Ruibin Yuan
@abc43992899
Followers
627
Following
134
Statuses
131
ML Student @HKUST, Music Tech MS @CarnegieMellon. Co-Founder of Multimodal Art Projection Community (MAP)
Hong Kong
Joined January 2017
YuE GP v3!!!
Yue GP v3: by popular demand I have added multiple generations per Genres prompt and the possiblity to generate multiple songs based on the same lyrics but with different Genre prompts. As a bonus, I have added a progression bar and an Abort button
0
0
1
RT @deepbeepmeep: Yue GP v3: by popular demand I have added multiple generations per Genres prompt and the possiblity to generate multiple…
0
1
0
YuE GP 2.0!
Here comes Yue GP 2.0 ! Thanks to new optimisations I have been cooking: x3 faster with 16Gb+ of VRAM (1 min of song takes now only 4 minutes on a RTX 4090 !) and x2 faster with 12 GB of VRAM.
1
0
4
RT @cocktailpeanut: YuE can now generate songs in just 4 minutes flat, 100% on your local PC! @deepbeepmeep has optimized his YueGP code e…
0
27
0
RT @cocktailpeanut: YuE Language Support "We support multiple languages, including but not limited to English, Mandarin Chinese, Cantonese…
0
1
0
RT @cocktailpeanut: At 4 minutes generation time, it's so much easier to experiment with all kinds of variations
0
1
0
RT @cocktailpeanut: Daft Punk (Technologic) reimagined by Charlie XCX (365) Generated by AI (YuE) with audio to audio.
0
11
0
RT @QiuqiangK: 2-hour tutorial code of LLM-based audio understanding: including 1) music tagging, 2) speech recogn…
0
25
0
RT @cocktailpeanut: Sabrina Carpenter sings Gangnam Style, in Korean. AI made this, in 10 minutes, on my PC (4090).
0
7
0
Wow Rap ver. Plastic Love by YuE👀
It's really really cool. If you think above example is just a fluke, watch this one. This time I asked it to rap instead of sing.
1
1
4
RT @cocktailpeanut: Audio-to-Audio Song Generation is here! 1. YuE can now use an audio clip as input! 2. @deepbeepmeep's custom transform…
0
163
0
Great work!
Another release for us the GPU Poors ! I have optimized YuE the best open source song generator and added a Gradio UI. Songs can now be generated with less than 10GB of VRAM . You can also generate on RTXx90 longer songs than with original repo
0
0
0
0
0
0
Wow the demo sounds cool.
Did Billie Eilish just release a single about OpenAI!? She did not (AI did). It's a banger anyway. YuE gives us open-weights music generation with vocals! The ICL version adds voice and style cloning, too.
0
0
2
RT @_akhaliq: IT KEEPS GETTING BETTER: YuE (乐) open-source full-song music generation model that rivals Suno AI! It’s Hugging Face & LLA…
0
223
0
RT @ai_for_success: RIP Suno and Udio. 😬 China just dropped another open-source model: YuE, a full-song music generation model. From lyr…
0
518
0
Thanks for posting our demo. 2025 will be the year of TRUE open AI!! We are working on upgrading the tokenizer and audio quality. And We will do RL to improve the good case rate.
IT KEEPS GETTING BETTER: YuE (乐) open-source full-song music generation model that rivals Suno AI! It’s Hugging Face & LLAMA-compatible for easy fine-tuning.
0
4
40
5/n: Big thanks to Multimodal Art Projection Research Community @MM_Art_Project and @hkust. Core: @abc43992899, @HanfengLin86550, Shuyue Guo, @GeZhang86038849, @jiahaopan010366, Contributors: @yongyi_zang, @LiuHaohe, @XJDu97, @XinrunDu, Zhen Ye, @zhengtianyu4, @nicolaus625, Minghao Liu, @LijunYu0, @Zeyue_Tian, Ziya Zhou, @lmxue_, @XingweiQu78535, @yizhilll, @allen_thshen, @ddlbojack, Shangda Wu, Jun Zhan, Chunhui Wang, Yatian Wang, @xiaohuaererer, Xiaowei Chi, Xinyue Zhang, Zhenzhu Yang, Yiming Liang, XiangzhouWang, Shansong Liu, Lingrui Mei, Peng Li, Yong Chen, @chenghua_lin, Xie Chen, @GuangyuXIA, Zhaoxiang Zhang, Chao Zhang, @WenhuChen, Xinyu Zhou, @xpqiu, Roger Dannenberg, Correspondence: Jiaheng Liu, Jian Yang, Stephen Huang, @wxue_audio, @xutan_tx, Yike Guo
1
2
12