This is the official released checkpoint of an algined Stable Diffusion v1.5 of SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation, designed to generate more safe images from our Safe-SD1.5.

Our project page is 🏠SafetyDPO HomePage and the GitHub repo is ⚙️SafetyDPO GitHub where we released all the code and the data.

In the future, we will release additional safe models, including the safe-SDXL.

Usage

A simple use case of our model is:

from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained("Visualignment/safe-stable-diffusion-v1-5")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
Downloads last month
14
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.