Instructions to use Ateeqq/ai-vs-human-image-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ateeqq/ai-vs-human-image-detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Ateeqq/ai-vs-human-image-detector") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoProcessor, AutoModelForImageClassification processor = AutoProcessor.from_pretrained("Ateeqq/ai-vs-human-image-detector") model = AutoModelForImageClassification.from_pretrained("Ateeqq/ai-vs-human-image-detector", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Model is not accurate
#1
by duyntnet - opened
Tested with 20 real images and it detected all of them as AI-generated images.
i tested on 20 real and 20 gpt-4o generated receipts. Yes, similar results where it detected all with great confidence to be AI generated
Lmao, nice commit https://huggingface.co/Ateeqq/ai-vs-human-image-detector/commit/60e824 it deserves it. I agree, we need a better detector, it should at least detect obvious AI generated images