Instructions to use benjamin-paine/stable-diffusion-v1-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use benjamin-paine/stable-diffusion-v1-5 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("benjamin-paine/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
FP16 model request
#2
by asfiyab - opened
Hi,
Do you have the FP16 checkpoints as well?
Hi there! Thank you for the suggestion.
I do not have the originals, but it's easy to downcast the fp32 versions in the repository, so I went ahead and added a .fp16.(ckpt|bin|safetensors) file alongside all the models in here.
Thanks! A lot of existing code relies on pulling the FP16 variant directly, so having the safetensors uploaded here helps
asfiyab changed discussion status to closed