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
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,14 +3,16 @@ license: mit
|
|
| 3 |
library_name: diffusers
|
| 4 |
pipeline_tag: unconditional-image-generation
|
| 5 |
tags:
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
widget:
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
# JiT-H/32 (Diffusers)
|
|
@@ -86,4 +88,4 @@ python run_jit_diffusers_inference.py --model_path ./JiT-H-16 --output_path ./de
|
|
| 86 |
python run_jit_diffusers_inference.py --model_path ./JiT-B-32 --output_path ./demo_images/jit_b32_test_inference.png --class_label 207 --seed 42 --steps 50 --cfg 3.0 --interval_min 0.1 --interval_max 1.0 --noise_scale 2.0 --t_eps 5e-2 --solver heun
|
| 87 |
python run_jit_diffusers_inference.py --model_path ./JiT-L-32 --output_path ./demo_images/jit_l32_test_inference.png --class_label 207 --seed 42 --steps 50 --cfg 2.5 --interval_min 0.1 --interval_max 1.0 --noise_scale 2.0 --t_eps 5e-2 --solver heun
|
| 88 |
python run_jit_diffusers_inference.py --model_path ./JiT-H-32 --output_path ./demo_images/jit_h32_test_inference.png --class_label 207 --seed 42 --steps 50 --cfg 2.3 --interval_min 0.1 --interval_max 1.0 --noise_scale 2.0 --t_eps 5e-2 --solver heun
|
| 89 |
-
```
|
|
|
|
| 3 |
library_name: diffusers
|
| 4 |
pipeline_tag: unconditional-image-generation
|
| 5 |
tags:
|
| 6 |
+
- diffusers
|
| 7 |
+
- jit
|
| 8 |
+
- image-generation
|
| 9 |
+
- class-conditional
|
| 10 |
widget:
|
| 11 |
+
- text: ImageNet class 207 (golden retriever)
|
| 12 |
+
output:
|
| 13 |
+
url: ./demo.png
|
| 14 |
+
language:
|
| 15 |
+
- en
|
| 16 |
---
|
| 17 |
|
| 18 |
# JiT-H/32 (Diffusers)
|
|
|
|
| 88 |
python run_jit_diffusers_inference.py --model_path ./JiT-B-32 --output_path ./demo_images/jit_b32_test_inference.png --class_label 207 --seed 42 --steps 50 --cfg 3.0 --interval_min 0.1 --interval_max 1.0 --noise_scale 2.0 --t_eps 5e-2 --solver heun
|
| 89 |
python run_jit_diffusers_inference.py --model_path ./JiT-L-32 --output_path ./demo_images/jit_l32_test_inference.png --class_label 207 --seed 42 --steps 50 --cfg 2.5 --interval_min 0.1 --interval_max 1.0 --noise_scale 2.0 --t_eps 5e-2 --solver heun
|
| 90 |
python run_jit_diffusers_inference.py --model_path ./JiT-H-32 --output_path ./demo_images/jit_h32_test_inference.png --class_label 207 --seed 42 --steps 50 --cfg 2.3 --interval_min 0.1 --interval_max 1.0 --noise_scale 2.0 --t_eps 5e-2 --solver heun
|
| 91 |
+
```
|