diff --git a/README.md b/README.md
index 92efaa1..b7f4293 100644
--- a/README.md
+++ b/README.md
@@ -23,7 +23,7 @@ WanGP supports the Wan (and derived models), Hunyuan Video and LTV Video models
 ### August 8 2025: WanGP v7.74 - Qwen Rebirth part 2
 Added support for Qwen Lightning lora for a 8 steps generation (https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-8steps-V1.0.safetensors). Lora is not normalized and you can use a multiplier around 0.1.
 
-Mag Cache support for all the Wan2.2 models
+Mag Cache support for all the Wan2.2 models Don't forget to set guidance to 1 and 8 denoising steps , your gen will be 7x faster !
 
 ### August 8 2025: WanGP v7.73 - Qwen Rebirth
 Ever wondered what impact not using Guidance has on a model that expects it ? Just look at Qween Image in WanGP 7.71 whose outputs were erratic. Somehow I had convinced myself that Qwen was a distilled model. In fact Qwen was dying for a negative prompt. And in WanGP 7.72 there is at last one for him.
diff --git a/assets/comp_effic.png b/assets/comp_effic.png
deleted file mode 100644
index ea0e3b2..0000000
Binary files a/assets/comp_effic.png and /dev/null differ
diff --git a/assets/data_for_diff_stage.jpg b/assets/data_for_diff_stage.jpg
deleted file mode 100644
index af98046..0000000
Binary files a/assets/data_for_diff_stage.jpg and /dev/null differ
diff --git a/assets/i2v_res.png b/assets/i2v_res.png
deleted file mode 100644
index fb13d61..0000000
Binary files a/assets/i2v_res.png and /dev/null differ
diff --git a/assets/logo.png b/assets/logo.png
deleted file mode 100644
index 0c55854..0000000
Binary files a/assets/logo.png and /dev/null differ
diff --git a/assets/t2v_res.jpg b/assets/t2v_res.jpg
deleted file mode 100644
index 6a58388..0000000
Binary files a/assets/t2v_res.jpg and /dev/null differ
diff --git a/assets/vben_vs_sota.png b/assets/vben_vs_sota.png
deleted file mode 100644
index 4f09de6..0000000
Binary files a/assets/vben_vs_sota.png and /dev/null differ
diff --git a/assets/video_dit_arch.jpg b/assets/video_dit_arch.jpg
deleted file mode 100644
index a13e499..0000000
Binary files a/assets/video_dit_arch.jpg and /dev/null differ
diff --git a/assets/video_vae_res.jpg b/assets/video_vae_res.jpg
deleted file mode 100644
index e1bfb11..0000000
Binary files a/assets/video_vae_res.jpg and /dev/null differ
diff --git a/shared/utils/cammmaster_tools.py b/shared/utils/cammmaster_tools.py
index 6e255a0..b93ebba 100644
--- a/shared/utils/cammmaster_tools.py
+++ b/shared/utils/cammmaster_tools.py
@@ -40,7 +40,7 @@ def get_relative_pose(cam_params):
 def get_camera_embedding(cam_type, num_frames=81):
 
     # load camera
-    tgt_camera_path = "wan/camera_extrinsics.json"
+    tgt_camera_path = "models/wan/camera_extrinsics.json"
     with open(tgt_camera_path, 'r') as file:
         cam_data = json.load(file)