All models

Pruna Video 2

Generate a clip from a prompt, a still or an audio track, with native speech

Generate Videov1.0.09 inputsVIDEO

a hand turning the pages of an old atlas, warm desk lamp

Try it right here

Fill the inputs the node publishes and run it on your own account. The same ports, defaults and types the studio uses.

Inputs

TEXT
IMAGE
First frame
AUDIO
Audio to follow
1 – 20INT
Duration (seconds)
TEXT
TEXT
TEXT
BOOLEAN
INT
Sign in to run

Running a model executes it on your account. Browsing the catalog stays free and needs no account.

Output

Fill in the inputs and run the node to see its output here.

Call it from your code

The same node, called by id from any surface. Every tab pins this node and passes the ports below.

import { BlitClient } from "@blitflow/sdk";

const { runNode } = new BlitClient({ apiKey: process.env.BLITFLOW_TOKEN });

const { outputs } = await runNode("p-video-2", {
  prompt: { value: "example" },
  image: { ref: "https://..." },
  audio: { ref: "https://..." },
  duration: { value: 1 },
  aspectRatio: { value: "16:9" },
  resolution: { value: "720p" },
  framesPerSecond: { value: "24" },
  draft: { value: false },
  seed: { value: 1 },
});

Schema

Every port this node publishes, with its type, its hint and the default it runs with. p-video-2 is the id you call.

Inputs

prompt*TEXT
imageIMAGE
First frame
audioAUDIO
Audio to follow
durationINT
Duration (seconds)
aspectRatioTEXT
16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 1:1
16:9
resolutionTEXT
720p · 1080p
720p
framesPerSecondTEXT
24 · 48
24
draftBOOLEANfalse
seedINT

Outputs

videoVIDEO

Chain it with the rest of the catalog

Open the studio