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
How to create merges with 1-step Unet?
#39
by WaveCut - opened
Hey! Your developments are great and i really appreciate it, but what i want is to create my own version of “1 step cfg unet” baked into my own or any else checkpoint, preserving it’s style. Is it possible without investing much into process?