<p>This is my new set of walking motion LoRAs trained on new parameters and dataset.</p><p></p><h1 id="general-recommendation-t5aawqwus">General recommendation</h1><ul><li><p>These are finetuned on a v2 model. They work also with AnimateLCM but don't work with v3 models</p></li><li><p>They are all trained on 16 frames. It means most probably the motion won't be flawless for inferences above 16 frames.</p></li></ul><ul><li><p>Animatediff v3 adapter lora is recommended regardless they are v2 models</p></li></ul><ul><li><p>If you want more motion try incrasing the scale multival (e.g. to 1.2)</p></li><li><p>I recommend using 3:2 aspect ratio for inference</p></li><li><p>Try playing with the lora strength and scale multival like increasing the scale multival and lowering the lora strength.</p></li><li><p>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.</p></li></ul><p></p><h1 id="lora-specific-recommendations-wddnjdwtk">LoRA specific recommendations</h1><p></p><h2 id="walking-front-view-umzn9d1nx">Walking front view</h2><ul><li><p>Recommended keywords: front-view, walking</p></li><li><p>LoRA strength: 0.8-1.0</p></li><li><p>Scale multival / motion scale: 1.0-1.2</p></li></ul><p></p><h2 id="walking-back-view-2dsemxq7w">Walking back view</h2><ul><li><p>Recommended keywords: back-view, walking</p></li><li><p>LoRA strength: 0.8-1.0</p></li><li><p>Scale multival / motion scale: 1.0-1.2</p></li></ul><p></p><h2 id="walking-right-view-2u7okwyp7">Walking right view</h2><ul><li><p>Recommended keywords: side-view, facing right, walking</p></li><li><p>LoRA strength: 0.5-1.0</p></li><li><p>Scale multival / motion scale: 1.0-1.2</p></li></ul><p></p><h2 id="walking-left-view-ll9whkcm4">Walking left view</h2><ul><li><p>Recommended keywords: side-view, facing left, walking</p></li><li><p>LoRA strength: 0.5-1.0</p></li><li><p>Scale multival / motion scale: 1.0-1.2</p></li></ul>

Cseti's walking motion LoRAs v2

Files with SHA256: b4a47ca66cfcfd4dd09f8a2554105333457eaa8c0182e4d64bd07b016ac31ea0