Inputs
Common Inputs
Omni Flash 1.2 Inputs
Omni Flash 1.1 Inputs
Omni Flash Inputs
Reference Inputs
Notes:
- The
promptmust not be empty; the node raises an error if it is. - The
text_to_videotask generates from the prompt alone — attaching images or videos raises an error. - The
image_to_videotask accepts images only (no videos) and requires exactly 1 or 2 images: the first is the starting frame and the optional second is the ending frame. - The
edittask (all models) and theextendtask (Omni Flash 1.1 and 1.2 only) require exactly one input video and keep the aspect ratio of that input video, overridingaspect_ratio. - At most 14 images and 3 videos can be attached. Each attached video must be 10 seconds or shorter, 15 seconds or shorter with Omni Flash 1.2, and 25 seconds or shorter for the
extendtask, whose result can be at most 30 seconds long. - Omni Flash always outputs 720p 24 FPS video with audio; resolution selection is only available with Omni Flash 1.1 and 1.2.
temperatureandtop_pcontrols are only available with the Omni Flash model; Omni Flash 1.1 and 1.2 use fixed generation settings.
Outputs
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):
1fc6017d4d6fbce8f04b2f0ded496553074b8498e3b7342179550fc768698897