Show Flux and Krea as Image v2 engine cards, and run Krea on edit, compose, and refine.

Krea image-to-image uses encode plus denoise graphs, not Klein reference latents, and still fails closed if the Krea models are missing.

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

docs/image-v2.md

@@ -6,12 +6,12 @@ Image edit (v1) and Image v2 are siblings. v1 is unchanged. Do not mute-fix `wor
 |---|---|---|
 | Tab | Image edit | Image v2 |
 | Route | `POST /api/edit` | `POST /api/v2/generate` and `POST /v2/generate` |
-| Graphs | One file, prune unused branch | `klein_v2_edit.json`, `klein_v2_compose.json`, `klein_v2_refine.json`, `klein_v2_generate.json`, or `krea_v2_generate.json` |
+| Graphs | One file, prune unused branch | Klein or Krea graphs per mode. Engine is always visible. |
 | Second still | Optional; switches branch | Compose only; required. Mismatch is a 400 |
 | Mask | — | Refine only; required. Missing mask is a 400, not an Edit fallback |
 | Input still | Required | Edit / Compose / Refine required. Generate ignores stills |
-| LoRAs | Optional user picker | Consistency (Flux). Concept LoRA on xAIGen only. Generate Consistency off. Krea Generate has no Consistency |
-| Defaults | 20 steps, CFG 1 | Flux: 24 steps, CFG 4 (turbo: 8 / 1). Krea Generate: 8 steps, CFG 1 |
+| LoRAs | Optional user picker | Consistency (Flux only). Concept LoRA on xAIGen only. Krea has no Consistency |
+| Defaults | 20 steps, CFG 1 | Flux: 24 steps, CFG 4 (turbo: 8 / 1). Krea: 8 steps, CFG 1 |
 
 Poll v2 jobs the same way as v1: `GET /api/generate/{id}/stream` and `GET /api/generate/{id}`.
 
@@ -20,7 +20,7 @@ Poll v2 jobs the same way as v1: `GET /api/generate/{id}/stream` and `GET /api/g
 - **edit** — one image + text. Task is `scene`. Sending `image_b` is rejected. Use this to change lighting, background, or the whole frame from a single still.
 - **compose** — two images + text. `image_b` is required. No silent one-image fallback. Use this to lock a person from A and pull a face or outfit from B.
 - **refine** — one canvas + a painted mask + text. `image_a` and `mask` are required. `image_b` is ignored. Prompt only what should change inside the mask. Strength is denoise in that region (not CFG). Use this for face / hand / chest fixes without opening Comfy.
-- **generate** — text only. No `image_a`, `image_b`, or mask. Size is width × height (768 / 1024 / 1280), not megapixels from a still. Engine is Flux (`klein_v2_generate.json`) or Krea (`krea_v2_generate.json`). Edit / Compose / Refine stay Flux.
+- **generate** — text only. No `image_a`, `image_b`, or mask. Size is width × height (768 / 1024 / 1280), not megapixels from a still. Engine is Flux or Krea for every Image v2 mode. Video stays MiniMax / LTX.
 
 Compose tasks:
 
@@ -37,6 +37,7 @@ Dummy tests:
 - Refine + last good gen + mask on the left breast + “red X painted on the left breast” at strength 0.4. Pass = X on the breast, face/pose/background stay. Fail = whole image regenerates, or nothing changes.
 - Generate + Flux + “a red cube on a white table, studio light” and no stills. Pass = a new image of that. Fail = missing-image error, or the output equals the last Edit/Compose still.
 - Generate + Krea + the same prompt. Pass = `krea_v2_generate.json` is queued. Fail = Flux graph runs under a Krea label, or a missing Krea model falls back to Flux.
+- Edit + Krea + one still. Pass = `krea_v2_edit.json`. Fail = Klein graph or Generate empty latent.
 
 ## Nodes the mapper patches
 
@@ -97,9 +98,11 @@ Generate Krea (`krea_v2_generate.json`):
 | `15` | `KSampler` euler / simple, default 8 steps, CFG 1 |
 | `9` / `10` | Prompt / negative from the API |
 
-Krea does not load Klein UNET, Klein CLIP, Klein VAE, Klein Consistency, or the Klein concept LoRA. Missing Krea diffusion / text encoder / VAE fails the job. Concept LoRA (`klein_snofs_v1_4`) is xAIGen only; AIGen bypasses that node. On Krea it stays off unless `NUXT_KREA_CONCEPT_LORA` is set on xAIGen.
+Krea Edit / Compose / Refine use the same UNET / CLIP / VAE. They encode the still (`VAEEncode`) and sample with denoise < 1. Krea has no Klein `ReferenceLatent`. Compose stitches A then B (`ImageStitch`) so both stills are in the latent. Missing Krea models fail the job. No Flux fallback.
 
