NSFW Content Filter

NSFW Content filtering model offers vision based filtering solution to find explicit content. Its main use case is to check outputs of the generative models like Stable Diffusion. Model combines zero-shot capabilities of pretrained CLIP with a linear probing approach for fine tuning.

During fine-tuning, a light classification layer is trained on top of the frozen CLIP encoder, significantly improving the quality of detecting NSFW Content compared to just zero-shot classification.

Feature

Training

Inference

Data parallelism

Yes

N/A

Tensor parallelism

N/A

N/A

Pipeline parallelism

N/A

N/A

Sequence parallelism

N/A

N/A

Activation checkpointing

Yes (Uniform or Block)

No

FP32/TF32

Yes

Yes (FP16 enabled by default)

AMP/FP16

Yes

Yes

AMP/BF16

Yes

Yes

BF16 O2

Yes

No

TransformerEngine/FP8

No

No

Multi-GPU

Yes

Yes

Multi-Node

Yes

Yes

Inference deployment

N/A

NVIDIA Triton supported

SW stack support

Slurm DeepOps/Base Command Manager/Base Command Platform

Slurm DeepOps/Base Command Manager/Base Command Platform

NVfuser

No

N/A

Distributed Optimizer

N/A

N/A

TorchInductor

No

N/A

Flash Attention

No

N/A