ComfyUI workflow generates BGM with Stable Audio 3 then audio-reactive animation
11/17/2026 — 11/17, 00:19·1 sources (all)·1 reports (all)
Key takeaways
- A DEV community author shared two ComfyUI workflows that first generate background music with Stable Audio 3 and then use LTX 2.3 to create…
Background & analysis
On November 17, 2026, an author writing in the AI section of DEV Community shared two ComfyUI workflows that chain Stable Audio 3 and LTX 2.3 in sequence. The approach first uses Stable Audio 3 to generate background music, then feeds that audio to LTX 2.3 so it can produce reaction animations that respond to the sound. The author notes that most video pipelines treat audio as material added only after the picture is finished, whereas these two graphs take the opposite route: the sound is produced first and the image is then built to react to it. In the author's framing, this is a modest structural change that substantially changes how the finished result feels.
The author also published the node counts for both graphs. The audio graph, which handles the Stable Audio 3 score, is the smaller one at 24 nodes and stays purely in the audio domain. Within that graph, EmptyLatentAudio is set to 60 latent frames, CLIPLoader loads t5gemma_b_b_ul2.safetensors with the type set to stable_audio, and SaveAudioMP3 writes the result to audio/stable_audio_3 at quality V0. The animation graph, driven by LTX 2.3, is far larger at 113 nodes. At this point the available record consists only of this single community walkthrough with its parameters, and there is no sign of follow-up development, a maintainer response, or any official statement about the workflow.
AI-generated from 1 reports · updated 12 hours ago
- Heat index
- 70
- All sources
- 1
- All reports
- 1
- First seen
- 13 hours ago
Reports on this story headlines open the original
A DEV Community author shared two ComfyUI workflows that generate background music with Stable Audio 3 first, then use LTX 2.3 to create audio-reactive animation. The author argues this makes audio the starting point rather than a post-production layer, and details the 24-node audio graph and 113-node video graph.
DEV Community · AIAI score 65
Other stories people are talking about
- Heat index 56Tutorial: building an Image Studio image-generation app with ComfyUI1 sources
- Heat index 70LongCat Avatar releases multi-shot digital human ComfyUI workflows1 sources
- Heat index 1345RisingNvidia board not discussing Jensen Huang's return, probe into his conduct advances22 sources
- Heat index 1241SurgeCalifornia Sues OpenAI Over Agents Escaping Tests, Intruding into Hugging Face15 sources
- Heat index 901Alibaba releases MoE model Qwen4-Max with 1M token context for low-cost, long-running tasks17 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

