Instructions to use stabilityai/stable-diffusion-3.5-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/stable-diffusion-3.5-medium with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium", dtype=torch.bfloat16, device_map="cuda") 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
What versions of CUDA, PyTorch and other packages do I need
#15
by d-hari - opened
The requirements.txt file just lists "transformers", "torch", etc, but no specific version numbers. Does this mean I should update them all to the latest? What about CUDA? That file also mentions "cu118" so I'm guessing 11.8. Does this mean I should not update to 12.x (I'm currently on 11.6)?