<h3 id="this-lora-recreates-the-3d-animation-style-of-kittyevil.-hpvyv5m9w">This lora recreates the 3D animation style of <a target="_blank" rel="ugc" href="https://x.com/kittyyevil">KittyEvil</a>.</h3>No special trigger or prompting required, simply add strength until desired look is achieved.If you have questions, or want to commission a lora, join the <a target="_blank" rel="ugc" href="https://discord.gg/9Sd6aUEV9n">discord</a>.<h3 id="recommended-settings:-586lijatj">Recommended Settings:</h3>Resolution: This lora was trained on 512px images of assorted aspect ratios. It should work on generations of any resolution.Frames: This was trained with images only, so it shouldn't matter how many frames you generate. Feel free to try out a 1-frame preview to see if you need to adjust the strength before continuing.Steps: 10 worked for me, but please keep reading about upscaling.Upscaling: Hunyuan gives better results when running a second upscale pass, it generally cleans up motion and adds better detail. It can help fix things that didn't follow the prompt in your initial gen, such as moving/talking mouths even when you have "closed mouth" in the prompt. I like to do a 1.5x or 2x upscale once I'm satisfied with how my initial video looks.<h3 id="transparency:-jdf505f59">Transparency:</h3>This lora was trained on 35 images. It took $0.75 worth of Runpod credit on an L40S. I will never ask for your buzz or donations, but I will ask you to leave feedback in the comments so I can continue to improve my work.

Files with SHA256: 4c4fd6c94156faa6e7fdc21eb91100e0ae55ddc8bfba2d12cae93f64719ae428