Instructions to use haywoodsloan/ai-image-detector-deploy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use haywoodsloan/ai-image-detector-deploy with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="haywoodsloan/ai-image-detector-deploy") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("haywoodsloan/ai-image-detector-deploy") model = AutoModelForImageClassification.from_pretrained("haywoodsloan/ai-image-detector-deploy", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Could you add a license to this model?
Hi, and thanks for publishing this checkpoint
I'd like to use it in an open-source project. To ship it I'd need to redistribute a derivative of the weights - specifically an ONNX export quantized to int8 - bundled with the extension.
The repo doesn't currently declare a license in its model card metadata, so I wanted to ask rather than assume. Would you be willing to add one?
MIT or Apache-2.0 would let projects like mine use and redistribute it with confidence, but any license that permits redistribution of derivatives would help and it would make the model much more usable for others too
Happy to credit you and link back to this repo prominently. Thanks either way!
Also blocked by this, from a different angle.
We run the model server-side in a hosted product - we don't redistribute the weights, so our ask is narrower than bundling an export.
Even a note on the card confirming commercial use is permitted, without redistribution rights, would unblock us - if a full permissive licence is more than you want to grant.
MIT or Apache-2.0 would of course be ideal and would cover both use cases.
Happy to credit you by name and link to this model page.
Thanks for publishing it - it performs well in our testing.