Image to my ears 🎵

+ Wikipedia AI-assistant ✌🏼Get prompts from images 🌠 Image segmentation ✂️

Hey folks!✌🏼 Hope that everyone is feeling great today! From now on, I'll send out updates 3 times a week (M, W, F). Let's see what's the latest👇🏻

Image to my ears 🎵

This new model on Hugging Face generates audio from images. Just upload an image and it will create an audio file for it. They used two models for this: extract text from an image(Clip) + generate music from the prompt (Mubert).

Listen to what the tool generated from Elon Musk's "let that sink in" image. 

Pretty futuristic I'd say.

New Image Segmentation model with the highest accuracy 🎧

OneFormer, outperforms older models across all segmentation tasks — having only 1 trained model, 1 architecture, and 1 dataset.

Older models have built specialized architectures + models to achieve good results for specific tasks — and OneFormer still got better results.

One flaw? Donkeys seem to be hard to segment... So, if you're looking into that particular edge case - drop your project🐴Just saying...

🛼 Makers corner

🤓 Tech corner

 Creativity corner

🧱 What are you building?

If you're using AI in your work or projects, I'd love to hear about it! Please reply to this email and let us know what you're up to. We may feature your work in our newsletter.

❤️ Share The Prompt

  • Share The Prompt with a friend, and invite them to subscribe here.

  • Book an ad in The Prompt (reply to this email if you’re interested)

What'd you think of today's edition?

Login or Subscribe to participate in polls.

Thank you for reading! ✌🏼