<h2 id="lora-for-subtracting-or-adding-color-to-lines.">LoRA for subtracting or adding color to lines.</h2>This is more of an as-is model that I created with two images in 60 steps on ΣΙΗ 1.5 so I am not promising that it is well made.<h3 id="process">Process</h3>Made using: <a target="_blank" rel="ugc" href="https://github.com/hako-mikan/sd-webui-traintrain">TrainTrain</a>Dataset: Left as Origin and right as Target<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/62654c00-fd17-48c2-bb81-61b98a000bb4/width=525/62654c00-fd17-48c2-bb81-61b98a000bb4.jpeg" />The differences are subtle because even small isolated differences have a large impact and this method is less destructive when resizing.TrainTrain .json settings: Truncated based on what I changed from default.<pre><code>{
 "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",
}
</code></pre>Model Trimming: After various block weight xyz tests I used <a target="_blank" rel="ugc" href="https://github.com/hako-mikan/sd-webui-supermerger">Supermerger</a> to alter the model to <code>:1.3:OUTALL</code> 1.3 weight because I was using :2 in tests but the supermerger process would essentially triple the saved model weight if I kept it at 2.

[Slider] Colored Lineart

Initial v1 version.Depending on the artist prompted you may want to include the following prompt but it's not necessary.Positive: colored lineartNegative: blending, no lineart

Files with SHA256: 879fb1beb3bb49b0f1988a9a86631c088d5712b85c5f332f6d59d3841e265636