This workflow uses WAN SCAIL for movement and Flux Klein for the first frame generation. While this is more efficient than the previous version, I still recommend a 5090 and good amount of RAM to run it efficiently. WAN Models diffusion models:https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/resolve/main/SCAIL/Wan21-14B-SCAIL-preview_fp8_e4m3fn_scaled_KJ.safetensors vae: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors text encoder: https://huggingface.co/Kijai/WanVideo_comfy/blob/main/umt5-xxl-enc-fp8_e4m3fn.safetensors clip_vision_h.safetensors: https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensorsspeed lora: https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v/resolve/main/loras/Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors Detection models (put in models/detection): vitpose_h_wholebody: https://huggingface.co/Kijai/vitpose_comfy/tree/main/onnx yolov10m:https://huggingface.co/Wan-AI/Wan2.2-Animate-14B/blob/main/process_checkpoint/det/yolov10m.onnx Klein (ask for access) Diffusion_models: https://huggingface.co/black-forest-labs/FLUX.2-klein-9b-fp8/blob/main/flux-2-klein-9b-fp8.safetensorsif no access: https://modelscope.cn/models/black-forest-labs/FLUX.2-klein-9b-fp8/file/view/master/flux-2-klein-9b-fp8.safetensors?status=2