<h1 id="heading-1742">Stop! These models are not for txt2img inference!</h1>Don't put them in your stable-diffusion-webui/models directory and expect to make images!<h2 id="heading-7">So what are these?</h2>These are new Modelscope based models for txt2video, optimized to produce 16:9 video compositions. They've been trained on 9,923 video clips and 29,769 tagged frames at 24 fps, 1024x576 res. Note that these are the bigger brothers to the <a target="_blank" rel="ugc" href="https://civarchive.com/models/96454/zeroscope-v2-576w-txt2video">https://civarchive.com/models/96454/zeroscope-v2-576w-txt2video</a> models. The XL models use 15.3GB of VRAM when rendering 30 fps at 1024x576.<h2 id="heading-1744">Where do they go?</h2>Drop them in the \stable-diffusion-webui\models\ModelScope\t2v folder It's imperative you rename the text2video_pytorch_<a target="_blank" rel="ugc" href="http://model.pt">model.pt</a> to .pth extension after downloading. The files must be named open_clip_pytorch_model.bin, and text2video_pytorch_model.pth<h2 id="heading-1745">Who made them? Original Source?</h2><a target="_blank" rel="ugc" href="https://huggingface.co/cerspense/zeroscope_v2_XL">https://huggingface.co/cerspense/zeroscope_v2_XL</a><h2 id="heading-1746">What else do I need?</h2>These models are specifically for use with the<a target="_blank" rel="ugc" href="https://github.com/kabachuha/sd-webui-text2video"> txt2video Auto1111 WebUI Extension</a>

Files with SHA256: b25d2b2605ea43e0447eb84b8b08ba027855569f74391ecc9a3abf283f045441