MULTIMODAL AI

–

18 October 2023 16h10

This MusicGen fine-tune goes hard.https://t.co/QBNQeFI26J

The end, dang! 🤘 pic.twitter.com/eJDYlEbGiJ
— fofr (@fofrAI) 18 octobre 2023

This MusicGen fine-tune goes hard. https://
replicate.com/fofr/musicgen-
slipknot
… The end, dang!

18 October 2023

Fine-Tuning MusicGen: Create Custom Music AI Models

By

–

17 October 2023 23h12

How to fine tune MusicGen, any style you want, any duration you want. It’s lots of fun.

→ View original post on X — @localghost

OpenPose Skeleton ControlNet Workflow for Photo Generation

By

@localghost

–

17 October 2023 21h17

Yeah, you can get an openpose skeleton from a photo. From there it's the same controlnet workflow.

→ View original post on X — @replicate

MusicGen Fine-Tuning: Create Custom Style Music in Minutes

By

@replicate

–

17 October 2023 20h49

You can now fine-tune MusicGen to generate music in any style. – Train a fine-tune in 15 mins
– Automatically labels your training data
– Automatically removes vocals
– Makes a track as long as you want

Show-1 Text-to-Video Model Now Available on Replicate

By

–

17 October 2023 15h13

Show-1 text-to-video is now on Replicate:https://t.co/CeyzJX5cxH

You can ask it to put text in a video:https://t.co/qe2kPUy3Od pic.twitter.com/GZ7tJFXYMP
— fofr (@fofrAI) 17 octobre 2023

Show-1 text-to-video is now on Replicate: https://
replicate.com/cjwbw/show-1 You can ask it to put text in a video: https://
replicate.com/p/7y7snnlbkvyh
lm2acmtbqcio3e
…

DALLE3 Image Generation Randomness and Seed Behavior Analysis

By

–

17 October 2023 15h01

Yes, though I'm not sure how much of this is true though. I don't see too much randomness between dalle3 conversations. Same prompt often gives same image.
Which could mean GPT is picking the same random seed. Or there might be a user based seed. I don't know.