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
where SD3.5 optimized TensorRT models?
#32
by FraYoshi - opened
Have just received an email from Stability stating:
"Stable Diffusion 3.5 (SD3.5) models are now optimized with TensorRT to deliver 2x faster performance and 40% less memory on NVIDIA GPUs."
Anyone knows where to download the models? I can only find 8 months old ones in here :(