This is <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1">SVD XT 1.1</a> trained using <a target="_blank" rel="ugc" href="https://github.com/pixeli99/SVD_Xtend">SVD_Xtend</a> from EP1-7 of "Classroom of the Elite" (512x256).Usage:<ol><li>Rename `svdXT11AnimeExp_svdXt11AnimeV10.safetensors` to `diffusion_pytorch_model.safetensors`.</li><li>Replace `unet/diffusion_pytorch_model.safetensors` of SVD XT 1.1</li><li>Run using <a target="_blank" rel="ugc" href="https://huggingface.co/docs/diffusers/using-diffusers/svd">official SVD diffusers </a>(or <a target="_blank" rel="ugc" href="https://github.com/pixeli99/SVD_Xtend/blob/main/infer_svd.ipynb">infer_svd.ipynb by pixeli99</a> used for <a target="_blank" rel="ugc" href="https://pastebin.com/Kk24WWvG">comparison</a>).</li></ol>Note: Small dataset for SVD, NO significantly improve so "exp" experimental. civitai 1st SVD 1.1 XT Fine-tune.Dataset processing: From all EP, all similar frames was removed.

Files with SHA256: 9b7f0f1665f2a54419d9da400cce954dd3eb3bf0aac021a3c9cb47c33511f18e