Instructions to use ByteDance/Hyper-SD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ByteDance/Hyper-SD with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ByteDance/Hyper-SD") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -52,7 +52,7 @@ prompt="a photo of a cat"
|
|
| 52 |
image=pipe(prompt=prompt, num_inference_steps=2, guidance_scale=0).images[0]
|
| 53 |
```
|
| 54 |
|
| 55 |
-
### Unified LoRA
|
| 56 |
```python
|
| 57 |
import torch
|
| 58 |
from diffusers import DiffusionPipeline, TCDScheduler
|
|
@@ -118,7 +118,7 @@ image=pipe(prompt=prompt, num_inference_steps=2, guidance_scale=0).images[0]
|
|
| 118 |
```
|
| 119 |
|
| 120 |
|
| 121 |
-
### Unified LoRA
|
| 122 |
```python
|
| 123 |
import torch
|
| 124 |
from diffusers import DiffusionPipeline, TCDScheduler
|
|
|
|
| 52 |
image=pipe(prompt=prompt, num_inference_steps=2, guidance_scale=0).images[0]
|
| 53 |
```
|
| 54 |
|
| 55 |
+
### Unified LoRA (support 1 to 8 steps inference)
|
| 56 |
```python
|
| 57 |
import torch
|
| 58 |
from diffusers import DiffusionPipeline, TCDScheduler
|
|
|
|
| 118 |
```
|
| 119 |
|
| 120 |
|
| 121 |
+
### Unified LoRA (support 1 to 8 steps inference)
|
| 122 |
```python
|
| 123 |
import torch
|
| 124 |
from diffusers import DiffusionPipeline, TCDScheduler
|