FLUX 3 Video: Text to Video
Generate full videos from a single text prompt with Flux.3, which expands natural language into complete scenes with synchronized audio, no reference images or complex settings needed. Outputs 1 video in 720p at 24fps, 5 to 20 seconds long, supporting any aspect ratio from 9:16 to 21:9 with built-in sound design. Ideal for quick social media clips, ad mockups, and concept films requiring realistic motion and cinematic style.
Try an example
About this workflow
This ComfyUI workflow turns a single text prompt into a finished video clip using the Flux 3 model. The Flux3TextToVideoNode interprets natural language into a complete moving scene with coherent action, camera motion, and synchronized sound. It’s designed for quick turnarounds: you set the prompt, pick a duration between 5–20 seconds, choose an aspect ratio from 9:16 to 21:9, and the node generates a 720p, 24 fps result with built-in audio.
Technically, the pipeline is minimal and focused. Flux3TextToVideoNode handles end-to-end generation from text, returning the video content (and its audio track) at the requested length, frame rate, and aspect ratio. The SaveVideo node then writes the output to disk as a single playable file. With only two nodes, it’s easy to understand, fast to set up, and reliable for creating social-ready clips, ad mockups, and cinematic concept shots without extra reference images or complex settings.
Questions & answers
Open Flux3TextToVideoNode and set the duration (any value between 5 and 20 seconds) and choose an aspect ratio (e.g., 9:16, 1:1, 16:9, 21:9). The node will render 720p at 24 fps to match those settings.
Flux3TextToVideoNode is designed to run via an API in many setups. If your version uses a hosted endpoint, you’ll need a valid API key and internet access, not a local GPU. Check the node’s parameters for authentication requirements.
Flux3TextToVideoNode generates synchronized audio with the clip. This workflow saves that track as-is. For a silent version or custom music, export the clip, then mute/replace the audio in your video editor or adapt the workflow with nodes that strip or swap audio.
Be explicit about subject, motion, and tone. Include camera directives (e.g., "slow dolly-in," "handheld, slight shake"), lighting ("golden hour rim light"), environment cues, and audio mood ("subtle city ambience"). Keep within the 5–20s range for stable timing.