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
|
@@ -307,7 +307,10 @@ eta=1.0
|
|
| 307 |
image = pipe("a blue paradise bird in the jungle", num_inference_steps=1, image=control_image, guidance_scale=0, eta=eta).images[0]
|
| 308 |
image.save('image_out.png')
|
| 309 |
```
|
| 310 |
-
|
|
|
|
|
|
|
|
|
|
| 311 |
|
| 312 |
## Citation
|
| 313 |
```bibtex
|
|
|
|
| 307 |
image = pipe("a blue paradise bird in the jungle", num_inference_steps=1, image=control_image, guidance_scale=0, eta=eta).images[0]
|
| 308 |
image.save('image_out.png')
|
| 309 |
```
|
| 310 |
+
## Comfyui Usage
|
| 311 |
+
* `Hyper-SDXL-Nstep-lora.safetensors`: [text-to-image workflow](https://huggingface.co/ByteDance/Hyper-SD/blob/main/comfyui/Hyper-SDXL-Nsteps-lora-workflow.json).
|
| 312 |
+
* `Hyper-SD15-Nstep-lora.safetensors`: [text-to-image workflow](https://huggingface.co/ByteDance/Hyper-SD/blob/main/comfyui/Hyper-SD15-Nsteps-lora-workflow.json)
|
| 313 |
+
* `Hyper-SDXL-1step-unet.safetensors`: working on it, will be updated soon.
|
| 314 |
|
| 315 |
## Citation
|
| 316 |
```bibtex
|