<h3 id="anima-version">Anima Version</h3>This is an experimental LoRA version trained on Anima Preview.Anima is a new DiT model focused on anime concepts. You can find it on Hugging Face at <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima">circlestone-labs/Anima · Hugging Face</a> Trigger word<pre><code>@4x0style</code></pre>Recommended strength is 1.0 Recommendation to Anima Lora Trainer I am working on <span style="background-color:rgb(26, 27, 30);color:rgb(141, 141, 143);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:14px">/ᐠ ̷ ̷𝅒 ̷‸ ̷𝅒 ̷ ᐟ\ﾉ<a target="_blank" rel="ugc" href="https://github.com/WalkingMeatAxolotl/AnimaLoraStudio">https://github.com/WalkingMeatAxolotl/AnimaLoraStudio</a>

Style - Chen bin/鬼针草 [Anima]

Trained on the Anima 1.0 base model.This version improves pantyhose rendering, but somehow at the cost of slightly less stable hands. The brushwork — coloring/shading in particular — is also a touch weaker than v2.2, so pick whichever version suits your taste. Switch to dora instead of lokr.v3.9 means the model has gone through 10 rounds of training on different configs since v2.2. T.T

Files with SHA256: 5eeebcf1afda7e3633d8f8ea37755556eb121bc5ce73864f89de54f08e55dc73