@ozz_shibuya@ozzon_japan These are gorgeous! Please tell Sensei that I miss her and I wish I could visit the store soon. I have not been fortunate enough lately to return to Japan.
Working on a zero-shot ‘audio reference to song’ module for YuE2. provide a song for reference then pick the key, tempo and lyrics for the new song that will use the singer and band from your reference. Here’s a new video from Nora while it’s training! youtu.be/20A_JM8BJnY
hum anything, get a finished song 🎤
Hum-to-Song is an YuE2 LoRA that turns humming into full songs 🎼
hum in, a produced track, verse, chorus, and the tune you hummed coming back around
▶️ on Spaces hf.co/spaces/hugging…
Many people have been asking me if you can train YuE2 based on your own version. Thanks to @ostrisai and @sin_ceriously it is already here!
And you can get going with 1-click in pinokio. Fully local on your PC.
AI Toolkit now supports training LoRAs for YuE2-3B, an amazing music model. Support would not be possible without the tokenizer and help from @sin_ceriously . Thank you! Also special thanks to @Machinedelusion. More in 🧵
Added initial support to fine tune LLMs in AI Toolkit with a focus on Omni models. First one added is
Qwen2.5-Omni-7B and I trained a LoRA for it to better caption and transcribe music files. You can use these LoRAs in the dataset captioner along with default cloud ones.
Audio to Audio LoRa's able to be trained now. We basically have the ability to make edit audio models!
@sin_ceriously Thanks for the initial training code
github.com/filliptm/Comfy…
The "hum-to-song" module training is complete. I'm open-sourcing it within the hour. Follow to make sure you don't miss the update.
Special thanks to my mates at fixedseed.com for sponsoring the compute.
#YuE2#opensource
My next experiment is to create the "hum the song into your mic" feature and bring it to YuE2 with a conditioning adapter. The attached song was created from only a vocal input and the rest of the audio generated from a style prompt. I'll release it after some more testing.
118 Followers 554 FollowingI have an AAS and BS in CS from the University of Arizona. I develop apps and am interested in gaming, art, philosophy, and psychology.
479 Followers 489 Followingapplication and ai/ml architect by day, AI whisperer, tinkerer and Concept artist by night, compulsive philosopher day and night. views my own.
1K Followers 175 FollowingPhotographs and art have a story to tell Photographs and art sharpen our senses Photographs and art are simply balm for the soul
4K Followers 6K Followinghttps://t.co/bO6kvgdLEO AI ML. Husband, Father
@BitBankNZx Crypto Trading Bot & Launchpad
https://t.co/ZRrl5gTRcd AI Social Net.
https://t.co/k4UbhkOJFO AI Art Generator
51K Followers 9K FollowingInvestor and AI startup founder. Focus: AI, LLMs, LifeOps, AI Product Management. Was founder @SkipFlag. EIR @Accel. Data Science & ML @LinkedIn, @AOL & @MIT
33 Followers 627 FollowingInterest in ai music/daw production, ai art & video. Here to enjoy other ai producers amazing directed works, maybe share some of my own experiments. Take care.
13K Followers 2K FollowingStaff Product Designer ▲ @Vercel
Building https://t.co/z2dX2CbMIm
Living on the road, traveling the US.
Husband to @joylynnlife. Dad of 2 boys.
41K Followers 5 Following#MHOutlanders is the latest mobile title in the Monster Hunter series, licensed by CAPCOM and developed by TiMi Studio Group.
Pre-registration is now open!
80K Followers 2K FollowingI am an experimental psychologist who studies visual illusions as well as makes illusion artworks. #illusion #opticalillusion #perception #錯視
1K Followers 86 FollowingThe professional creative toolset for AI animation by https://t.co/DHatwSkh7J
AIアニメーションのためのプロフェッショナル・クリエイティブツールセット
by https://t.co/DHatwSkh7J
物語を、望み通りに。
3K Followers 57 FollowingWhat you imagine is what Vidu(ヴィドゥ)❥
📩 Mail - Vidu Japan: [email protected]
💬 Discord: https://t.co/tHmJgET0hC
🙌 CPP募集中:https://t.co/vKXuxma3oo