Instructions to use BiliSakura/NiT-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/NiT-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BiliSakura/NiT-diffusers", 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
Delete transformer
Browse files
transformer/config.json
DELETED
|
@@ -1,14 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_class_name": "NiTTransformer2DModel",
|
| 3 |
-
"class_dropout_prob": 0.1,
|
| 4 |
-
"depth": 28,
|
| 5 |
-
"encoder_depth": 8,
|
| 6 |
-
"hidden_size": 1152,
|
| 7 |
-
"in_channels": 32,
|
| 8 |
-
"input_size": 32,
|
| 9 |
-
"num_classes": 1000,
|
| 10 |
-
"num_heads": 16,
|
| 11 |
-
"patch_size": 1,
|
| 12 |
-
"qk_norm": true,
|
| 13 |
-
"z_dim": 1280
|
| 14 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
transformer/diffusion_pytorch_model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:68cf19eb16e2231d1493dbb2c1bc7922fdfb23cc1e4b209aca6b6282238aa83b
|
| 3 |
-
size 2736207096
|
|
|
|
|
|
|
|
|
|
|
|