Add Image v2 as a sibling of Image edit, with separate Klein graphs.

Keep the v1 Image tab on its dual-branch template. The host agent follows Desktop's live port so Coolify stays on :8198. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-28 21:22:37 -05:00
parent 55f8cb1def
commit 21fe2412f9
18 changed files with 1678 additions and 67 deletions
@@ -0,0 +1,255 @@
+import { addStudioJob, kickStudioQueue, listStudioJobs, videoJobsBusy } from '~/server/utils/studioQueue'
+import { comfyConfigured } from '~/server/utils/comfy'
+import { imageDimensions } from '~/server/utils/resolution'
+import { clampImageCfg, clampImageScaleMegapixels, clampImageSteps } from '~/utils/generationPresets'
+import {
+  IMAGE_V2_CFG_DEFAULT,
+  IMAGE_V2_CONSISTENCY_CLIP,
+  IMAGE_V2_CONSISTENCY_MODEL,
+  IMAGE_V2_SNOFS_CLIP,
+  IMAGE_V2_SNOFS_MODEL,
+  IMAGE_V2_STEPS_DEFAULT,
+  IMAGE_V2_TURBO_CFG,
+  IMAGE_V2_TURBO_STEPS,
+  clampImageV2Strength,
+  parseImageV2Mode,
+  parseImageV2Task,
+  type ImageV2Mode,
+  type ImageV2Task
+} from '~/utils/imageV2'
+import { getStill, rememberInputStill, stillPath } from '~/server/utils/library'
+import { existsSync, readFileSync } from 'node:fs'
+
+type ImageFile = { filename: string; data: Buffer; type?: string }
+
+function parseBool(raw: unknown) {
+  return raw === true || raw === 'true' || raw === '1' || raw === 1
+}
+
+function isHttpUrl(value: string) {
+  return /^https?:\/\//i.test(value)
+}
+
+async function fileFromUrl(url: string): Promise<ImageFile> {
+  const res = await fetch(url, { signal: AbortSignal.timeout(20_000) })
+  if (!res.ok) {
+    throw createError({ statusCode: 400, statusMessage: `Could not fetch image (${res.status})` })
+  }
+  const mime = String(res.headers.get('content-type') || 'image/png').split(';')[0]
+  if (!/^image\//i.test(mime)) {
+    throw createError({ statusCode: 400, statusMessage: 'image_a / image_b URL must be an image' })
+  }
+  const data = Buffer.from(await res.arrayBuffer())
+  if (data.length > 40 * 1024 * 1024) {
+    throw createError({ statusCode: 400, statusMessage: 'Image is too large' })
+  }
+  const ext = mime.includes('jpeg') || mime.includes('jpg') ? '.jpg' : mime.includes('webp') ? '.webp' : '.png'
+  return { filename: `remote${ext}`, data, type: mime }
+}
+
+function fileFromStill(ownerKey: string, id: string): ImageFile {
+  const still = getStill(ownerKey, id)
+  const path = stillPath(ownerKey, still.id)
+  if (!existsSync(path)) {
+    throw createError({ statusCode: 400, statusMessage: 'That still is missing from the library' })
+  }
+  return {
+    filename: still.filename || `${still.id}.png`,
+    data: readFileSync(path),
+    type: 'image/png'
+  }
+}
+
+async function resolveImageRef(ownerKey: string, raw: unknown, uploaded: ImageFile | null) {
+  if (uploaded) return uploaded
+  const value = String(raw || '').trim()
+  if (!value || value === 'null') return null
+  if (isHttpUrl(value)) return fileFromUrl(value)
+  return fileFromStill(ownerKey, value)
+}
+
+function readMultipart(parts: Array<{ name?: string; filename?: string; type?: string; data?: Buffer }> | null) {
+  const fields: Record<string, string> = {}
+  let imageA: ImageFile | null = null
+  let imageB: ImageFile | null = null
+  for (const part of parts || []) {
+    if ((part.name === 'image_a' || part.name === 'image') && part.filename && part.data?.length) {
+      imageA = { filename: part.filename, data: part.data, type: part.type }
+    } else if ((part.name === 'image_b' || part.name === 'image2') && part.filename && part.data?.length) {
+      imageB = { filename: part.filename, data: part.data, type: part.type }
+    } else if (part.name && part.data) {
+      fields[part.name] = part.data.toString('utf8')
+    }
+  }
+  return { fields, imageA, imageB }
+}
+
+export default defineEventHandler(async (event) => {
+  const contentType = String(getHeader(event, 'content-type') || '')
+  let fields: Record<string, unknown> = {}
+  let uploadedA: ImageFile | null = null
+  let uploadedB: ImageFile | null = null
+
+  if (contentType.includes('multipart/form-data')) {
+    const form = await readMultipartFormData(event).catch(() => null)
+    const parsed = readMultipart(form || [])
+    fields = parsed.fields
+    uploadedA = parsed.imageA
+    uploadedB = parsed.imageB
+  } else {
+    fields = await readBody<Record<string, unknown>>(event).catch(() => ({}))
+  }
+
+  const mode = parseImageV2Mode(fields.mode)
+  if (!mode) {
+    throw createError({ statusCode: 400, statusMessage: 'mode must be edit or compose' })
+  }
+  const task = parseImageV2Task(fields.task, 'scene')
+  const prompt = String(fields.prompt || '').trim()
+  if (!prompt) {
+    throw createError({ statusCode: 400, statusMessage: 'A prompt is required' })
+  }
+  if (!comfyConfigured()) {
+    throw createError({
+      statusCode: 503,
+      statusMessage: 'Beast ComfyUI is not configured. Set COMFY_HOST.'
