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
Flux.1 [Dev]-Model License
#55
by jaymueller - opened
Thanks for creating these loras, they certainly look interesting. However, as they are derivatives of the Flux.1 [dev] Model, the Flux.1 [dev] License applies to them. It would be nice if they could be marked as such. I think the easiest way to do that is to create a new repository here on huggingface, upload the Flux loras only there and add the License to that repository.
Thank you
Hi @jaymueller
Thanks for your reminder and so sorry about the confusion.
We have modified and labeled our LICENSE.md : )
If you have further questions please inform us at any time.
Thank you! :)
jaymueller changed discussion status to closed