[Slider] Colored Lineart

用于从线条中减去或添加颜色的LoRA模型。

这是一个我使用两张图片在ΣΙΗ 1.5上训练60步后创建的“即用型”模型，因此我不能保证其质量很好。

过程

制作工具： TrainTrain

数据集： 左侧为原图，右侧为目标图

差异较为细微，因为即使微小的孤立差异也会产生显著影响，而此方法在缩放时破坏性较小。

TrainTrain .json 设置： 截取自我对默认值的修改部分。

{
    "network_type": "lierla",
    "network_rank": "4",
    "network_alpha": "4",
    "train_iterations": "60",
    "train_batch_size": "1",
    "train_learning_rate": "0.0001",
    "train_optimizer": "AdamW",
    "train_lr_scheduler": "cosine_annealing",
    "train_lr_scheduler_settings": "eta_min=0.00002",
    "use_gradient_checkpointing": true,
    "network_blocks(BASE = TextEncoder)": [
        "IN00", "IN01", "IN02", "IN03", "IN04", "IN05", "IN06", "IN07", "IN08", "IN09", "IN10", "IN11", "M00", "OUT00", "OUT02", "OUT03", "OUT04", "OUT06", "OUT07", "OUT08", "OUT09", "OUT10", "OUT11", "OUT05", "OUT01"
    ],
    "network_strength": "1.0",
    "network_conv_rank": "0",
    "network_conv_alpha": "0",
    "network_element": "Full",
    "network_train_text_encoder": false,
    "image_max_ratio": "2.0",
    "train_min_timesteps": "400",
    "train_max_timesteps": "800",
    "train_loss_function": "Smooth-L1",
    "train_lr_scheduler_num_cycles": "1",
    "train_lr_scheduler_power": "1.0",
    "train_snr_gamma": "1.0",
    "diff_alt_ratio": "1.0",
    "diff_revert_original_target": true,
    "diff_use_diff_mask": false,
    "model_v_pred": true,
    "mode": "ADDifT",
}

模型裁剪： 在经过多个模块权重xyz测试后，我使用 Supermerger 将模型调整为 :1.3:OUTALL，权重设为1.3，因为测试中我曾使用:2，但若保持为2，Supermerger过程会使保存的模型权重几乎增加三倍。