@kristopolous78921

I realized the full pipeline didn't exist, you could run it locally and the amd machines were great at this. Also some new features of qwen 3.6 series such as their ASR models made this especially useful. So these are all locally run on open-weight models. Anyone with a sufficiently powerful Radeon or an Nvidia card can do this. Also they can modify any step in the pipeline and regenerate so it's fully controllable. The pipeline is as follows. Qwen does the initial lyric creation, then Acestep does the music, Qwen ASR does timestamp extraction, images are either generative or captured through a web search agent, ltx makes it with the right time constraints and then ffmpeg tapes them together and overlays the initial audio. You can do it in 3 levels of complexity (low/medium/high) depending on how much you want to wait

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.