Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Instructions to use CompVis/stable-diffusion-v1-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CompVis/stable-diffusion-v1-4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", dtype=torch.bfloat16, device_map="cuda") prompt = "A high tech solarpunk utopia in the Amazon rainforest" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Add safety module functionality to readme
#30
by natolambert - opened
No description provided.
I think it would be good to describe to the user how this is done. Let me know if it is not correct / in the right spot!
Very nice! Thanks!
patrickvonplaten changed pull request status to merged
The concepts are intentionally hidden to reduce the likelihood of reverse-engineering this filter
Wouldn't it be useful to give at least broad hints what is detected besides nudity? People may both be interested in being sure that some things are not generated or knowing if the filter is hiding too much (for their taste and/or purpose).
cc @meg @multimodalart do you think we could add more info here?