<h2 id="model-description-vi4e31l8q"><strong>Model Description</strong></h2><p>This repository contains a collection of basic camera motion LoRAs finetuned on Animatediff v2 models. The training process utilized Kijai's <a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-ADMotionDirector"><strong><u>AnimateDiff Motion Director ComfyUI nodes</u></strong></a>. These LoRAs have been tested exclusively in ComfyUI with Kosinkadink's <a target="_blank" rel="ugc" href="https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved"><strong><u>AnimateDiff-Evolved nodes</u></strong></a>, however they may be compatible with other AnimateDiff implementations.</p><h2 id="how-to-use-kgdh46i4m"><strong>How to use</strong></h2><ul><li><p>copy the motion lora files into your "ComfyUI\models\animatediff_motion_lora" folder</p></li><li><p>Use the "Load Animatediff LoRA" node</p></li></ul><h2 id="general-recommendation-5jyz6703s">General recommendation</h2><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 work with SD 1.5 checkpoints</p></li><li><p>Animatediff v3 adapter LoRA is recommended regardless they are v2 models</p></li><li><p>If you want more motion try increasing the scale multival</p></li><li><p>I recommend using the above Base AR (Aspect ratio) for inference however they might work with other ARs too</p></li><li><p>Try playing with the strength of</p><ul><li><p>motion LoRA</p></li><li><p>scale multival</p></li><li><p>v3_adapter lora</p></li></ul><p>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><li><p>If you chain multiple motion LoRAs, I recommend lowering their strength, otherwise, the quality of the result will be worse</p></li></ul><h2 id="example-workflow-rszzvokoe">Example workflow</h2><p><span style="color:rgb(193, 194, 197)">You will find an example workflow here: </span><a target="_blank" rel="ugc" href="https://civarchive.com/articles/6702￼With">https://civarchive.com/articles/6702<br /><span style="color:rgb(193, 194, 197)">With</span></a><span style="color:rgb(193, 194, 197)"> this you will be able to recreate this animation: </span><a target="_blank" rel="ugc" href="https://civarchive.com/images/24310950">https://civarchive.com/images/24310950</a></p><h2 id="details-tp6dhgaet"><strong>Details</strong></h2><h3 id="zooming-in-(16-frame)-gbvmzv4m7"><strong>Zooming in (16 frame)</strong></h3><ul><li><p>recommended strength: 0.7-1.0</p></li></ul><h3 id="zooming-in-(32-frame)-h2rf6s1ff"><strong>Zooming in (32 frame)</strong></h3><ul><li><p>this is an experimental motion LoRA trained on 32 frames so it can be used with higher context length than 16.</p></li><li><p>recommended strength: 0.7-0.85</p></li></ul><h3 id="zooming-out-lednegq2w"><strong>Zooming out</strong></h3><ul><li><p>recommended strength: 0.7-1.0</p></li></ul><h3 id="lateral-(horizontal)-left-qi3riiuqy"><strong>Lateral (horizontal) left</strong></h3><ul><li><p>recommended strength: 0.7-1.0</p></li></ul><h3 id="lateral-(horizontal)-right-j14ilergp"><strong>Lateral (horizontal) right</strong></h3><ul><li><p>recommended strength: 0.7-1.0</p></li></ul><h3 id="crane-(vertical)-up-12jz05aq2"><strong>Crane (vertical) up</strong></h3><ul><li><p>recommended strength: 0.7-1.0</p></li></ul><h3 id="crane-(vertical)-down-4ruwc3kqj"><strong>Crane (vertical) down</strong></h3><ul><li><p>recommended strength: 0.7-1.0</p></li></ul><p></p>

Cseti's Basic camera motion LoRAs sd15-ad2-v1

1600_cseti_9213319_camera-lateral_left-10vid_mv2.safetensors

Lateral left (16fr)

Crane down (16fr)

Files with SHA256: f7c660048062a0d87ea05832439a4ed5c85ea9de8127e2132d0d07ac12faee26