Add image-to-text Describe on the bench via exclusive llama.cpp caption jobs.

This commit is contained in:
Towsty
2026-09-30 22:50:19 -05:00
parent 9481791ac5
commit 15ef891b26
15 changed files with 937 additions and 35 deletions
+50
View File
@@ -0,0 +1,50 @@
import { validateCaptionBody } from '~/shared/caption.mjs'
import { addStudioJob, kickStudioQueue, type StudioJobPayload } from '~/server/utils/studioQueue'
import { getStill } from '~/server/utils/library'
export default defineEventHandler(async (event) => {
const { owner } = assertLibraryOwner(event)
const raw = await readBody(event)
let body: ReturnType<typeof validateCaptionBody>
try {
body = validateCaptionBody(raw)
} catch (e: any) {
throw createError({ statusCode: e.statusCode || 400, statusMessage: e.message })
}
assertFolderAccess(event, body.folderId)
const still = getStill(owner, body.stillId)
assertFolderAccess(event, still.folderId)
const row = await addStudioJob({
ownerKey: owner,
kind: 'caption',
familyId: crypto.randomUUID(),
payload: {
prompt: `Describe · ${body.captionStyle}`,
name: `Describe · ${body.captionStyle}`,
folderId: body.folderId,
stillId: still.id,
captionStyle: body.captionStyle,
aspect: 'auto',
width: 0,
height: 0,
steps: 1,
turbo: true,
seed: 0,
cfg: 0,
fps: 24,
samplerName: 'euler',
scheduler: 'simple',
duration: 0,
sound: false,
workflow: 'minimax',
useIdentityRefs: false,
hideThumbnail: false,
referenceStillIds: [],
extensions: [],
queueAutoRun: true
} as StudioJobPayload
})
kickStudioQueue()
return { id: row.id, liveJobId: row.liveJobId, captionStyle: body.captionStyle, stillId: still.id }
})
+6 -1
View File
@@ -48,7 +48,7 @@ export default defineEventHandler(async () => {
host: comfy.host || '',
queueRunning: queue.running,
queuePending: queue.pending,
asleep: Boolean(control?.asleep) && !comfyReachable && !control?.yue2?.busy,
asleep: Boolean(control?.asleep) && !comfyReachable && !control?.yue2?.busy && !control?.caption?.busy,
processUp: Boolean(control?.process ?? control?.processUp),
lastActivityAt: control?.lastActivityAt || null,
stats: comfy.ok ? comfy.stats : undefined
@@ -58,6 +58,11 @@ export default defineEventHandler(async () => {
busy: Boolean(control?.yue2?.busy),
backend: control?.yue2?.backend || 'yue2'
},
caption: {
configured: Boolean(control?.caption?.configured),
busy: Boolean(control?.caption?.busy),
backend: control?.caption?.backend || 'llama.cpp'
},
imageComfy: {
configured: imageConfigured,
ok: imageOk,
+2 -1
View File
@@ -10,13 +10,14 @@ export default defineEventHandler((event) => {
|| job.status === 'running'
|| job.status === 'held'
|| (job.status === 'error' && Date.now() - job.updatedAt < 60 * 60 * 1000)
|| (job.kind === 'caption' && job.status === 'complete' && Date.now() - job.updatedAt < 60 * 60 * 1000)
))
const claimed = new Set(active.map(job => job.shotQueueId).filter(Boolean) as string[])
const queues = listShotQueues(owner)
const byId = new Map(queues.map(queue => [queue.id, queue]))
const jobs = active.map((job) => {
const shots = job.shotQueueId ? byId.get(job.shotQueueId) || null : null
const kind = job.kind === 'edit' ? 'edit' : job.kind === 'music' ? 'music' : 'video'
const kind = job.kind === 'edit' ? 'edit' : job.kind === 'music' ? 'music' : job.kind === 'caption' ? 'caption' : 'video'
const shotSummary = shots ? summarizeQueue(shots) : null
const plannedShots = shotSummary
? undefined