towsty/aigen
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Ship MiniMax v2 identity refs and Qwen sidecar edits.

Browse Source 
Keep v1 as the default video graph, relay image edits to the Qwen Lightning box, and keep /api/health up if one Comfy host is unset.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Towsty
2026-08-26 14:29:15 -05:00
co-authored by Cursor
parent 551c29a62a
commit c55a48a57e
22 changed files with 2061 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files
server/utils/workflow.ts
+130 -26
View File
@@ -1,5 +1,8 @@
// Nitro bundles this JSON into the production server output.
import workflowTemplate from '../assets/workflow_minimax_video.json'
// 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'
export type VideoWorkflowId = 'v1' | 'v2'
export interface GenerateParams {
prompt: string
@@ -16,6 +19,10 @@ export interface GenerateParams {
scheduler: string
filenamePrefix?: string
sound?: boolean
workflow?: VideoWorkflowId
duration?: number
useIdentityRefs?: boolean
referenceImageNames?: string[]
}
type WorkflowNode = { class_type: string; inputs: Record<string, unknown>; _meta?: { title?: string } }
@@ -23,6 +30,7 @@ type WorkflowGraph = Record<string, WorkflowNode>
const PROMPT_CLASSES = new Set([
'MiniMaxH3ImageToVideo',
'MiniMaxH3ReferenceToVideo',
'CLIPTextEncode',
'CLIPTextEncodeQwen3VL',
'TextEncodeQwen3VL'
@@ -30,6 +38,7 @@ const PROMPT_CLASSES = new Set([
const SEED_CLASSES = new Set(['RandomNoise', 'KSampler', 'SamplerMiniMax', 'KSamplerAdvanced'])
const IMAGE_CLASSES = new Set(['LoadImage'])
const LORA_CLASSES = new Set(['LoraLoaderModelOnly', 'LoraLoader'])
const V2_REF_LOADERS = ['140', '141', '142', '143'] as const
function entriesOf(graph: WorkflowGraph, classType: string) {
return Object.entries(graph).filter(([, node]) => node.class_type === classType)
@@ -47,13 +56,24 @@ function titleOf(node: WorkflowNode) {
return node._meta?.title || ''
}
function templateFor(id: VideoWorkflowId) {
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 graph = structuredClone(workflowTemplate) as WorkflowGraph
const version = params.workflow === 'v2' ? 'v2' : 'v1'
const graph = structuredClone(templateFor(version))
const width = snap32(params.width)
const height = snap32(params.height)
const refs = (params.referenceImageNames || []).map(name => String(name || '').trim()).filter(Boolean).slice(0, 4)
const useRefs = version === 'v2' && params.useIdentityRefs === true && refs.length > 0
for (const [, node] of Object.entries(graph)) {
if (IMAGE_CLASSES.has(node.class_type) && 'image' in node.inputs) {
for (const [id, node] of Object.entries(graph)) {
if (IMAGE_CLASSES.has(node.class_type) && 'image' in node.inputs && id === '114') {
node.inputs.image = params.imageName
}
@@ -64,9 +84,14 @@ export function buildWorkflow(params: GenerateParams) {
if (node.class_type === 'MiniMaxH3ImageToVideo') {
node.inputs.prompt = params.prompt
node.inputs.width = width
node.inputs.height = height
node.inputs.length = params.length
if (typeof node.inputs.width === 'number') node.inputs.width = width
if (typeof node.inputs.height === 'number') node.inputs.height = height
if (typeof node.inputs.length === 'number') node.inputs.length = params.length
}
if (node.class_type === 'MiniMaxH3ReferenceToVideo') {
node.inputs.prompt = params.prompt
if (!Array.isArray(node.inputs.length)) node.inputs.length = ['174', 1]
}
if (node.class_type === 'CreateVideo' && 'fps' in node.inputs) {
@@ -93,7 +118,7 @@ export function buildWorkflow(params: GenerateParams) {
if ('seed' in node.inputs) node.inputs.seed = params.seed
}
if (LORA_CLASSES.has(node.class_type)) {
if (LORA_CLASSES.has(node.class_type) && !/identity|ref 1/i.test(titleOf(node))) {
node.inputs.strength_model = params.turbo ? 1 : 0
}
@@ -101,11 +126,22 @@ export function buildWorkflow(params: GenerateParams) {
node.inputs.filename_prefix = params.filenamePrefix || node.inputs.filename_prefix || 'video/MiniMax_H3'
}
if (node.class_type === 'PrimitiveBoolean') {
if (node.class_type === 'PrimitiveBoolean' && /lightning|turbo/i.test(titleOf(node))) {
node.inputs.value = params.turbo
}
if (node.class_type === 'ComfySwitchNode' && typeof node.inputs.switch === 'boolean') {
if (node.class_type === 'PrimitiveBoolean' && /identity|ref2va|reference/i.test(titleOf(node))) {
node.inputs.value = useRefs
}
if (node.class_type === 'PrimitiveFloat' && /duration/i.test(titleOf(node))) {
const seconds = typeof params.duration === 'number' && params.duration > 0
