Flux 3 Text to Video - ComfyUI Built-in Node Documentation

Generates a video with synchronized audio from a text prompt using FLUX 3. The node sends your prompt to the FLUX 3 service, waits for the generation to finish, and returns the completed video clip.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	What you want, in plain language; the prompt is interpreted and expanded before generation. Describe ambient sound, music and speech separately for layered audio. (default: "")	STRING	Yes	Multiline text
`aspect_ratio`	Output aspect ratio. ‘auto’ picks one from the prompt and inputs. (default: “auto”)	COMBO	Yes	Multiple options available, including `"auto"`
`duration`	Clip length in seconds. ‘auto’ fits the length to the content. (default: “auto”)	COMBO	Yes	Multiple options available, including `"auto"`
`resolution`	Output resolution. (default: “720p”)	COMBO	Yes	`"720p"` `"1080p"` `"1440p"` `"2160p"`
`generate_audio`	Generate synchronized audio (ambient, speech, effects). Off produces a video with no audio track. (default: True)	BOOLEAN	Yes	True False
`safety_tolerance`	Moderation tolerance, 0 is the strictest. Requests that send images or video are capped at 2 whatever you set here. (default: 2)	INT	Yes	0 to 4
`seed`	Seed to determine if node should re-run; FLUX 3 picks its own seed, so actual results are nondeterministic regardless of this value. (default: 42)	INT	Yes	0 to 4294967295

Note: safety_tolerance is an advanced input. The seed input includes Control After Generate controls in the UI. The displayed price is based on resolution and duration: HD (720p) is charged at $0.2431 per second and FHD (1080p) at $0.4147 per second. QHD (1440p) is charged at $0.572 per second and UHD (2160p) at $1.144 per second. When a fixed duration is chosen, the total estimated cost for the clip is shown; when duration is “auto”, the per-second rate is shown.

Outputs

Output Name	Description	Data Type
`video`	The generated video clip, with synchronized audio when `generate_audio` is enabled.	VIDEO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 2fa8c715c8467e2a2a3e131875d3b459a5599c2bab550656670aa1461e896aab

​Inputs

​Outputs

Inputs

Outputs