Upgraded the version of the Lora model, modified the resolution and dimensions during training, and generated clearer images.
Recommended resolution: 768 * 768
lihui.safetensors
Same model published on other platforms. May have additional downloads or version variants.