readme

README.md

@@ -19,8 +19,8 @@ Code repository: [GitHub](https://github.com/ShandaAI/FloodDiffusion)
 
 The files in this repository are organized to match the directory structure required by FloodDiffusion.
 
-### 1. Model Checkpoints (`outputs.zip`)
-The `outputs.zip` archive contains the pretrained model weights.
+### 1. Model Checkpoints
+The `outputs.zip` and `outputs_tiny.zip` archive contains the pretrained model weights.
 
 *   **Target**: Unzip into your project root. It should create an `outputs/` folder.
 
@@ -29,8 +29,12 @@ outputs/
 ├── vae_1d_z4_step=300000.ckpt          # VAE model (1D, z_dim=4)
 ├── 20251106_063218_ldf/
 │   └── step_step=50000.ckpt            # LDF model checkpoint (HumanML3D)
-└── 20251107_021814_ldf_stream/
-    └── step_step=240000.ckpt           # Streaming LDF model checkpoint (BABEL)
+├── 20251107_021814_ldf_stream/
+│   └── step_step=240000.ckpt           # LDF streaming model checkpoint (BABEL)
+├── 20251217_023720_ldf_tiny/
+│   └── step_step=60000.ckpt            # LDF tiny model checkpoint
+└── 20251219_01492_ldf_tiny_stream/
+    └── step_step=200000.ckpt           # LDF tiny streaming model checkpoint
 ```
 
 ### 2. Datasets