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
Hyper-SD lora for CosXL?
#41
by 10mmlover - opened
Hi, I'm using the 8 step lora with sdxl with good effect. When I try to use it with a CosXL base or CosXL merged checkpoint, the results are very muddy and don't have any sharpness. Do you think a version of this lora will come out that's compatible with CosXL from Stability AI? Thanks.