Global Feed Post Login
Replying to Avatar Vitor Pamplona

We are now in half a second to do in-device text-to-image generation. We will see in-device mid journey first, than chat gpt next, then in-device video generation. Things are moving fast.

https://blog.research.google/2024/01/mobilediffusion-rapid-text-to-image.html?m=1

Avatar
petri 1y ago

Transcription is also blazing fast:

https://x.com/reach_vb/status/1752434666659889575

https://www.takeargmax.com/blog/whisperkit

https://github.com/argmaxinc/WhisperKit

Reply to this note

Please Login to reply.

Discussion

No replies yet.