-There is no `LoadImage`. If the executed Generate graph has a required LoadImage, the job fails. v1 node 145 (muted T2I with a baked prompt) is not used.
+Krea does not load Klein UNET, Klein CLIP, Klein VAE, Klein Consistency, or the Klein concept LoRA. Concept LoRA (`klein_snofs_v1_4`) is xAIGen only; AIGen bypasses that node. On Krea it stays off unless `NUXT_KREA_CONCEPT_LORA` is set on xAIGen.
+
+There is no `LoadImage` on Generate. If the executed Generate graph has a required LoadImage, the job fails. v1 node 145 (muted T2I with a baked prompt) is not used.
 
 If `image_b` is sent on Edit/Compose and the executed graph has fewer than two `LoadImage` nodes, the job fails. If Refine runs without a mask input or without denoise on the scheduler, the job fails.
 
@@ -114,7 +117,7 @@ If `image_b` is sent on Edit/Compose and the executed graph has fewer than two `
 | Steps | 24 (turbo 8) |
 | CFG | 4 (turbo 1) |
 | Scale to MP | 1.0 lanczos |
-| Strength (denoise) | 0.35 on Refine only. Hidden on Edit/Compose/Generate. Range 0.15–0.75 |
+| Strength (denoise) | 0.35 on Flux Refine. Krea Edit 0.75, Compose 0.70, Refine uses the slider. Hidden on Flux Edit/Compose/Generate. Range 0.15–0.75 |
 | Size | Generate only. 1:1 1024×1024, 3:4 768×1024, 4:3 1024×768, 16:9 1280×768, 9:16 768×1280 |
 
 ### When to use each Refine strength
@@ -133,5 +136,6 @@ Do not raise Strength to rewrite the whole frame. If the face or background move
 - **refine** — prompt only the masked change. Face vs hand/chest chips set Strength and LoRAs together.
 - **generate / Flux** — On xAIGen, Concept LoRA defaults 0.65 / 0.35. On AIGen the node is not loaded. Consistency stays 0. Turbo is 8 steps / CFG 1.
 - **generate / Krea** — 8 steps, CFG 1, no Consistency. Concept LoRA stays 0 unless a Krea concept file is configured.
+- **edit / compose / refine / Krea** — same 8 / CFG 1. Strength is denoise on the encoded still. Compose stitches A|B.
 
 Presets on this tab store sliders + mode + task + engine (+ Strength when Refine, + size when Generate). They do not load v1 LoRA stacks or a cached latent. Missing engine on an old preset is Flux.

