Trained on Anima Base v1 using the <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/2850290?fileId=2736406">example dataset</a> and the <a target="_blank" rel="ugc" href="https://github.com/sorryhyun/anima_lora">anima_lora</a> script with default settings. Trigger word: <code>@greg rutkowski</code> Now that I've figured out how to use the training scripts, I realize v3 was way overcooked. Please use v4 instead!<hr /><h3 id="v3-is-deprecated">v3 is deprecated</h3>This is my first LoRA, and there are a few known issues:<ul><li>I have no idea what I'm doing, or why the angel's halo looks that. But two halos are better than one, no?</li><li>Your gens might look underfit or overfit, depending on the seed.</li><li>I have only tested this LoRA alone with Anima Base. If you use a fine-tune or other LoRAs, your mileage may vary.</li></ul>If those are not deal breakers for you, go ahead and download this. Be sure to share your masterpieces and feedback :)Usage tip: you can reduce errors by being highly specific with your prompts. In the Frieren example, I used <code>from side</code> to prevent the character's torso from turning the wrong way, and <code>centered around the head of her staff</code> to force the staff in the correct orientation.

Files with SHA256: fc799db1ed7bd3012e4aa093f9eface0ca4037be29587d24a82213c84bdf6374