Diffusers
Safetensors
CondDDIMPipeline
downscaling
ERA5 - COSMO-REA6
reanalysis data
wind velocities
diffusion
superresolution
Instructions to use lschmidt/ddim-dsc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lschmidt/ddim-dsc with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lschmidt/ddim-dsc", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ datasets:
|
|
| 15 |
|
| 16 |
# DDIM-DSC: 4× Downscaling of Wind Velocities
|
| 17 |
|
| 18 |
-
**DDIM-DSC** is a custom-trained [Denoising Diffusion Implicit Model (DDIM)](https://github.com/huggingface/diffusers) designed for the **
|
| 19 |
|
| 20 |
It performs **4× spatial downscaling** on 2-channel wind fields (u and v components), using **ERA5** as low-resolution input and **COSMO-REA6** as the high-resolution target.
|
| 21 |
|
|
|
|
| 15 |
|
| 16 |
# DDIM-DSC: 4× Downscaling of Wind Velocities
|
| 17 |
|
| 18 |
+
**DDIM-DSC** is a custom-trained [Denoising Diffusion Implicit Model (DDIM)](https://github.com/huggingface/diffusers) designed for the **downscaling of wind velocity fields** from coarse- to high-resolution using reanalysis data.
|
| 19 |
|
| 20 |
It performs **4× spatial downscaling** on 2-channel wind fields (u and v components), using **ERA5** as low-resolution input and **COSMO-REA6** as the high-resolution target.
|
| 21 |
|