Wan Video ComfyUI (T2V & I2V)

压缩包包含两个用于运行的 ComfyUI 工作流：

1. Wan 2.1 T2V：wan2-t2v-upscale-v1.json

2. Wan 2.1 I2V：wan2-i2v-upscale-v1.json

参考输出：

在配备 RTX4060 8GB 显存 + 32GB 内存的设备上，I2V：提示词执行耗时 2807.42 秒

在配备 RTX5080 笔记本 16GB 显存 + 32GB 内存的设备上，I2V：提示词执行耗时 1401.00 秒

要求：

模型：

• wan2.1-t2v-14b-Q3_K_M.gguf（T2V）放置于：ComfyUI\models\unet
  https://huggingface.co/city96/Wan2.1-T2V-14B-gguf/resolve/main/wan2.1-t2v-14b-Q3_K_M.gguf

• wan2.1-i2v-14b-480p-Q3_K_M.gguf（I2V）放置于：ComfyUI\models\unet
  https://huggingface.co/city96/Wan2.1-I2V-14B-480P-gguf/resolve/main/wan2.1-i2v-14b-480p-Q3_K_M.gguf

• wan2.1_t2v_1.3B_fp16.safetensors（T2V 模型，用于工作流 "v2v"）放置于：ComfyUI\models\diffusion_models
  https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_t2v_1.3B_fp16.safetensors

• umt5-xxl-encoder-Q4_K_M.gguf（CLIP）放置于：ComfyUI\models\text_encoders
  https://huggingface.co/city96/umt5-xxl-encoder-gguf/resolve/main/umt5-xxl-encoder-Q4_K_M.gguf

• umt5_xxl_fp8_e4m3fn_scaled.safetensors（CLIP，若修改工作流 "v2v" 可使用此模型）放置于：ComfyUI\models\text_encoders
  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）放置于：ComfyUI\models\vae
  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）放置于：ComfyUI\models\clip_vision
  https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/clip_vision/clip_vision_h.safetensors

• RealESRGAN_x2plus.pth（超分模型）放置于：ComfyUI\models\upscale_models
  https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth

ComfyUI 节点：

• rgthree-comfy
• ComfyUI-KJNodes
• ComfyUI-VideoHelperSuite
• ComfyUI-Frame-Interpolation
• Comfyui-Memory_Cleanup（若修改工作流则非必需）

若您的硬件性能更强，可选择更高量化级别的模型。