Add MiniMax and PinkCherry LTX as pickable video engines, with still or text start.

Shot 1 can run text-to-video; later shots still extend from the last frame. Recommend output is also normalized into shot-script cards.

Co-authored-by: Cursor <cursoragent@cursor.com>

server/utils/workflow.ts

@@ -1,9 +1,18 @@
 // Nitro bundles these JSON graphs into the production server output.
 import workflowV1 from '../assets/workflow_minimax_video.json'
 import workflowV2 from '../assets/workflow_minimax_video_v2.json'
+import workflowLtx from '../assets/workflow_ltx_video.json'
 import { buildIdentityPrompt } from '~/utils/identityPrompt'
+import {
+  isLtxWorkflow,
+  isTextToVideo,
+  LTX_NEGATIVE,
+  parseVideoWorkflow,
+  type VideoWorkflowId
+} from '~/utils/videoModels'
 
-export type VideoWorkflowId = 'v1' | 'v2'
+export type { VideoWorkflowId }
+export { parseVideoWorkflow }
 
 export interface GenerateParams {
   prompt: string
@@ -31,6 +40,7 @@ type WorkflowGraph = Record<string, WorkflowNode>
 
 const PROMPT_CLASSES = new Set([
   'MiniMaxH3ImageToVideo',
+  'MiniMaxH3TextToVideo',
   'MiniMaxH3ReferenceToVideo',
   'CLIPTextEncode',
   'CLIPTextEncodeQwen3VL',
@@ -58,16 +68,15 @@ function titleOf(node: WorkflowNode) {
 }
 
 function templateFor(id: VideoWorkflowId) {
+  if (isLtxWorkflow(id)) return workflowLtx as WorkflowGraph
   return (id === 'v2' ? workflowV2 : workflowV1) as WorkflowGraph
 }
 
-export function parseVideoWorkflow(raw: unknown): VideoWorkflowId {
-  return String(raw || '').trim() === 'v2' ? 'v2' : 'v1'
-}
-
 export function buildWorkflow(params: GenerateParams) {
-  const version = params.workflow === 'v2' ? 'v2' : 'v1'
-  const graph = structuredClone(templateFor(version))
+  const version = parseVideoWorkflow(params.workflow)
+  if (isLtxWorkflow(version)) return buildLtxWorkflow(params, version)
+
+  const graph = structuredClone(templateFor(version === 't2v' ? 'v1' : version === 'v2' ? 'v2' : 'v1'))
   const width = snap32(params.width)
   const height = snap32(params.height)
   const refs = Array.from({ length: 4 }, (_, index) => String(params.referenceImageNames?.[index] || '').trim())
@@ -155,7 +164,7 @@ export function buildWorkflow(params: GenerateParams) {
     }
   }
 
-  if (version === 'v1' && graph['128']?.class_type === 'ImageScaleToTotalPixels') {
+  if (version === 'v1' && !isTextToVideo(version) && graph['128']?.class_type === 'ImageScaleToTotalPixels') {
     graph['128'] = {
       class_type: 'ImageScale',
       inputs: {
@@ -169,7 +178,7 @@ export function buildWorkflow(params: GenerateParams) {
     }
   }
 
-  if (version === 'v1') {
+  if (version === 'v1' || version === 't2v') {
     graph['105:cfg'] = {
       class_type: 'FluxGuidance',
       inputs: {
@@ -191,10 +200,11 @@ export function buildWorkflow(params: GenerateParams) {
       graph[qualityId].inputs.value = params.turbo ? 20 : params.steps
     }
     if (turboId && graph[turboId]?.class_type === 'PrimitiveInt') {
-      graph[turboId].inputs.value = params.turbo ? params.steps : (params.workflow === 'v2' ? 6 : 8)
+      graph[turboId].inputs.value = params.turbo ? params.steps : (version === 'v2' ? 6 : 8)
     }
   }
 
+  if (version === 't2v') applyMinimaxTextToVideo(graph, params, width, height)
   if (version === 'v2') applyV2IdentityPath(graph, params, useRefs, refs, graphPrompt)
 
   if (params.sound === false) {
@@ -203,6 +213,7 @@ export function buildWorkflow(params: GenerateParams) {
     if (graph['105:91']?.inputs) delete graph['105:91'].inputs.audio
     delete graph['163']
     if (graph['172']?.inputs) delete graph['172'].inputs.audio
+    if (graph['105:104']?.inputs) delete graph['105:104'].inputs.audio_vae
   }
 
   return graph
@@ -210,10 +221,76 @@ export function buildWorkflow(params: GenerateParams) {
 
 function promptForNode(classType: string, useRefs: boolean, actionPrompt: string, graphPrompt: string) {
   if (classType === 'MiniMaxH3ImageToVideo') return useRefs ? '' : actionPrompt
+  if (classType === 'MiniMaxH3TextToVideo') return actionPrompt
   if (classType === 'MiniMaxH3ReferenceToVideo') return useRefs ? graphPrompt : actionPrompt
   return graphPrompt
 }
 
