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
We have released the sd3.5m turbo version, welcome to try it!
#21
by sunhaha123 - opened
https://huggingface.co/tensorart/stable-diffusion-3.5-medium-turbo, you can find lora\ckpt\workflow in our repository.
@sunhaha123 Your model does not have unet as well, I'm wondering how should I load the model with diffusers pipeline?
ValueError: Pipeline <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> expected {'unet', 'text_encoder', 'tokenizer', 'feature_extractor', 'safety_checker', 'image_encoder', 'vae', 'scheduler'}, but only {'vae', 'scheduler', 'text_encoder', 'tokenizer'} were passed.
Should be StableDiffusion3Pipeline