I've had this running locally for a while and whilst it's an alternative you can actually use, it's not anywhere near the quality of DALL-E, let alone DALL-E-2. (Although since I mainly use it for abstracts and inspiration, that's fine.)
Here’s a web demo[0] where you can try out any two images and see the resulting hashes, and whether there’s a collision. You can also try your own transformations (rotation, adding a filter, etc) on the image. Demo was built using Gradio[1].
[0]: https://huggingface.co/spaces/akhaliq/AppleNeuralHash2ONNX [1]: https://gradio.dev