<h1 id="ltxv-13b-shinkai-anime-style-lora-4khupldgk">LTXV 13b Shinkai anime style lora</h1><h2 id="inference-w46bht6tf">Inference</h2>Please note that the distilled model might not work properly with this lora. Based on my tests it might have a weaker effect or you might notice some visual artifacts.For inference I used ComfyUI.Trigger words: sh1nka1 styleStrength: 0.8-1.0<h2 id="trainig-details:-d8lh6b4rm">Trainig details:</h2>Trained only on videos.<ul><li>dataset: 192 videos 864x480x41</li><li>steps: 58000</li><li>LR: 2e-4</li><li>optimizer: adamw</li><li>scheduler: contant</li><li>rank: 128</li><li>batch size: 1</li><li>gradient accumulation steps: 1</li></ul>For training I used the official <a target="_blank" rel="ugc" href="https://github.com/Lightricks/LTX-Video-Trainer">LTX-Video Trainer</a> repo.<h2 id="important-notes:-qqfqmi95p">Important Notes:</h2>This LoRA is created as part of a fan project for research purposes only and is not intended for commercial use. It is based on the movies called "Tenki no Ko" and "Kimi no Na wa" that are protected by copyright. Users utilize the model at their own risk. Users are obligated to comply with copyright laws and applicable regulations. The model has been developed for non-commercial purposes, and it is not my intention to infringe on any copyright. I assume no responsibility for any damages or legal consequences arising from the use of the model.<h2 id="acknowledgement-qjzdnr1co">Acknowledgement</h2>Special thanks to <a target="_blank" rel="ugc" href="https://github.com/Lightricks/LTX-Video">Lightricks Team</a> for making this available for the community for free!

Files with SHA256: 84f2067d6811547c3b3c934e824350edd1347351f2e5750711fd00178cfb0ea5