Instructions to use nvidia/difix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nvidia/difix with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nvidia/difix", 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
|
@@ -4,7 +4,7 @@ datasets:
|
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
---
|
| 7 |
-
# **
|
| 8 |
CVPR 2025 (Oral)
|
| 9 |
[**Code**](https://github.com/nv-tlabs/Difix3D) | [**Project Page**](https://research.nvidia.com/labs/toronto-ai/difix3d/) | [**Paper**](https://arxiv.org/abs/2503.01774)
|
| 10 |
|
|
@@ -26,7 +26,7 @@ Difix is an all-encompassing solution, a single model compatible for both NeRF a
|
|
| 26 |
|
| 27 |
**Model Developer:** NVIDIA
|
| 28 |
|
| 29 |
-
**Model Versions:**
|
| 30 |
|
| 31 |
**Deployment Geography:** Global
|
| 32 |
|
|
|
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
---
|
| 7 |
+
# **Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models**
|
| 8 |
CVPR 2025 (Oral)
|
| 9 |
[**Code**](https://github.com/nv-tlabs/Difix3D) | [**Project Page**](https://research.nvidia.com/labs/toronto-ai/difix3d/) | [**Paper**](https://arxiv.org/abs/2503.01774)
|
| 10 |
|
|
|
|
| 26 |
|
| 27 |
**Model Developer:** NVIDIA
|
| 28 |
|
| 29 |
+
**Model Versions:** difix
|
| 30 |
|
| 31 |
**Deployment Geography:** Global
|
| 32 |
|