support teacache in wan

examples/wanvideo/README.md

@@ -31,6 +31,8 @@ Put sunglasses on the dog.
 
 https://github.com/user-attachments/assets/272808d7-fbeb-4747-a6df-14a0860c75fb
 
+[TeaCache](https://github.com/ali-vilab/TeaCache) is supported in both T2V and I2V models. It can significantly improve the efficiency. See [`./wan_1.3b_text_to_video_accelerate.py`](./wan_1.3b_text_to_video_accelerate.py).
+
 ### Wan-Video-14B-T2V
 
 Wan-Video-14B-T2V is an enhanced version of Wan-Video-1.3B-T2V, offering greater size and power. To utilize this model, you need additional VRAM. We recommend that users adjust the `torch_dtype` and `num_persistent_param_in_dit` settings to find an optimal balance between speed and VRAM requirements. See [`./wan_14b_text_to_video.py`](./wan_14b_text_to_video.py).

examples/wanvideo/wan_1.3b_text_to_video_accelerate.py

@@ -0,0 +1,34 @@
+import torch
+from diffsynth import ModelManager, WanVideoPipeline, save_video, VideoData
+from modelscope import snapshot_download
+
+
+# Download models
+snapshot_download("Wan-AI/Wan2.1-T2V-1.3B", local_dir="models/Wan-AI/Wan2.1-T2V-1.3B")
+
+# Load models
+model_manager = ModelManager(device="cpu")
+model_manager.load_models(
+    [
+        "models/Wan-AI/Wan2.1-T2V-1.3B/diffusion_pytorch_model.safetensors",
+        "models/Wan-AI/Wan2.1-T2V-1.3B/models_t5_umt5-xxl-enc-bf16.pth",
+        "models/Wan-AI/Wan2.1-T2V-1.3B/Wan2.1_VAE.pth",
+    ],
+    torch_dtype=torch.bfloat16, # You can set `torch_dtype=torch.float8_e4m3fn` to enable FP8 quantization.
+)
+pipe = WanVideoPipeline.from_model_manager(model_manager, torch_dtype=torch.bfloat16, device="cuda")
+pipe.enable_vram_management(num_persistent_param_in_dit=None)
+
+# Text-to-video
+video = pipe(
+    prompt="纪实摄影风格画面，一只活泼的小狗在绿茵茵的草地上迅速奔跑。小狗毛色棕黄，两只耳朵立起，神情专注而欢快。阳光洒在它身上，使得毛发看上去格外柔软而闪亮。背景是一片开阔的草地，偶尔点缀着几朵野花，远处隐约可见蓝天和几片白云。透视感鲜明，捕捉小狗奔跑时的动感和四周草地的生机。中景侧面移动视角。",
+    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",
+    num_inference_steps=50,
+    seed=0, tiled=True,
+    # TeaCache parameters
+    tea_cache_l1_thresh=0.05, # The larger this value is, the faster the speed, but the worse the visual quality.
+    tea_cache_model_id="Wan2.1-T2V-1.3B", # Choose one in (Wan2.1-T2V-1.3B, Wan2.1-T2V-14B, Wan2.1-I2V-14B-480P, Wan2.1-I2V-14B-720P).
+)
+save_video(video, "video1.mp4", fps=15, quality=5)
+
+# TeaCache doesn't support video-to-video