pages/index.vue

@@ -711,29 +711,29 @@
         </div>
         <div v-else-if="studioMode === 'editv2'" class="space-y-3">
           <p class="text-xs text-zinc-500">Edit, Compose, Refine, and Generate are separate graphs. Shares the desktop GPU with video.</p>
-          <div v-if="v2Mode === 'generate'" class="space-y-3 rounded-2xl border border-white/10 bg-zinc-950/40 p-3">
-            <div>
-              <p class="text-xs text-zinc-400">Engine</p>
-              <div class="mt-2 flex flex-wrap gap-2">
+          <p class="mb-2 text-xs uppercase tracking-wider text-zinc-500">Image engine</p>
+          <div class="grid grid-cols-2 gap-2">
             <button
               type="button"
-                  class="rounded-full border px-2.5 py-1 text-xs"
-                  :class="v2Engine === 'flux' ? 'border-amber-300/70 text-amber-100' : 'border-white/10 text-zinc-400'"
+              class="rounded-xl border px-3 py-2 text-left text-sm"
+              :class="v2Engine === 'flux' ? 'border-amber-300 bg-amber-400/10 text-amber-100' : 'border-white/10 hover:border-white/20'"
               @click="setV2Engine('flux')"
             >
-                  Flux
+              <span class="block font-semibold">Flux</span>
+              <span class="text-xs text-zinc-400">Klein 9B. Edit, compose, refine, and generate.</span>
             </button>
             <button
               type="button"
-                  class="rounded-full border px-2.5 py-1 text-xs"
-                  :class="v2Engine === 'krea' ? 'border-amber-300/70 text-amber-100' : 'border-white/10 text-zinc-400'"
+              class="rounded-xl border px-3 py-2 text-left text-sm"
+              :class="v2Engine === 'krea' ? 'border-amber-300 bg-amber-400/10 text-amber-100' : 'border-white/10 hover:border-white/20'"
               @click="setV2Engine('krea')"
             >
-                  Krea
+              <span class="block font-semibold">Krea</span>
+              <span class="text-xs text-zinc-400">Krea 2 Turbo. Photograph engine for stills.</span>
             </button>
           </div>
-              <p class="mt-2 text-xs text-zinc-500">Flux is the current edit and compose engine. Krea is a separate photograph engine.</p>
-            </div>
+          <p class="mt-2 text-xs text-zinc-500">Flux is Klein 9B. Krea is Krea 2 Turbo. Video stays MiniMax or LTX.</p>
+          <div v-if="v2Mode === 'generate'" class="space-y-3 rounded-2xl border border-white/10 bg-zinc-950/40 p-3">
             <div>
               <p class="text-xs text-zinc-400">Size · near 1 MP</p>
               <div class="mt-2 flex flex-wrap gap-2">
@@ -750,7 +750,7 @@
               </div>
             </div>
           </div>
-          <div v-if="v2Mode === 'refine'" class="space-y-2 rounded-2xl border border-white/10 bg-zinc-950/40 p-3">
+          <div v-if="v2Mode === 'refine' || (v2Engine === 'krea' && v2Mode !== 'generate')" class="space-y-2 rounded-2xl border border-white/10 bg-zinc-950/40 p-3">
             <label class="block text-sm">
               <span class="mb-1 block text-zinc-300">Strength (denoise)</span>
               <div class="flex items-center gap-3">
@@ -765,7 +765,7 @@
                 <span class="w-12 tabular-nums text-sm text-zinc-200">{{ v2Denoise }}</span>
               </div>
             </label>
-            <div class="flex flex-wrap gap-2">
+            <div v-if="v2Mode === 'refine'" class="flex flex-wrap gap-2">
               <button
                 type="button"
                 class="rounded-full border px-2.5 py-1 text-xs"
@@ -1986,7 +1986,9 @@ import {
   IMAGE_V2_GENERATE_HEIGHT,
   IMAGE_V2_GENERATE_WIDTH,
   IMAGE_V2_KREA_CFG,
+  IMAGE_V2_KREA_COMPOSE_DENOISE,
   IMAGE_V2_KREA_CONCEPT_LORA,
+  IMAGE_V2_KREA_EDIT_DENOISE,
   IMAGE_V2_KREA_STEPS,
   IMAGE_V2_REFINE_FACE,
   IMAGE_V2_REFINE_FACE_PROMPT,
@@ -3503,18 +3505,18 @@ function currentPresetSnapshot() {
       loraStack: [],
       settings: {
         mode: v2Mode.value,
-        engine: v2Mode.value === 'generate' ? v2Engine.value : 'flux',
+        engine: v2Engine.value,
         task: v2Mode.value === 'compose' ? v2Task.value : v2Mode.value === 'refine' ? 'refine' : v2Mode.value === 'generate' ? 't2i' : 'scene',
         negative: v2Negative.value,
         snofsModel: v2ConceptLoraEnabled.value ? clampImageV2Strength(v2SnofsModel.value, IMAGE_V2_SNOFS_MODEL) : 0,
         snofsClip: v2ConceptLoraEnabled.value ? clampImageV2Strength(v2SnofsClip.value, IMAGE_V2_SNOFS_CLIP) : 0,
-        consistencyModel: v2Mode.value === 'generate' ? 0 : clampImageV2Strength(v2ConsistencyModel.value, IMAGE_V2_CONSISTENCY_MODEL),
-        consistencyClip: v2Mode.value === 'generate' ? 0 : clampImageV2Strength(v2ConsistencyClip.value, IMAGE_V2_CONSISTENCY_CLIP),
-        steps: clampImageSteps(v2Steps.value, IMAGE_V2_STEPS_DEFAULT),
-        cfg: clampImageCfg(v2Cfg.value, IMAGE_V2_CFG_DEFAULT),
+        consistencyModel: v2Mode.value === 'generate' || v2Engine.value === 'krea' ? 0 : clampImageV2Strength(v2ConsistencyModel.value, IMAGE_V2_CONSISTENCY_MODEL),
+        consistencyClip: v2Mode.value === 'generate' || v2Engine.value === 'krea' ? 0 : clampImageV2Strength(v2ConsistencyClip.value, IMAGE_V2_CONSISTENCY_CLIP),
+        steps: clampImageSteps(v2Steps.value, v2Engine.value === 'krea' ? IMAGE_V2_KREA_STEPS : IMAGE_V2_STEPS_DEFAULT),
+        cfg: clampImageCfg(v2Cfg.value, v2Engine.value === 'krea' ? IMAGE_V2_KREA_CFG : IMAGE_V2_CFG_DEFAULT),
