Base on my previous experience, I've made a new lora(still using civitai's trainer) with very minor changes to learn and figure how it changes the result, it's still a LONG way to go...What does it do? [COLOR+<s>STYLE</s>] It generates images with the PRIMARY color hue. It also ends up with a less obvious style if left unprompted. At higher weights, you may often see portraits, shadowed face and moles on face. Skin may have pink or blue tint depending on the color theme.What are the triggers? The main color triggers are: Red, Blue, Yellow, Black, White. The colors can be customized by playing around with the combination, the position of the prompt affects the priority of the color, the color in front will be prioritized. Check my prompts for examples. If you use other colors, their hue may shift closer to PRIMARY. Optional add-on prompts: ,1girl, solo, portrait, close-up, Simple Background, Gradient background *There is also a PRIMARY prompt BUT I still don't know what it does...😢 The only thing I learn is that if no color is prompt, it will give a slight PRIMARY color. Same thing, if anyone know, lmk.Recommended Weight Depending on the models used, the weight is good from 0.5 to 1.2. On average, 0.5 to 1.0 have a more stable result.Recommended model: Any model will work well with the colors, overall it works best with colorful/bright models. RE-LIVE_VIVIDPAST makes the colors POP if you want a burst of colors.<h3 id="core-color-series:-on3ortq52">CORE Color Series:</h3><ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/445178/cmyk-core">CMYK-CORE</a> - Cyan, Magenta, Yellow, Black, White.</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/454486/primary-core">PRIMARY-CORE</a> - Red, Blue, Yellow, Black, White.</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/530820">SECONDARY-CORE</a> - Orange, Green, Purple, Black, White.</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/606314">UMBRA-CORE</a> - Black with glow.</li></ul><hr />No rant this time, but the most important take away I learnt this time is that image quality is more important than image quantity. Keywords choices are also important. To play around more with different setting, I'll try to download Koyha-ss. (Hope I survive the learning curve.)I know there are many tutorials, but I am more of a hands-on learner, its less confusing for me to figure it out by experimenting.

PRIMARY-CORE (Red,Blue,Yellow)

This lora have quite equal color strength, the position of the prompt affects the priority of the color, the color in front will be prioritized.Strength<ol><li>Red: 3/5 ⭐️⭐️⭐️</li><li>Blue: 4/5 ⭐️⭐️⭐️⭐️</li><li>Yellow: 3/5 ⭐️⭐️⭐️</li><li>Black: 4/5 ⭐️⭐️⭐️⭐️</li><li>White: 3/5 ⭐️⭐️⭐️</li><li>Style: 3/5 ⭐️⭐️⭐️</li></ol>Not sure if I'll refine it, I may retrain it when I have nothing to do.

Files with SHA256: 2403c572dbe5a1a273416e2606d448a6e2ae03f8db12aec569aa5278dbb09333