Instructions to use amd/Nitro-E with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use amd/Nitro-E 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-E", 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
|
@@ -39,9 +39,15 @@ from core.tools.inference_pipe import init_pipe
|
|
| 39 |
|
| 40 |
device = torch.device('cuda:0')
|
| 41 |
dtype = torch.bfloat16
|
| 42 |
-
resolution = 512
|
| 43 |
repo_name = "amd/Nitro-E"
|
|
|
|
|
|
|
| 44 |
ckpt_name = 'Nitro-E-512px.safetensors'
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
use_grpo = True
|
| 46 |
|
| 47 |
if use_grpo:
|
|
|
|
| 39 |
|
| 40 |
device = torch.device('cuda:0')
|
| 41 |
dtype = torch.bfloat16
|
|
|
|
| 42 |
repo_name = "amd/Nitro-E"
|
| 43 |
+
|
| 44 |
+
resolution = 512
|
| 45 |
ckpt_name = 'Nitro-E-512px.safetensors'
|
| 46 |
+
|
| 47 |
+
# for 1024px model
|
| 48 |
+
# resolution = 1024
|
| 49 |
+
# ckpt_name = 'Nitro-E-1024px.safetensors'
|
| 50 |
+
|
| 51 |
use_grpo = True
|
| 52 |
|
| 53 |
if use_grpo:
|