         megapixels: v2Mode.value === 'generate' ? undefined : clampImageScaleMegapixels(v2Megapixels.value, 1),
         turbo: v2Turbo.value === true,
-        strength: v2Mode.value === 'refine' ? clampImageV2Denoise(v2Denoise.value) : undefined,
+        strength: v2Mode.value === 'generate' || (v2Mode.value !== 'refine' && v2Engine.value !== 'krea') ? undefined : clampImageV2Denoise(v2Denoise.value),
         width: v2Mode.value === 'generate' ? v2Width.value : undefined,
         height: v2Mode.value === 'generate' ? v2Height.value : undefined
       }
@@ -3556,18 +3558,18 @@ function applyGenerationPreset(preset: GenerationPreset) {
   if (preset.kind === 'imagev2') {
     const settings = preset.settings as ImageV2PresetSettings
     v2Mode.value = settings.mode === 'compose' ? 'compose' : settings.mode === 'refine' ? 'refine' : settings.mode === 'generate' ? 'generate' : 'edit'
-    v2Engine.value = v2Mode.value === 'generate' ? parseImageV2Engine(settings.engine, 'flux') : 'flux'
+    v2Engine.value = parseImageV2Engine(settings.engine, 'flux')
     v2Task.value = v2Mode.value === 'compose' ? (settings.task || 'scene') : v2Mode.value === 'refine' ? 'refine' : v2Mode.value === 'generate' ? 't2i' : 'scene'
     if (typeof settings.negative === 'string') v2Negative.value = settings.negative
     v2SnofsModel.value = v2ConceptLoraEnabled.value ? clampImageV2Strength(settings.snofsModel, IMAGE_V2_SNOFS_MODEL) : 0
     v2SnofsClip.value = v2ConceptLoraEnabled.value ? clampImageV2Strength(settings.snofsClip, IMAGE_V2_SNOFS_CLIP) : 0
-    v2ConsistencyModel.value = v2Mode.value === 'generate' ? 0 : clampImageV2Strength(settings.consistencyModel, IMAGE_V2_CONSISTENCY_MODEL)
-    v2ConsistencyClip.value = v2Mode.value === 'generate' ? 0 : clampImageV2Strength(settings.consistencyClip, IMAGE_V2_CONSISTENCY_CLIP)
-    v2Steps.value = clampImageSteps(settings.steps, IMAGE_V2_STEPS_DEFAULT)
-    v2Cfg.value = clampImageCfg(settings.cfg, IMAGE_V2_CFG_DEFAULT)
+    v2ConsistencyModel.value = v2Mode.value === 'generate' || v2Engine.value === 'krea' ? 0 : clampImageV2Strength(settings.consistencyModel, IMAGE_V2_CONSISTENCY_MODEL)
+    v2ConsistencyClip.value = v2Mode.value === 'generate' || v2Engine.value === 'krea' ? 0 : clampImageV2Strength(settings.consistencyClip, IMAGE_V2_CONSISTENCY_CLIP)
+    v2Steps.value = clampImageSteps(settings.steps, v2Engine.value === 'krea' ? IMAGE_V2_KREA_STEPS : IMAGE_V2_STEPS_DEFAULT)
+    v2Cfg.value = clampImageCfg(settings.cfg, v2Engine.value === 'krea' ? IMAGE_V2_KREA_CFG : IMAGE_V2_CFG_DEFAULT)
     v2Megapixels.value = clampImageScaleMegapixels(settings.megapixels, 1)
     v2Turbo.value = settings.turbo === true
-    if (v2Mode.value === 'refine') v2Denoise.value = clampImageV2Denoise(settings.strength)
+    if (v2Mode.value === 'refine' || (v2Engine.value === 'krea' && v2Mode.value !== 'generate')) v2Denoise.value = clampImageV2Denoise(settings.strength)
     if (v2Mode.value === 'generate') {
       const size = clampImageV2Size(settings.width, settings.height)
       v2Width.value = size.width
@@ -4839,7 +4841,7 @@ function applyStillSettings(still: LibraryStill) {
       ? settings.mode
       : 'edit'
     setV2Mode(mode)
-    v2Engine.value = mode === 'generate' ? parseImageV2Engine(settings.engine, 'flux') : 'flux'
+    v2Engine.value = parseImageV2Engine(settings?.engine, 'flux')
     if (!settings) return
     if (typeof settings.negative === 'string') v2Negative.value = settings.negative
     if (v2ConceptLoraEnabled.value) {
@@ -4849,7 +4851,7 @@ function applyStillSettings(still: LibraryStill) {
       v2SnofsModel.value = 0
       v2SnofsClip.value = 0
     }
-    if (mode !== 'generate') {
+    if (mode !== 'generate' && v2Engine.value !== 'krea') {
       if (settings.consistencyModel != null) v2ConsistencyModel.value = clampImageV2Strength(settings.consistencyModel, IMAGE_V2_CONSISTENCY_MODEL)
       if (settings.consistencyClip != null) v2ConsistencyClip.value = clampImageV2Strength(settings.consistencyClip, IMAGE_V2_CONSISTENCY_CLIP)
     }
@@ -4857,7 +4859,7 @@ function applyStillSettings(still: LibraryStill) {
     if (settings.cfg != null) v2Cfg.value = clampImageCfg(settings.cfg, IMAGE_V2_CFG_DEFAULT)
     if (settings.megapixels != null) v2Megapixels.value = clampImageScaleMegapixels(settings.megapixels, 1)
     v2Turbo.value = settings.turbo === true
-    if (mode === 'refine' && settings.strength != null) v2Denoise.value = clampImageV2Denoise(settings.strength)
+    if ((mode === 'refine' || (v2Engine.value === 'krea' && mode !== 'generate')) && settings.strength != null) v2Denoise.value = clampImageV2Denoise(settings.strength)
     if (mode === 'generate') {
       const size = clampImageV2Size(settings.width, settings.height)
       v2Width.value = size.width
@@ -5466,17 +5468,15 @@ function setV2Mode(mode: ImageV2Mode) {
     v2Task.value = 't2i'
     v2ConsistencyModel.value = 0
     v2ConsistencyClip.value = 0
-  } else {
-    v2Engine.value = 'flux'
-    if (previous === 'generate' && v2ConsistencyModel.value === 0 && v2ConsistencyClip.value === 0) {
+  } else if (previous === 'generate' && v2Engine.value === 'flux' && v2ConsistencyModel.value === 0 && v2ConsistencyClip.value === 0) {
     v2ConsistencyModel.value = IMAGE_V2_CONSISTENCY_MODEL
     v2ConsistencyClip.value = IMAGE_V2_CONSISTENCY_CLIP
   }
-  }
+  if (v2Engine.value === 'krea' && mode === 'edit') v2Denoise.value = IMAGE_V2_KREA_EDIT_DENOISE
+  if (v2Engine.value === 'krea' && mode === 'compose') v2Denoise.value = IMAGE_V2_KREA_COMPOSE_DENOISE
 }
 
