update doc

configs/caching/adacache/wan_i2v_ada.json

+{
+    "infer_steps": 40,
+    "target_video_length": 81,
+    "target_height": 480,
+    "target_width": 832,
+    "self_attn_1_type": "flash_attn3",
+    "cross_attn_1_type": "flash_attn3",
+    "cross_attn_2_type": "flash_attn3",
+    "seed": 442,
+    "sample_guide_scale": 5,
+    "sample_shift": 3,
+    "enable_cfg": true,
+    "cpu_offload": false,
+    "feature_caching": "Ada"
+}

docs/EN/source/method_tutorials/cache.md

@@ -18,6 +18,7 @@ In actual effect, TeaCache achieves significant acceleration while ensuring gene
 | Single H200 inference time: 58s | Single H200 inference time: 17.9s |
 | ![Effect before acceleration](../../../../assets/gifs/1.gif) | ![Effect after acceleration](../../../../assets/gifs/2.gif) |
 - Speedup ratio: **3.24**
+- config：[wan_t2v_1_3b_tea_480p.json](../../../../configs/caching/teacache/wan_t2v_1_3b_tea_480p.json)
 - Reference paper: [https://arxiv.org/abs/2411.19108](https://arxiv.org/abs/2411.19108)
 
 ### TaylorSeer Cache
@@ -28,6 +29,7 @@ The core of `TaylorSeer Cache` lies in using Taylor formula to recalculate cache
 | Single H200 inference time: 57.7s | Single H200 inference time: 41.3s |
 | ![Effect before acceleration](../../../../assets/gifs/3.gif) | ![Effect after acceleration](../../../../assets/gifs/4.gif) |
 - Speedup ratio: **1.39**
+- config：[wan_t2v_taylorseer](../../../../configs/caching/taylorseer/wan_t2v_taylorseer.json)
 - Reference paper: [https://arxiv.org/abs/2503.06923](https://arxiv.org/abs/2503.06923)
 
 ### AdaCache
@@ -42,6 +44,7 @@ This allows flexible adjustment of cache strategies based on dynamic changes in
 | Single H200 inference time: 227s | Single H200 inference time: 83s |
 | ![Effect before acceleration](../../../../assets/gifs/5.gif) | ![Effect after acceleration](../../../../assets/gifs/6.gif) |
 - Speedup ratio: **2.73**
+- config：[wan_i2v_ada](../../../../configs/caching/adacache/wan_i2v_ada.json)
 - Reference paper: [https://arxiv.org/abs/2411.02397](https://arxiv.org/abs/2411.02397)
 
 ### CustomCache
@@ -56,6 +59,7 @@ This not only efficiently determines the timing of cache reuse, but also maximiz
 | Single H200 inference time: 57.9s | Single H200 inference time: 16.6s |
 | ![Effect before acceleration](../../../../assets/gifs/7.gif) | ![Effect after acceleration](../../../../assets/gifs/8.gif) |
 - Speedup ratio: **3.49**
+- config：[wan_t2v_custom_1_3b](../../../../configs/caching/custom/wan_t2v_custom_1_3b.json)
 
 
 ## How to Run

docs/ZH_CN/source/method_tutorials/cache.md

@@ -18,6 +18,7 @@
 | 单卡H200推理耗时：58s | 单卡H200推理耗时：17.9s |
 | ![加速前效果](../../../../assets/gifs/1.gif) | ![加速后效果](../../../../assets/gifs/2.gif) |
 - 加速比为：**3.24**
+- config：[wan_t2v_1_3b_tea_480p.json](../../../../configs/caching/teacache/wan_t2v_1_3b_tea_480p.json)
 - 参考论文：[https://arxiv.org/abs/2411.19108](https://arxiv.org/abs/2411.19108)
 
 ### TaylorSeer Cache
@@ -28,6 +29,7 @@
 | 单卡H200推理耗时：57.7s | 单卡H200推理耗时：41.3s |
 | ![加速前效果](../../../../assets/gifs/3.gif) | ![加速后效果](../../../../assets/gifs/4.gif) |
 - 加速比为：**1.39**
+- config：[wan_t2v_taylorseer](../../../../configs/caching/taylorseer/wan_t2v_taylorseer.json)
 - 参考论文：[https://arxiv.org/abs/2503.06923](https://arxiv.org/abs/2503.06923)
 
 ### AdaCache
@@ -42,6 +44,7 @@
 | 单卡H200推理耗时：227s | 单卡H200推理耗时：83s |
 | ![加速前效果](../../../../assets/gifs/5.gif) | ![加速后效果](../../../../assets/gifs/6.gif) |
 - 加速比为：**2.73**
+- config：[wan_i2v_ada](../../../../configs/caching/adacache/wan_i2v_ada.json)
 - 参考论文：[https://arxiv.org/abs/2411.02397](https://arxiv.org/abs/2411.02397)
 
 ### CustomCache
@@ -56,6 +59,7 @@
 | 单卡H200推理耗时：57.9s | 单卡H200推理耗时：16.6s |
 | ![加速前效果](../../../../assets/gifs/7.gif) | ![加速后效果](../../../../assets/gifs/8.gif) |
 - 加速比为：**3.49**
+- config：[wan_t2v_custom_1_3b](../../../../configs/caching/custom/wan_t2v_custom_1_3b.json)
 
 
 ## 使用方式

scripts/cache/run_wan_t2v_tea.sh

@@ -32,7 +32,7 @@ python -m lightx2v.infer \
 --model_cls wan2.1 \
 --task t2v \
 --model_path $model_path \
---config_json ${lightx2v_path}/configs/caching/teacache/wan_t2v_1_3b.json \
+--config_json ${lightx2v_path}/configs/caching/teacache/wan_t2v_1_3b_tea_480p.json \
 --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage." \
 --negative_prompt "镜头晃动，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" \
 --save_video_path ${lightx2v_path}/save_results/output_lightx2v_wan_t2v_tea.mp4