Fed up? Models too big filling up your storage, nodes a nightmare to install with constant errors, GPU RAM always running out and crashing halfway? RunningHub solves it all! With RTX 4090 24G VRAM in the cloud, all models and nodes pre-integrated, just sign up with Gmail to get 1000 free credits and run your workflow instantly — smooth, fast, and hassle-free!Workflow Link:<a target="_blank" rel="ugc" href="https://www.runninghub.ai/workflow/1967799412284096514?inviteCode=rh-v1153">https://www.runninghub.ai/workflow/1967799412284096514?inviteCode=rh-v1153</a>Using the VACE model (KJ scale version) released by the Fun team, I built a first-and-last-frame workflow, and the results are decent. For the Lightx2v model, version 2.1 was used.It’s recommended to write enhancement keywords for the desired effect to go along with it.Kj version Fun vace:<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/VACE">https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/VACE</a>Wan2.1-T2V-14B-StepDistill-CfgDistil lora<a target="_blank" rel="ugc" href="https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill-Lightx2v/tree/main/loras">https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill-Lightx2v/tree/main/loras</a>

Files with SHA256: 49cd96e9adae4a533c936a0d102546e10e74565b537e6ab905c29e1ac2d99b27