 function setV2Engine(engine: ImageV2Engine) {
-  if (engine === 'krea' && v2Mode.value !== 'generate') return
   const previous = v2Engine.value
   v2Engine.value = engine
   if (engine === 'krea') {
@@ -5487,6 +5487,8 @@ function setV2Engine(engine: ImageV2Engine) {
     v2ConsistencyModel.value = 0
     v2ConsistencyClip.value = 0
     v2Turbo.value = false
+    if (v2Mode.value === 'edit') v2Denoise.value = IMAGE_V2_KREA_EDIT_DENOISE
+    if (v2Mode.value === 'compose') v2Denoise.value = IMAGE_V2_KREA_COMPOSE_DENOISE
     return
   }
   if (previous === 'krea') {
@@ -5494,6 +5496,10 @@ function setV2Engine(engine: ImageV2Engine) {
     v2Cfg.value = IMAGE_V2_CFG_DEFAULT
     v2SnofsModel.value = v2ConceptLoraEnabled.value ? IMAGE_V2_SNOFS_MODEL : 0
     v2SnofsClip.value = v2ConceptLoraEnabled.value ? IMAGE_V2_SNOFS_CLIP : 0
+    if (v2Mode.value !== 'generate') {
+      v2ConsistencyModel.value = IMAGE_V2_CONSISTENCY_MODEL
+      v2ConsistencyClip.value = IMAGE_V2_CONSISTENCY_CLIP
+    }
   }
 }
 
