From 814f68f2a79832d03a3e2f6f7675882013256ea2 Mon Sep 17 00:00:00 2001
From: Inn1917 <1475691351@qq.com>
Date: Tue, 2 Sep 2025 15:47:16 +0800
Subject: [PATCH] modify filenames

---
 README.md                        | 25 +++++++++++++------------
 code/download_checkpoints.py     |  2 +-
 code/panoramic_image_to_video.py |  2 +-
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/README.md b/README.md
index 7fe231a..0a620c1 100644
--- a/README.md
+++ b/README.md
@@ -202,16 +202,7 @@ chmod +x install.sh
 ./install.sh
 
 ```
-## 📊 GPU vram requirement
-The minimum GPU vram requirement to run our pipeline is 16g. The specific amount of GPU vram occupation under different model settings are listed below.
-| Model Name | VRAM |
-| :---------: | :----------: |
-| PanoVideoGen-480p w.o. vram management | ~40g |
-| PanoVideoGen-720p w.o. vram management | ~60g |
-| PanoVideoGen-720p-5b w.o. vram management | ~19g |
-| PanoVideoGen-480p w. vram management | ~15g |
-| PanoVideoGen-720p w. vram management | ~19g |
-| PanoVideoGen-720p-5b w. vram management | ~12g |
+
 
 ## 💫 Pretrained Models
 | Model Name | Description | Download |
@@ -222,6 +213,16 @@ The minimum GPU vram requirement to run our pipeline is 16g. The specific amount
 |PanoVideoGen-720p-5b|lora_5b.safetensors|[Link](https://huggingface.co/Skywork/Matrix-3D)|
 |PanoLRM-480p|pano_lrm_480p.pt|[Link](https://huggingface.co/Skywork/Matrix-3D)|
 
+## 📊 GPU vram requirement
+The minimum GPU vram requirement to run our pipeline is 16g. The specific amount of GPU vram occupation under different model settings are listed below.
+| Model Name | vram management on/off |VRAM |
+| :---------: | :----------: | :----------: |
+| PanoVideoGen-480p| off | ~40g |
+| PanoVideoGen-720p| off | ~60g |
+| PanoVideoGen-720p-5b| off | ~19g |
+| PanoVideoGen-480p| on | ~15g |
+| PanoVideoGen-720p| on | ~19g |
+| PanoVideoGen-720p-5b| on | ~12g |
 
 <!-- | Model Name | Drop Location |
 | :---------: | :----------: | 
@@ -301,13 +302,13 @@ torchrun --nproc_per_node ${VISIBLE_GPU_NUM} code/panoramic_image_to_video.py \
   --enable_vram_management # enable this to allow model to run on devices with 19G vram.
 ```
 
-<span id="5b">**5b model**</span> We recently developed a 5b version of our video generation model based on Wan2.2-TI2V-5b model. The 5b model achieves fast video generation as well as lower vram usage. To run the video generation with 5b model, you can now enable 5b model usage with a command line argument setting:
+<span id="5B">**5B model**</span> We recently developed a 5B version of our video generation model based on Wan2.2-TI2V-5B model. The 5B model achieves fast video generation as well as lower vram usage. To run the video generation with 5B model, you can now enable 5B model usage with a command line argument setting:
 ```bash
 VISIBLE_GPU_NUM=1
 torchrun --nproc_per_node ${VISIBLE_GPU_NUM} code/panoramic_image_to_video.py \
   --inout_dir="./output/example1"  \
   --resolution=720 \
-  --use_5b_model # enable this to generate video with light-weight 5b model.
+  --use_5b_model # enable this to generate video with light-weight 5B model.
 ```
 
 - 🏡 **Step 3: Extract 3D Scene**
diff --git a/code/download_checkpoints.py b/code/download_checkpoints.py
index e5be8f5..a94cd2e 100644
--- a/code/download_checkpoints.py
+++ b/code/download_checkpoints.py
@@ -17,7 +17,7 @@ def download_ckpt(local_dir, repo_id, filename):
         print(f"File exists already: {local_path}")
 os.makedirs("./checkpoints", exist_ok=True)
 repo_id_list = ["Ruicheng/moge-vitl","Iceclear/StableSR","Iceclear/StableSR","Skywork/Matrix-3D","Skywork/Matrix-3D","Skywork/Matrix-3D","Skywork/Matrix-3D","Skywork/Matrix-3D"]
-filename_list = ["model.pt","stablesr_turbo.ckpt","vqgan_cfw_00011.ckpt","checkpoints/text2panoimage_lora.safetensors","checkpoints/pano_lrm_480p.pt","checkpoints/pano_video_gen_480p.ckpt","checkpoints/pano_video_gen_720p.bin","checkpoints/lora_5b.safetensors"]
+filename_list = ["model.pt","stablesr_turbo.ckpt","vqgan_cfw_00011.ckpt","checkpoints/text2panoimage_lora.safetensors","checkpoints/pano_lrm_480p.pt","checkpoints/pano_video_gen_480p.ckpt","checkpoints/pano_video_gen_720p.bin","checkpoints/pano_video_gen_720p_5b.safetensors"]
 local_dir_list = ["./checkpoints/moge","./checkpoints/StableSR","./checkpoints/StableSR","./checkpoints/flux_lora","./checkpoints/pano_lrm","./checkpoints/Wan-AI/wan_lora","./checkpoints/Wan-AI/wan_lora","./checkpoints/Wan-AI/wan_lora"]
 
 N = len(repo_id_list)
diff --git a/code/panoramic_image_to_video.py b/code/panoramic_image_to_video.py
index cd7db54..78d6f77 100644
--- a/code/panoramic_image_to_video.py
+++ b/code/panoramic_image_to_video.py
@@ -342,7 +342,7 @@ def main(args):
             ],
             use_usp=True if dist.get_world_size() > 1 else False
         )
-        lora_checkpoint = os.path.abspath("./checkpoints/Wan-AI/wan-lora/lora_5b.safetensors")
+        lora_checkpoint = os.path.abspath("./checkpoints/Wan-AI/wan-lora/pano_video_gen_720p_5b.safetensors")
         model = add_lora_to_model(
             getattr(pipe, "dit"),
             "q,k,v,o,ffn.0,ffn.2".split(","),