? params.duration
: params.length / Math.max(params.fps, 1)
node.inputs.value = seconds
}
if (node.class_type === 'ComfySwitchNode' && typeof node.inputs.switch === 'boolean' && /lightning|turbo|lora/i.test(titleOf(node))) {
node.inputs.switch = params.turbo
}
@@ -114,7 +150,7 @@ export function buildWorkflow(params: GenerateParams) {
}
}
if (graph['128']) {
if (version === 'v1' && graph['128']?.class_type === 'ImageScaleToTotalPixels') {
graph['128'] = {
class_type: 'ImageScale',
inputs: {
@@ -128,16 +164,18 @@ export function buildWorkflow(params: GenerateParams) {
}
}
graph['105:cfg'] = {
class_type: 'FluxGuidance',
inputs: {
guidance: params.cfg,
conditioning: ['105:104', 0]
},
_meta: { title: 'Guidance scale' }
}
if (graph['105:16']?.inputs) {
graph['105:16'].inputs.conditioning = ['105:cfg', 0]
if (version === 'v1') {
graph['105:cfg'] = {
class_type: 'FluxGuidance',
inputs: {
guidance: params.cfg,
conditioning: ['105:104', 0]
},
_meta: { title: 'Guidance scale' }
}
if (graph['105:16']?.inputs) {
graph['105:16'].inputs.conditioning = ['105:cfg', 0]
}
}
for (const [, node] of entriesOf(graph, 'ComfySwitchNode')) {
@@ -152,15 +190,69 @@ export function buildWorkflow(params: GenerateParams) {
}
}
if (version === 'v2') applyV2IdentityPath(graph, params, useRefs, refs)
if (params.sound === false) {
delete graph['105:23']
delete graph['105:24']
if (graph['105:91']?.inputs) delete graph['105:91'].inputs.audio
delete graph['163']
if (graph['172']?.inputs) delete graph['172'].inputs.audio
}
return graph
}
function applyV2IdentityPath(
graph: WorkflowGraph,
params: GenerateParams,
useRefs: boolean,
refs: string[]
) {
if (useRefs && graph['155'] && graph['167'] && graph['168']) {
graph['167'].inputs.latent_image = ['155', 1]
graph['168'].inputs.conditioning = ['155', 0]
graph['155'].inputs.prompt = params.prompt
graph['155'].inputs.length = ['174', 1]
delete graph['173']
V2_REF_LOADERS.forEach((id, index) => {
const name = refs[index]
const inputKey = `ref_images.ref_image_${index + 1}`
if (name && graph[id]) {
graph[id].inputs.image = name
} else {
delete graph[id]
if (graph['155']?.inputs) delete graph['155'].inputs[inputKey]
}
})
graph['v2:cfg'] = {
class_type: 'FluxGuidance',
inputs: {
guidance: params.cfg,
conditioning: ['155', 0]
},
_meta: { title: 'Guidance scale' }
}
graph['168'].inputs.conditioning = ['v2:cfg', 0]
return
}
delete graph['155']
delete graph['150']
for (const id of V2_REF_LOADERS) delete graph[id]
if (graph['173'] && graph['168']) {
graph['v2:cfg'] = {
class_type: 'FluxGuidance',
inputs: {
guidance: params.cfg,
conditioning: ['173', 0]
},
_meta: { title: 'Guidance scale' }
}
graph['168'].inputs.conditioning = ['v2:cfg', 0]
}
}
const LABEL_OVERRIDES: Record<string, string> = {
'114': 'Loading image',
'128': 'Scaling image',
@@ -168,6 +260,14 @@ const LABEL_OVERRIDES: Record<string, string> = {
'119': 'Scaling image',
'120': 'Reading image size',
'92': 'Saving MP4',
'140': 'Loading identity ref 1',
'141': 'Loading identity ref 2',
'142': 'Loading identity ref 3',
'143': 'Loading identity ref 4',
'150': 'Identity references',
'155': 'Reference to video',
'172': 'Encoding video',
'173': 'Image to video',
'105:6': 'Loading MiniMax H3 model',
'105:11': 'Loading video VAE',
'105:13': 'Loading Qwen3-VL encoder',
@@ -177,6 +277,7 @@ const LABEL_OVERRIDES: Record<string, string> = {
'105:14': 'Sampling',
'105:16': 'Preparing guider',
'105:cfg': 'Applying guidance',
'v2:cfg': 'Applying guidance',
'105:17': 'Selecting sampler',
'105:23': 'Decoding audio',
'105:24': 'Loading audio VAE',
@@ -192,13 +293,16 @@ const LABEL_OVERRIDES: Record<string, string> = {
'105:126': 'Selecting turbo LoRA'
}
function labelsFrom(template: WorkflowGraph) {
return Object.entries(template).map(([id, node]) => [id, node._meta?.title || `Node ${id}`] as const)
}
export const NODE_LABELS: Record<string, string> = {
...Object.fromEntries(
Object.entries(workflowTemplate as WorkflowGraph).map(([id, node]) => [id, node._meta?.title || `Node ${id}`])
),
...Object.fromEntries(labelsFrom(workflowV1 as WorkflowGraph)),
...Object.fromEntries(labelsFrom(workflowV2 as WorkflowGraph)),
...LABEL_OVERRIDES
}
export function isEncodingNode(node: string) {
return node === '92' || node === '105:91' || /encoding|saving mp4/i.test(NODE_LABELS[node] || '')
return node === '92' || node === '105:91' || node === '172' || /encoding|saving mp4|create video/i.test(NODE_LABELS[node] || '')
}