@@ -5587,6 +5593,7 @@ async function editImageV2() {
     body.append('task', v2Mode.value === 'generate' ? 't2i' : v2Mode.value === 'refine' ? 'refine' : v2Mode.value === 'compose' ? v2Task.value : 'scene')
     if (v2Mode.value !== 'generate' && file.value) body.append('image_a', file.value)
     if (v2Mode.value === 'compose' && editRefFile.value) body.append('image_b', editRefFile.value)
+    if (v2Mode.value === 'refine' || (v2Engine.value === 'krea' && v2Mode.value !== 'generate')) {
       if (v2Mode.value === 'refine') {
         const maskBlob = await refinePainter.value?.exportPng()
         if (!maskBlob) {
@@ -5594,14 +5601,15 @@ async function editImageV2() {
           return
         }
         body.append('mask', new File([maskBlob], 'refine-mask.png', { type: 'image/png' }))
+      }
       body.append('strength', String(clampImageV2Denoise(v2Denoise.value)))
     }
     if (v2Mode.value === 'generate') {
       const size = clampImageV2Size(v2Width.value, v2Height.value)
       body.append('width', String(size.width))
       body.append('height', String(size.height))
-      body.append('engine', v2Engine.value)
     }
+    body.append('engine', v2Engine.value)
     body.append('prompt', prompt.value.trim())
     body.append('negative', v2Negative.value)
     body.append('snofs_model', String(v2ConceptLoraEnabled.value ? clampImageV2Strength(v2SnofsModel.value, v2Engine.value === 'krea' ? 0 : IMAGE_V2_SNOFS_MODEL) : 0))

server/api/v2/generate.post.ts

@@ -12,6 +12,8 @@ import {
   IMAGE_V2_TURBO_CFG,
   IMAGE_V2_TURBO_STEPS,
   IMAGE_V2_KREA_CFG,
+  IMAGE_V2_KREA_COMPOSE_DENOISE,
+  IMAGE_V2_KREA_EDIT_DENOISE,
   IMAGE_V2_KREA_STEPS,
   IMAGE_V2_DENOISE_DEFAULT,
   clampImageV2Denoise,
@@ -180,13 +182,7 @@ export default defineEventHandler(async (event) => {
   const hideInput = parseBool(fields.hideInput)
   const hideThumbnail = parseBool(fields.hideThumbnail)
   const requestedEngine = parseImageV2Engine(fields.engine, 'flux')
-  if (requestedEngine === 'krea' && mode !== 'generate') {
-    throw createError({
-      statusCode: 400,
-      statusMessage: 'Krea is available on Generate first.'
-    })
-  }
-  const engine = mode === 'generate' ? requestedEngine : 'flux'
+  const engine = requestedEngine
   const turbo = parseBool(fields.turbo)
   const steps = engine === 'krea'
     ? clampImageSteps(fields.steps, IMAGE_V2_KREA_STEPS)
@@ -207,7 +203,14 @@ export default defineEventHandler(async (event) => {
   const v2Task = (
     mode === 'generate' ? 't2i' : mode === 'refine' ? 'refine' : mode === 'edit' ? 'scene' : task
   ) as ImageV2Task
-  const refineStrength = mode === 'refine' ? clampImageV2Denoise(fields.strength, IMAGE_V2_DENOISE_DEFAULT) : undefined
+  const refineStrength = mode === 'generate'
+    ? undefined
+    : engine === 'krea' || mode === 'refine'
+      ? clampImageV2Denoise(
+        fields.strength,
+        mode === 'compose' ? IMAGE_V2_KREA_COMPOSE_DENOISE : mode === 'edit' ? IMAGE_V2_KREA_EDIT_DENOISE : IMAGE_V2_DENOISE_DEFAULT
+      )
+      : undefined
   const generateConsistencyModel = clampImageV2Strength(
     fields.consistency_model,
     mode === 'generate' || engine === 'krea' ? 0 : IMAGE_V2_CONSISTENCY_MODEL

