import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("deepsafe/deepsafe-services", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]DeepSafe Model Weights
Weights for the 24 models used by DeepSafe, a benchmark that tests how well deepfake detectors actually work.
These weights are not ours. Each belongs to the authors of the model it came from and keeps that model's own license. See THIRD_PARTY_NOTICES.md.
Why mirror them
Paper download links rot. DeepSafe lost one model outright when its weights were deleted from the host its paper pointed at. Mirroring means setup still works in three years.
Usage
You do not normally download this by hand. setup.sh does it:
git clone https://github.com/deepsafehq/deepsafe-bench.git
cd deepsafe-bench && bash setup.sh
Roughly 44 GB, covering 7 image, 9 video, 3 audio and 5 provenance models, plus the CLIP and face-detection caches they depend on. No token needed.
Model code is mirrored separately at deepsafe/model-code.
Takedown
If you authored any of these weights and want them removed, open an issue at https://github.com/deepsafehq/deepsafe-bench and they come down within 48 hours, no questions asked.
- Downloads last month
- -