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 short video using the Flux3TextToVideoNode, then writes the result to a standard video file with SaveVideo. No input image is needed: the prompt alone describes the subject, the motion, the camera and the sound.
The core controls are the prompt, the aspect ratio (auto, or 9:16 to 21:9), the duration (auto, or 5 to 20 seconds), the resolution (720p to 2160p) and the seed for repeatable results. With generate_audio on, the node also creates a synchronized sound track for the clip.
When the generation is done, SaveVideo writes the clip, with its audio, to a single playable file.
Questions & answers
Yes. With generate_audio on (the default), Flux3TextToVideoNode creates a synchronized sound track and SaveVideo keeps it in the file. Turn generate_audio off for a silent clip.
No. This workflow is text-to-video: the prompt is the only required input. To animate a still image, use the FLUX 3 Video image-to-video workflow instead.
Set duration on Flux3TextToVideoNode to a value from 5 to 20 seconds, or to auto to let the model choose a length from the prompt. The output is 24 fps.
Aspect ratio can be auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4 or 9:16. Resolution can be 720p, 1080p, 1440p or 2160p. Higher resolutions take longer to generate.