Skip to main content
This page documents the complete LongLive-2.0 wire surface: every command you send with reactor.sendCommand(), the events the model emits back, and an end-to-end example. For the conceptual model and a quick start, see the overview. LongLive-2.0 outputs a single video track, main_video, in chunks of 29 frames (~1.2s at 24fps). Transitions take effect on chunk boundaries. See Chunks, scenes, and length for how the per-scene 48-chunk budget and the cumulative session_chunk clock work.

​
Commands

Send commands to the model using reactor.sendCommand(). Below are all available commands:
CommandDescription
set_shotSet the opening shot, or queue a soft transition (keeps the scene)
scene_cutQueue a hard cut to a new scene (purges memory, fresh 48-chunk budget)
schedule_shotPlant a soft shot at a specific session_chunk
schedule_scene_cutPlant a hard cut at a specific session_chunk
startBegin generating video on main_video
pausePause generation after the current chunk
resumeResume generation from a pause
resetAbort, clear the prompt and all scheduled beats, return to idle
set_seedSet the noise seed (read once at start)

​
set_shot

Set the opening shot before start, or queue a soft shot change mid-stream. A shot keeps the scene’s attention memory (the “sink tokens”) and continuity, swapping the prompt conditioning. Use it for a new beat within the same world (a camera move, an action, a time skip). Mid-stream it activates at the next chunk boundary and spends from the current scene’s 48-chunk budget.Acknowledged by shot_set; rejected with command_error if the prompt is empty.Parameters:
ParameterTypeRequiredDescription
promptstringYesThe shot’s prompt text
Example:
// Opening shot (before start)
await reactor.sendCommand("set_shot", {
  prompt: "A lone astronaut walks across a windswept red dune at golden hour",
});

// Soft transition mid-stream: same world, new beat
await reactor.sendCommand("set_shot", {
  prompt: "The camera pulls back to reveal a vast crater on the horizon",
});

​
Messages from model

The model emits these events. Subscribe with reactor.on("message", ...) (or the generated React hooks). Every message is delivered as JSON { "type": "<name>", "data": { … } }.
EventWhenPayload
shot_setA set_shot was accepted{ prompt: string }
scene_cutA scene_cut fired (immediate or scheduled){ prompt: string, at_session_chunk: int }
shot_scheduledA schedule_shot was accepted{ prompt: string, at_session_chunk: int }
scene_cut_scheduledA schedule_scene_cut was accepted{ prompt: string, at_session_chunk: int }
generation_startedstart succeeded, frames begin{ prompt: string, chunk_num: int, frame_num: int }
chunk_completeOnce per completed chunk of main_video{ chunk_index: int, session_chunk: int, frames_emitted: int, active_prompt: string }
generation_pausedIn response to pause{ chunk_index: int }
generation_resumedIn response to resume{ chunk_index: int }
generation_resetIn response to reset{ reason: string }
generation_completeA scene reached the chunk ceiling with no cut{ total_chunks: int }
command_errorA command was rejected (bad precondition){ command: string, reason: string }
stateOn connect, after every command, after each chunkFull session snapshot (see below)

​
state payload

state is the single source of truth for the session’s observable state. Subscribe once and treat it as the authoritative session snapshot; you generally do not need to track individual command acknowledgements and chunk_complete events yourself.
FieldTypeMeaning
runningboolstarted && !paused. Equivalent to “frames are actively streaming”
startedboolTrue once start has been accepted; remains true through pauses. False on reset
pausedboolTrue while generation is paused
current_chunkintChunks since the current scene began; resets to 0 on every scene_cut
session_chunkintCumulative chunks since start; never resets. The clock scheduled beats fire against
current_frameintFrames emitted on main_video so far
current_promptstring | nullThe prompt currently driving generation, or null if none set
has_promptboolWhether an opening shot has been set this session
seedintCurrent seed value (effective only on the next start)
scheduled_shotsint[]session_chunk indices of pending scheduled shots
scheduled_scene_cutsint[]session_chunk indices of pending scheduled cuts

​
Complete example

import { LongliveV2Model } from "@reactor-models/longlive-v2";

const longlive = new LongliveV2Model();

longlive.onChunkComplete(({ session_chunk, active_prompt }) => {
  console.log(`chunk ${session_chunk}: ${active_prompt}`);
});
longlive.onCommandError(({ command, reason }) => {
  console.error(`${command} rejected: ${reason}`);
});

await longlive.connect(jwt);

// Compose the storyboard before starting:
await longlive.setShot({ prompt: "A lone astronaut walks across a red dune at golden hour" });
await longlive.scheduleShot({
  prompt: "The camera pulls back to reveal a vast crater",
  at_session_chunk: 20,
});
await longlive.scheduleSceneCut({
  prompt: "Hard cut: a neon-lit Tokyo street at night",
  at_session_chunk: 40,
});

await longlive.start();