<p>These LoRAs are trained for Wan2.1, and will work there, but my primary use case is with autoregressive distillations of Wan2.1 such as Longlive, StreamDiffusionV2, and Krea Real Time.<br /><br />If you want to try this LoRA in real time, you can do so with the <strong>open source</strong> tool <a target="_blank" rel="ugc" href="https://github.com/daydreamlive">Daydream Scope</a>. I am one of the developers on the team. All of the demos here were created with Scope - 4090 or 5090 required, though Runpod templates are available, and remote inference under construction. <br /><a rel="ugc" href="https://daydream.live/real-time-video-generation-control">Real-time VACE writeup</a> <br />Scope/Real-Time VACE tutorial:</p><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/hYrKqB5xLGY" start="0"></iframe></div><p><br /><br />The datasets for these were chosen with the causal nature of autoregressive models in mind, and that has been where my testing has taken place - you can consider these experimental of course. <br /></p>

Daydream Scope Wan LoRAs

<p>MASSIVE shoutout to the ULTRA powerful @RalFinger - I generated synthetic data using his <a target="_blank" rel="ugc" href="https://civitai.com/models/179353/acid-slime-bubbles-fluxsdxlpony15">acidzlime LoRA</a> , and I have plans to repeat this process with other styles. His LoRAs are the best LoRAs, hands down.</p>

Files with SHA256: a4028744227d95ca03eb0db1a0906dc34d84356d44ab4778348ceb35661ec94a