Wan Animated ComfyUI

압축 파일에는 다음을 실행하기 위한 1개의 ComfyUI 워크플로우가 포함되어 있습니다:

wan2.2-Animate.json

참조 출력:

RTX4060 8GB vRAM + 32GB RAM(얼굴 교체 비활성화): 101fps x 496x896: 프롬프트 실행 시간 00:14:24

RTX4070Ti Super 16GB vRAM + 32GB RAM: 141fps x 560x992: 프롬프트 실행 시간 00:11:36

RTX5080 랩톱 16GB vRAM + 64GB RAM: 141fps x 560x992: 프롬프트 실행 시간 00:12:44

요구 사항:

모델:

• Wan2.2-Animate-14B(GGUF): ComfyUI\models\unet에 저장

https://huggingface.co/QuantStack/Wan2.2-Animate-14B-GGUF/resolve/main/Wan2.2-Animate-14B-Q6_K.gguf

다른 버전과 동일:

• umt5_xxl_fp8_e4m3fn_scaled.gguf (CLIP): ComfyUI\models\text_encoders에 저장

https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors

• wan_2.1_vae.safetensors (VAE): ComfyUI\models\vae에 저장

https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors

• clip_vision_h.safetensors (CLIP_VISION): ComfyUI\models\clip_vision에 저장

https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors

• 선택적 LoRAs: ComfyUI\models\loras\에 저장

https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors

https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/LoRAs/Wan22_relight/WanAnimate_relight_lora_fp16.safetensors

/model/1789152

/model/1434650

ComfyUI 노드:

• rgthree-comfy

• ComfyUI-KJNodes

• ComfyUI-VideoHelperSuite

• ComfyUI-Frame-Interpolation

• ComfyUI-GGUF

• comfyui_controlnet_aux

• comfyui-custom-scripts

• comfyui-impact-pack

• comfyui-impact-subpack

• comfyui-rmbg

• comfyui-segment-anything-2

• Comfyui-Memory_Cleanup