+    })
+  }
+
+  if (mode === 'edit' && (task === 'identity' || task === 'outfit' || task === 'face_lock')) {
+    throw createError({
+      statusCode: 400,
+      statusMessage: `${task} requires Compose and image B. Edit is one image only.`
+    })
+  }
+
+  const ownerKey = libraryOwnerKey(event)
+  const imageA = await resolveImageRef(ownerKey, fields.image_a, uploadedA)
+  const imageB = await resolveImageRef(ownerKey, fields.image_b, uploadedB)
+
+  if (!imageA) {
+    throw createError({ statusCode: 400, statusMessage: 'image_a is required' })
+  }
+  if (mode === 'edit' && imageB) {
+    throw createError({
+      statusCode: 400,
+      statusMessage: 'Edit mode takes one image. Use Compose for two stills.'
+    })
+  }
+  if (mode === 'compose' && !imageB) {
+    throw createError({
+      statusCode: 400,
+      statusMessage: 'Compose requires image_b. Refusing to fall back to one-image generation.'
+    })
+  }
+
+  const library = publicLibrary(event)
+  const folderId = library.folders.some(folder => folder.id === String(fields.folderId || ''))
+    ? String(fields.folderId)
+    : library.folders[0]?.id
+  if (!folderId) {
+    throw createError({ statusCode: 400, statusMessage: 'Create a library folder before generating' })
+  }
+  assertFolderExists(event, folderId)
+
+  const destFolder = library.folders.find(folder => folder.id === folderId)
+  const folderLocked = Boolean(destFolder?.protected && !destFolder.unlocked)
+  const hideInput = parseBool(fields.hideInput)
+  const hideThumbnail = parseBool(fields.hideThumbnail)
+  const turbo = parseBool(fields.turbo)
+  const steps = turbo ? IMAGE_V2_TURBO_STEPS : clampImageSteps(fields.steps, IMAGE_V2_STEPS_DEFAULT)
+  const cfg = turbo ? IMAGE_V2_TURBO_CFG : clampImageCfg(fields.cfg, IMAGE_V2_CFG_DEFAULT)
+  const megapixels = clampImageScaleMegapixels(fields.megapixels ?? fields.scaleMegapixels, 1)
+  const seed = fields.seed && String(fields.seed) !== 'random'
+    ? Number(fields.seed)
+    : Math.floor(Math.random() * 2_147_483_647)
+  const size = imageDimensions(imageA.data)
+  const clipName = String(fields.name || '').trim().slice(0, 80)
+  const v2Mode = mode as ImageV2Mode
+  const v2Task = (mode === 'edit' ? 'scene' : task) as ImageV2Task
+
+  const still = await rememberInputStill({
+    ownerKey,
+    folderId,
+    filename: imageA.filename,
+    data: imageA.data,
+    width: size?.width || 0,
+    height: size?.height || 0,
+    hideInput
+  })
+  const savedRef = imageB
+    ? await rememberInputStill({
+      ownerKey,
+      folderId,
+      filename: imageB.filename,
+      data: imageB.data,
+      hideInput
+    })
+    : null
+
+  const studio = await addStudioJob({
+    ownerKey,
+    familyId: crypto.randomUUID(),
+    kind: 'edit',
+    payload: {
+      prompt,
+      name: clipName,
+      folderId,
+      aspect: 'auto',
+      width: size?.width || 0,
+      height: size?.height || 0,
+      steps,
+      turbo,
+      seed,
+      cfg,
+      fps: 24,
+      samplerName: 'euler',
+      scheduler: 'simple',
+      duration: 0,
+      sound: false,
+      workflow: 'v1',
+      useIdentityRefs: false,
+      stillId: still?.id,
+      stillFilename: still?.filename,
+      hideThumbnail,
+      hideInput,
+      folderLocked,
+      referenceStillIds: [null, null, null, null],
+      extensions: [],
+      queueAutoRun: false,
+      negative: String(fields.negative || '').trim(),
+      referenceStillId: savedRef?.id,
+      referenceStillFilename: savedRef?.filename,
+      scaleToTotalPixels: true,
+      scaleMegapixels: megapixels,
+      imagePipeline: 'v2',
+      v2Mode,
+      v2Task,
+      snofsModel: clampImageV2Strength(fields.snofs_model, IMAGE_V2_SNOFS_MODEL),
+      snofsClip: clampImageV2Strength(fields.snofs_clip, IMAGE_V2_SNOFS_CLIP),
+      consistencyModel: clampImageV2Strength(fields.consistency_model, IMAGE_V2_CONSISTENCY_MODEL),
+      consistencyClip: clampImageV2Strength(fields.consistency_clip, IMAGE_V2_CONSISTENCY_CLIP)
+    }
+  })
+  await kickStudioQueue()
+  let latest = listStudioJobs(ownerKey).find(item => item.id === studio.id)
+  if (!latest?.liveJobId && !(await videoJobsBusy())) {
+    await kickStudioQueue()
+    latest = listStudioJobs(ownerKey).find(item => item.id === studio.id)
+  }
+  const liveJobId = latest?.liveJobId || ''
+
+  return {
+    jobId: liveJobId || studio.id,
+    studioJobId: studio.id,
+    queued: !liveJobId,
+    seed,
+    steps,
+    cfg,
+    mode: v2Mode,
+    task: v2Task,
+    workflow: v2Mode === 'compose' ? 'klein_v2_compose.json' : 'klein_v2_edit.json',
+    hideThumbnail,
+    folderLocked
+  }
+})