Zephyr is a stylistic LoRA trained on a highly opinionated, handpicked dataset, aiming to improve anime quality by muting the colors and exposure; increasing the detail; add a slight artistic feel to the images.The versions indicate the iteration of the dataset and the order the models were made in, and although correlated, not necessarily indicative of quality. V3 is better than V4 for example. The order in which the models are listed is a better approximation of the quality. Zephyr doesn't require trigger words, as it was trained without captions, with frozen text encoder weights, meaning that it's applying the aesthetic bias only through the UNet. Considering this, Zephyr shouldn't conflict with other LoRAs.Zephyr is currently in rapid development, so you can expect many updates. Open to criticism and suggestions.

Zephyr LoRA - Illustrous

What's new:<ul><li>Changed gradient accumulation from 32 images to 64</li><li>Tripled training time</li></ul>What's next:<ul><li>Continued trouble with meaningful updates beyond the earliest 100 or so steps. Considering increasing the rank or creating a full blown finetune, the change from 32 to 64 for batch size was decent, but obviously not it</li></ul>

Files with SHA256: 7521fa45bd60242b9f5cc8d7e83d01f08242936ce75b7777626d4b123ed0549b