Gong Junmin

True Frontier Intelligence

Introducing ACE Studio Music Video. Your AI crew directs, casts, and shoots your music video. Powered by Seedance (2.0 is live, 2.5 coming next week), Midjourney, GPT Image 2, and more. Any style. Any genre. Try it now → acestudio.ai

let's build something incredible! ACE Studio Music Video | Your AI Crew Directs, Casts & Shoots youtu.be/amx7gYLPW10?is…

🔈お知らせ #ボカコレ2026夏 にて「ACE Studio賞」の実施が決定しました！！✨ あわせて、 #ボカコレ2026夏  参加予定の方、 または過去のボカコレに参加された方を対象に、 9月15日まで先着2,000名様限定で、 「ACE Studio 1ヶ月体験ライセンス」をプレゼント中！！✨ 🔽キャンペーンはこちら acestudio.ai/vocacolle-2026… #ACEStudio

The version we deployed on AceMusic uses the same latest tag as the open-source release with its default recipe. In terms of model scale, ACE-Step has already hit the current ceiling for open-source implementations. Naturally, there is still a certain gap when compared to top-tier mainstream commercial models, though it is nowhere near as far behind as you claimed. The difference lies in their respective orientations rather than a sheer disparity in capability. Just as ACE-Step cannot replicate certain outputs and stylistic genres achievable with Suno, many users of ACE-Step have reported that this open-source model is capable of producing plenty of musical works that Suno cannot generate. Commercial models undergo reinforcement learning tailored to cater to mass market demands, which filters out certain sonic characteristics during training. You should view this model as a vital supplement to commercial offerings rather than a full replacement.

@junmingong I am now of version 60 of my attempts to install Ace Step. It is working but not nearly as well as suno. I am using runpod serverless machines, we have debuged every aspect of this. Can we use. the loras with your image?

ACE‑Step 1.5 XL will be released in the next two days. The all‑new 4B DiT model brings comprehensive improvements: lyrics are almost error‑free, complex music generation and prompt adherence are both significantly enhanced.

Meet LiveBand: a real-time AI jamming companion! 🎸 It generates live music accompaniments with zero perceived latency ⚡️ It runs locally on Macbooks, can generate any instrument (more than one at a time), is wildly robust, and is trained from scratch on a single GPU! 🧵👇

The answer is: x.com/junmingong/sta…

we've reached the point where "new SOTA model" generates less dopamine than a good meme jaded isn't even the word👀

Here is the answer x.com/junmingong/sta…

Built ACE-Step UI in public (4.1k⭐). Shipped LocalMusic AI on Mac App Store. Now bootstrapping a web agency back home. Same engineering bar, smaller scope. Following along is fun: @AmbsdOP

Introducing Magenta RealTime 2 (MRT2): the live music model you can play as an instrument. MRT2 offers MIDI and prompt controls, and runs natively on a MacBook with <200ms latency. Open weights. Open source inference engine. Suite of apps and plugins. Hear what it can do and try it out for yourself below 🧵

Just some of the untested hacks, strange add-ons and experimental integrations built for Live Suite with the free Extensions SDK, now in public beta. Link in comments.

Release soon on the Unity Store! discussions.unity.com/t/3d-medieval-… Music by AceStep 😍 Hey @junmingong ! 😀 If you knew how happy I am to be able to make my own music... #unity3d #indie #indiedev #gamedev #madewithunity #indiegames #assetstore #unity #unitydeveloper

To top off this week, there's now a paper about DEMON published on @arxiv. A lot of great insights there - especially for researchers from the AI audio-gen domain. Here's the video covering some basics, and the paper is in the tweet below. Next week, on Tuesday (Jun 2), we are hosting our webinar with @RyanOnTheInside, author of the paper, so you can ask any questions.

@DaydreamLiveAI @Strength04_X Yes, I have tried it. Fancy!

@Strength04_X @junmingong Have you gotten a chance to try it out at music.daydream.live already? Would love your feedback @Strength04_X!

Built on ACE-Step, this lets you perform AI-generated music with synth hardware, almost like playing an instrument Hardware knobs shape DiT's initial noise, and the music is generated in real time through streaming A new kind of music is emerging Live music is the future

Project: daydreamlive.github.io/DEMON/

@RyanOnTheInside @ACEStep_Music Live music is the future

I just released this open source project built on @ACEStep_Music. DEMON: Diffusion Engine for Musical Orchestrated Noise. It lets you play ACEStep like a musical instrument, remixing songs and loops with feedback that approaches real-time. Its essentially StreamDiffusion but instead of Stable Diffusion it is ACEStep1.5, and instead of images it is full songs. It runs on 30/40/5090. Built with @DaydreamLiveAI team, testing, and building the demo. We are hosting it if you want to try it without installing. For full details, links, and writeup please see the pinned project page.