---
license: mit
tags:
  - super-resolution
  - ddim
  - weather
  - wind
library_name: diffusers
model_type: ddim
datasets:
  - your-dataset-name
---
# DDIM-DSC (4× Super-Resolution for Wind Data)
---

## 🧠 Model Architecture

- **Base**: DDIM
- **Input channels**: 10 
- **Output channels**: 10
- **Scale factor**: 4×
---

---
## 🚀 How to Use
```python
import torch
from diffusers import DiffusionPipeline, DDIMScheduler
from diffusers import DDIMScheduler

# 
pipe = DiffusionPipeline.from_pretrained(
    "lschmidt/ddim-dsc",
    custom_pipeline="cond_ddim_pipeline", 
    trust_remote_code=True
)

#
batch_size = 1
in_channels = 6
sequence_len = 3

# 
lres_image = torch.randn((sequence_len, in_channels, sample_size, sample_size)).to(pipe.device)
pipe(image=lres_image)