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 Settings
- Draw Things
- DiffusionBee
Download comfyui/ComfyUI-HyperSDXL1StepUnetScheduler/__init__.py from ByteDance/Hyper-SD: direct link, hf CLI and curl.
- Browser
- Download file 71 Bytes
-
https://huggingface.co/ByteDance/Hyper-SD/resolve/refs%2Fpr%2F21/comfyui/ComfyUI-HyperSDXL1StepUnetScheduler/__init__.py
- Command line
-
hf download hf://ByteDance/Hyper-SD@refs/pr/21/comfyui/ComfyUI-HyperSDXL1StepUnetScheduler/__init__.py
-
curl -L -o __init__.py https://huggingface.co/ByteDance/Hyper-SD/resolve/refs%2Fpr%2F21/comfyui/ComfyUI-HyperSDXL1StepUnetScheduler/__init__.py
71 Bytes
| from .node import NODE_CLASS_MAPPINGS | |
| __all__ = ['NODE_CLASS_MAPPINGS'] |