Instructions to use amd/Nitro-T-1.2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use amd/Nitro-T-1.2B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("amd/Nitro-T-1.2B", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ Nitro-T is a set of text-to-image diffusion models focused on highly efficient t
|
|
| 21 |
|
| 22 |
⚡️ [Open-source code](https://github.com/AMD-AIG-AIMA/Nitro-T)! Our GitHub provides training and data preparation scripts to reproduce our results. We hope this codebase for efficient diffusion model training enables researchers to iterate faster on ideas and lowers the barrier for independent developers to build custom models.
|
| 23 |
|
| 24 |
-
📝 Read our technical blog post for more details on the techniques we used to achieve fast training and for results and evaluations.
|
| 25 |
|
| 26 |
## Details
|
| 27 |
|
|
@@ -65,7 +65,7 @@ image = pipe(
|
|
| 65 |
image.save("output.png")
|
| 66 |
```
|
| 67 |
|
| 68 |
-
For more details on training and evaluation please visit the [GitHub repo](https://github.com/AMD-AIG-AIMA/Nitro-T) and read our technical blog post.
|
| 69 |
|
| 70 |
|
| 71 |
|
|
|
|
| 21 |
|
| 22 |
⚡️ [Open-source code](https://github.com/AMD-AIG-AIMA/Nitro-T)! Our GitHub provides training and data preparation scripts to reproduce our results. We hope this codebase for efficient diffusion model training enables researchers to iterate faster on ideas and lowers the barrier for independent developers to build custom models.
|
| 23 |
|
| 24 |
+
📝 Read our [technical blog post](https://rocm.blogs.amd.com/artificial-intelligence/nitro-t-diffusion/README.html) for more details on the techniques we used to achieve fast training and for results and evaluations.
|
| 25 |
|
| 26 |
## Details
|
| 27 |
|
|
|
|
| 65 |
image.save("output.png")
|
| 66 |
```
|
| 67 |
|
| 68 |
+
For more details on training and evaluation please visit the [GitHub repo](https://github.com/AMD-AIG-AIMA/Nitro-T) and read our [technical blog post](https://rocm.blogs.amd.com/artificial-intelligence/nitro-t-diffusion/README.html).
|
| 69 |
|
| 70 |
|
| 71 |
|