So... this one is broken but i have spent too much time on it already, hence its release as-is. This is a "style" LoRA to bring some realistic stuff to ANIMA, based on UnNamedIXL but this is less than enough.But after 4 trainings on different dataset (with previous version re-used as based of further training), some merging of epochs, and an analysis of the effect of specific DiT blocks (1, 14 and 16 for the curious), i am stopping for now.I am using "photorealistic, realistic face" in the prompt and "uncanny, painting, illustration" in the negative to mitigate ANIMA tendencies to shun realistic results, but there was no trigger words built-in the datasets (you can check the showcase picture, it is really a hit or miss situation 😭)<hr />Legal<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:16px">The CircleStone Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

UnNamed for ANIMA

Posted on Civitai, upload found elsewhere are FORBIDDEN and done without the author permission.

Files with SHA256: 165b17e8b4d695ac2b097482096e8fd7d889fa94d4a17f69b9845758733a2098