<h1 id="color-theory-(study)-s6j71z5vw">Color Theory (Study)</h1>This is a small study on tagging color concepts in the context of artworks that make use of color theory.I'm not an expert on any of these topics, just enjoying learning &amp; sharing.I've also used these as an comparative study on DoRA/LoRA training (I prefer the DoRA results).Usage Guide:These tags are already common Danbooru tags,so applying some of the techniques here to other models might work for more aesthetic color compositions.Color HarmonyExtreme unity leads to under-stimulation,extreme complexity leads to over-stimulation.Harmony is a dynamic equilibrium.Analogous ColorsAnalogous colors are any three colors which are side by side on a 12-part color wheel,such as yellow-green, yellow, and yellow-orange.Usually one of the three colors predominates.Complementary ColorsComplementary colors are any two colors which are directly opposite each other,such as red-green, red-purple and yellow-green.<h2 id="tagging:-yp6m6hc30">Tagging:</h2>For color triggers, theme/background should be interchangeable - but I gave more focus to theme tagging.Color wheel (clockwise order):<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0ff1d493-299a-4426-bc7e-01cce78fe4e5/width=525/0ff1d493-299a-4426-bc7e-01cce78fe4e5.jpeg" /><pre><code>red theme
orange theme
yellow theme
green theme
blue theme
purple theme</code></pre>Saturation:<pre><code>colorful
high contrast
black theme
white theme
brown theme
grey theme
cyan theme
pink theme</code></pre>Lighting:<pre><code>light
light beams
dappled light
dark
shadow</code></pre>Complementary Colors:<pre><code>yellow, purple
orange, cyan
red, green
blue, orange</code></pre>Composition:<pre><code>spot color
scenery
simple background
gradient background</code></pre>Three Color Palette:For a 3 color palette, can aim to apply colors to the generation by the rule of thirds for a nice balance.For a character focus, <code>hair, eyes, accessories</code> can work well for a 10% element.A <code>{color} theme</code> works well for the 30% element.And a <code>{color} background</code> works well for the remaing 60%.Example combination:<pre><code>green background, cyan theme, red eyes</code></pre>Stepping through the color gamut of available tags with an X/Y plot on Prompt/SR:<pre><code>green,yellow,orange

cyan,green,yellow

red,purple,blue</code></pre>Selective Coloring:Selective coloring is a photography technique where one color is prominent in the final shot whereas all the other colors have either been changed to monochrome or had their color saturation levels lowered.White:<code>spot color, white theme, white backgroun, light, light beam, dappled light</code>Black:<code>spot color, black theme, dark, shadow</code><hr /><h3 id="license-rdmgienwa">License</h3><a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a>

Color Theory (Study)

This is a DoRA, not your typically made LoRA. A1111 v1.9.0 and up is required to use this. Forge users must download two files, which can be found <a target="_blank" rel="ugc" href="https://github.com/lllyasviel/stable-diffusion-webui-forge/pull/608/files">here</a>. Go to stable-diffusion-webui\ldm_patched\modules and replace the files there.<ul><li>When used at strength 1, some artifacting occurs for certain prompts in Forge</li></ul>Training settings:DoRA training required updating the lycoris submodule:<a target="_blank" rel="ugc" href="https://github.com/bmaltais/kohya_ss/issues/2589#issuecomment-2171903484">https://github.com/bmaltais/kohya_ss/issues/2589#issuecomment-2171903484</a>Kohya training toml<pre><code>bucket_no_upscale = true
bucket_reso_steps = 256
cache_latents = true
cache_latents_to_disk = true
caption_extension = ".txt"
clip_skip = 2
dynamo_backend = "no"
enable_bucket = true
epoch = 30
full_bf16 = true
gradient_accumulation_steps = 1
gradient_checkpointing = true
huber_c = 0.1
huber_schedule = "snr"
learning_rate = 1.0
logging_dir = "E:/work/LoRa_work/logging"
loss_type = "l2"
lr_scheduler = "cosine"
lr_scheduler_args = []
lr_scheduler_num_cycles = 1
lr_scheduler_power = 1
max_bucket_reso = 2048
max_data_loader_n_workers = 0
max_grad_norm = 1
max_timestep = 1000
max_token_length = 225
max_train_epochs = 30
max_train_steps = 3395
metadata_author = "motimalu"
min_bucket_reso = 512
min_snr_gamma = 5
mixed_precision = "bf16"
multires_noise_discount = 0.3
multires_noise_iterations = 6
network_alpha = 16
network_args = [ "preset=full", "conv_dim=1", "conv_alpha=1", "rank_dropout=0",
"bypass_mode=False", "dora_wd=True", "module_dropout=0", "use_tucker=False",
"use_scalar=False", "rank_dropout_scale=False", "algo=locon", "train_norm=False",]
network_dim = 32
network_module = "lycoris.kohya"
no_half_vae = true
noise_offset_type = "Multires"
optimizer_args = []
optimizer_type = "Prodigy"
output_dir = "D:/model_output"
output_name = "pony_color_theory_dora_v1"
pretrained_model_name_or_path =
"C:/workspace/webui_forge_cu121_torch21/webui/models/Stable-diffusion/ponyDiffusionV6XL_v6Start
WithThisOne.safetensors"
prior_loss_weight = 1
resolution = "1024,1024"
sample_every_n_epochs = 10
sample_prompts = "D:/model_output\\prompt.txt"
sample_sampler = "euler_a"
save_every_n_epochs = 30
save_model_as = "safetensors"
save_precision = "bf16"
seed = 339491249
text_encoder_lr = 1
train_batch_size = 6
train_data_dir = "C:/data/color_theory"
unet_lr = 1
xformers = true</code></pre>

Files with SHA256: 8b206c4d17981c956182925060b5b7fbe4d372406437b6633f8193653250ffb7