This LoRA was built to perfectly replicate the Nijijourney style.The Dataset contains around 300-320 images (depending on the base model).Helpful Tags:<ul><li><code>warm theme</code> (Highly recommended)</li><li><code>cold theme</code></li><li><code>European</code></li><li><code>Asian</code></li><li><code>Mature</code></li><li><code>Young</code></li></ul>(All of these tags were used when building the dataset to make it as versatile as possible.)Recommended Weight:If it's your main/only style LoRA: 0.8 – 1.2If you're mixing it with other style LoRAs: 0.6 – 0.8Generation Tips:<ul><li>The lower the CFG, the better. I recommend keeping your CFG between 2 and 5 (3.5 seems to be the sweet spot for a lot of checkpoints).</li><li>You'll get the best results with samplers that pull out fine details (like DPM++ 2M).</li><li>If you want it to stick to the style as closely as possible, use NoobAI-based checkpoints that actually understand the <code>oil painting \(medium\)</code> tag. Good examples are NoobAI EPS 1.1, Chenkin Noob XL, and similar models.</li></ul><a target="_blank" rel="ugc" href="https://tensor.art/models/971506550910799275/Niji-Solace-ILNAI-v1.0">tensor art</a>

Niji Solace | Style | IL/NAI/Anima

The dataset has been expanded to almost 400 images and further cleaned up.The style is more consistent now, but there's a slight overfitting toward darker skin tones, so I'd recommend using the <code>pale skin</code> tag more often.6000 steps 4 batchUNET_LR 0.0001 TE_LR 0.00001Optimizer: AdamW8bit Training model: Illustrious V2.0 Stable

Files with SHA256: 94841c6340a8c4614d19dc9354914f379accc5675081856dd25f3c8d7790992a