+function applyMinimaxTextToVideo(graph: WorkflowGraph, params: GenerateParams, width: number, height: number) {
+  const node = graph['105:104']
+  if (node) {
+    node.class_type = 'MiniMaxH3TextToVideo'
+    node._meta = { title: 'MiniMax H3 Text to Video' }
+    delete node.inputs.first_frame
+    node.inputs.prompt = params.prompt
+    node.inputs.width = width
+    node.inputs.height = height
+    if (params.sound !== false && graph['105:24']) node.inputs.audio_vae = ['105:24', 0]
+    else delete node.inputs.audio_vae
+  }
+  delete graph['114']
+  delete graph['119']
+  delete graph['120']
+  delete graph['127']
+  delete graph['128']
+}
+
+function buildLtxWorkflow(params: GenerateParams, version: VideoWorkflowId) {
+  const graph = structuredClone(workflowLtx as WorkflowGraph)
+  const width = snap32(params.width)
+  const height = snap32(params.height)
+  const textToVideo = isTextToVideo(version)
+  if (graph['4']?.inputs) graph['4'].inputs.image = params.imageName
+  if (graph['5']?.inputs) {
+    graph['5'].inputs.width = width
+    graph['5'].inputs.height = height
+  }
+  if (graph['6']?.inputs) graph['6'].inputs.text = params.prompt
+  if (graph['7']?.inputs) graph['7'].inputs.text = LTX_NEGATIVE
+  if (graph['8']?.inputs && typeof graph['8'].inputs.length === 'number') graph['8'].inputs.length = params.length
+  if (graph['9']?.inputs) graph['9'].inputs.frame_rate = params.fps
+  if (graph['10']?.inputs) graph['10'].inputs.cfg = params.cfg
+  if (graph['11']?.inputs) graph['11'].inputs.sampler_name = params.samplerName || 'euler'
+  if (graph['12']?.inputs) graph['12'].inputs.steps = params.steps
+  if (graph['13']?.inputs) graph['13'].inputs.noise_seed = params.seed
+  if (graph['16']?.inputs) {
+    graph['16'].inputs.frame_rate = params.fps
+    graph['16'].inputs.filename_prefix = params.filenamePrefix || 'video/LTX23'
+  }
+  if (graph['21']?.inputs) graph['21'].inputs.strength_model = 1
+  if (textToVideo) {
+    delete graph['4']
+    delete graph['5']
+    graph['8'] = {
+      class_type: 'EmptyLTXVLatentVideo',
+      inputs: {
+        width,
+        height,
+        length: params.length,
+        batch_size: 1
+      },
+      _meta: { title: 'Empty LTX latent' }
+    }
+    if (graph['9']?.inputs) {
+      graph['9'].inputs.positive = ['6', 0]
+      graph['9'].inputs.negative = ['7', 0]
+    }
+    if (graph['12']?.inputs) graph['12'].inputs.latent = ['8', 0]
+    if (graph['14']?.inputs) graph['14'].inputs.latent_image = ['8', 0]
+  }
+  return graph
+}
+
 function applyV2IdentityPath(
   graph: WorkflowGraph,
   params: GenerateParams,
@@ -304,9 +381,10 @@ function labelsFrom(template: WorkflowGraph) {
 export const NODE_LABELS: Record<string, string> = {
   ...Object.fromEntries(labelsFrom(workflowV1 as WorkflowGraph)),
   ...Object.fromEntries(labelsFrom(workflowV2 as WorkflowGraph)),
+  ...Object.fromEntries(labelsFrom(workflowLtx as WorkflowGraph)),
   ...LABEL_OVERRIDES
 }
 
 export function isEncodingNode(node: string) {
-  return node === '92' || node === '105:91' || node === '172' || /encoding|saving mp4|create video/i.test(NODE_LABELS[node] || '')
+  return node === '92' || node === '16' || node === '105:91' || node === '172' || /encoding|saving mp4|create video|save mp4/i.test(NODE_LABELS[node] || '')
 }