Instructions to use BiliSakura/JiT-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/JiT-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/JiT-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 JiT-B-16/conversion_metadata.json
Browse files
JiT-B-16/conversion_metadata.json
DELETED
|
@@ -1,17 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"source_checkpoint": "/root/worksapce/models/raw/jit-b-16/checkpoint-last.pth",
|
| 3 |
-
"weights": "ema1",
|
| 4 |
-
"epoch": null,
|
| 5 |
-
"jit_args": {
|
| 6 |
-
"model_type": "JiT-B/16",
|
| 7 |
-
"sample_size": 256,
|
| 8 |
-
"num_class_embeds": 1000,
|
| 9 |
-
"attention_dropout": 0.0,
|
| 10 |
-
"dropout": 0.0,
|
| 11 |
-
"model": "JiT-B/16",
|
| 12 |
-
"img_size": 256,
|
| 13 |
-
"class_num": 1000,
|
| 14 |
-
"attn_dropout": 0.0,
|
| 15 |
-
"proj_dropout": 0.0
|
| 16 |
-
}
|
| 17 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|