<h2 id="general-recommendation-npxjo2678">General recommendation</h2><ul><li>These are finetuned on a v2 model. They work also with AnimateLCM but don't work with v3 models</li><li>Animatediff v3 adapter lora is recommended regardless they are v2 models</li><li>They are trained on 16 frames, so the motion won't be flawless on longer inference.</li><li>If you want more motion try incrasing the scale multival (e.g. to 1.2)</li><li>I recommend using smaller starting resolution (like 512x320), then upscale.</li><li>All motion LoRAs were trained on 3:2 aspect ratio (576x384) so I recommend using this or close to this AR during inference</li><li>I recommend using IP-Adapter, however it reduces the effect of the mLORAs, so play with the strength. "Ease in out" weight type is a good starting point.</li></ul>

Files with SHA256: 012bd1e94b02fe24bf49e69a78c2beaf20214cd02b3e134bfe22b833233da3fc