refine code

examples/wanvideo/model_inference/Wan2.2-I2V-A14B.py

@@ -22,7 +22,7 @@ dataset_snapshot_download(
     allow_file_pattern=["data/examples/wan/cat_fightning.jpg"]
 )
 input_image = Image.open("data/examples/wan/cat_fightning.jpg").resize((832, 480))
-# Text-to-video
+
 video = pipe(
     prompt="Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage.",
     negative_prompt="色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走",

examples/wanvideo/model_inference/Wan2.2-T2V-A14B.py

@@ -1,9 +1,6 @@
 import torch
 from diffsynth import save_video
 from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
-from modelscope import snapshot_download
-
-snapshot_download("Wan-AI/Wan2.2-T2V-A14B", local_dir="models/Wan-AI/Wan2.2-T2V-A14B")
 
 
 pipe = WanVideoPipeline.from_pretrained(

examples/wanvideo/model_inference/Wan2.2-TI2V-5B.py

@@ -10,7 +10,7 @@ pipe = WanVideoPipeline.from_pretrained(
     model_configs=[
         ModelConfig(model_id="Wan-AI/Wan2.2-TI2V-5B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
         ModelConfig(model_id="Wan-AI/Wan2.2-TI2V-5B", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu"),
-        ModelConfig(model_id="Wan-AI/Wan2.2-TI2V-5B", origin_file_pattern="Wan2.2_VAE.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="Wan-AI/Wan2.2-TI2V-5B", origin_file_pattern="Wan2.2_VAE.pth", offload_device="cpu"),
     ],
 )
 pipe.enable_vram_management()