<h1 id="wan-14b-wallace-and-gromit-style-lora-k6vox5zb3">Wan 14B Wallace and Gromit style LoRA</h1><h2 id="inference-9vnp07kfn">Inference</h2>Trigger words: walgro styleStrength: 0.8-1.2Prompt examples: You can find prompt examples on my HF page here: <a target="_blank" rel="ugc" href="https://huggingface.co/Cseti/wan-14b-wallace_and_gromit-style-lora-v1">https://huggingface.co/Cseti/wan-14b-wallace_and_gromit-style-lora-v1</a><h2 id="trainig-details:-2075ho2ci">Trainig details:</h2>Trained only on videos.<ul><li>dataset: 87 videos 570x405 81,65,33 frame videos</li><li>steps: 15660</li><li>LR: 8e-5</li><li>optimizer: AdamW8bitKahan</li><li>rank: 32</li><li>batch size: 1</li><li>gradient accumulation steps: 1</li></ul>For training I used the diffusion-pipe repo.Important: 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 Wallace and Gromit, which 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.

Files with SHA256: 90082ec70f8bab295442a131e94e0311d9394584bb32e88353486fa383931691