server/assets/krea_v2_compose.json

@@ -0,0 +1,122 @@
+{
+  "1": {
+    "inputs": { "image": "" },
+    "class_type": "LoadImage",
+    "_meta": { "title": "Load Image A" }
+  },
+  "22": {
+    "inputs": { "image": "" },
+    "class_type": "LoadImage",
+    "_meta": { "title": "Load Image B" }
+  },
+  "2": {
+    "inputs": {
+      "upscale_method": "lanczos",
+      "megapixels": 1,
+      "resolution_steps": 1,
+      "image": ["1", 0]
+    },
+    "class_type": "ImageScaleToTotalPixels",
+    "_meta": { "title": "Scale Image A" }
+  },
+  "23": {
+    "inputs": {
+      "upscale_method": "lanczos",
+      "megapixels": 1,
+      "resolution_steps": 1,
+      "image": ["22", 0]
+    },
+    "class_type": "ImageScaleToTotalPixels",
+    "_meta": { "title": "Scale Image B" }
+  },
+  "27": {
+    "inputs": {
+      "direction": "right",
+      "match_image_size": true,
+      "spacing_width": 0,
+      "spacing_color": "black",
+      "image1": ["2", 0],
+      "image2": ["23", 0]
+    },
+    "class_type": "ImageStitch",
+    "_meta": { "title": "Stitch A then B" }
+  },
+  "4": {
+    "inputs": {
+      "unet_name": "krea2_turbo_mxfp8.safetensors",
+      "weight_dtype": "default"
+    },
+    "class_type": "UNETLoader",
+    "_meta": { "title": "Load Krea 2 Turbo" }
+  },
+  "5": {
+    "inputs": {
+      "clip_name": "qwen3vl_4b_fp8_scaled.safetensors",
+      "type": "krea2",
+      "device": "default"
+    },
+    "class_type": "CLIPLoader",
+    "_meta": { "title": "Load Krea 2 CLIP" }
+  },
+  "6": {
+    "inputs": { "vae_name": "qwen_image_vae.safetensors" },
+    "class_type": "VAELoader",
+    "_meta": { "title": "Load Qwen Image VAE" }
+  },
+  "9": {
+    "inputs": {
+      "text": "",
+      "clip": ["5", 0]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": { "title": "Positive Prompt" }
+  },
+  "10": {
+    "inputs": {
+      "text": "",
+      "clip": ["5", 0]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": { "title": "Negative Prompt" }
+  },
+  "11": {
+    "inputs": {
+      "pixels": ["27", 0],
+      "vae": ["6", 0]
+    },
+    "class_type": "VAEEncode",
+    "_meta": { "title": "VAE Encode Stitch" }
+  },
+  "15": {
+    "inputs": {
+      "seed": 1,
+      "steps": 8,
+      "cfg": 1,
+      "sampler_name": "euler",
+      "scheduler": "simple",
+      "denoise": 0.7,
+      "model": ["4", 0],
+      "positive": ["9", 0],
+      "negative": ["10", 0],
+      "latent_image": ["11", 0]
+    },
+    "class_type": "KSampler",
+    "_meta": { "title": "KSampler" }
+  },
+  "20": {
+    "inputs": {
+      "samples": ["15", 0],
+      "vae": ["6", 0]
+    },
+    "class_type": "VAEDecode",
+    "_meta": { "title": "VAE Decode" }
+  },
+  "21": {
+    "inputs": {
+      "filename_prefix": "aigen-v2-krea-compose",
+      "images": ["20", 0]
+    },
+    "class_type": "SaveImage",
+    "_meta": { "title": "Save Image" }
+  }
+}

server/assets/krea_v2_edit.json

@@ -0,0 +1,95 @@
+{
+  "1": {
+    "inputs": { "image": "" },
+    "class_type": "LoadImage",
+    "_meta": { "title": "Load Image A" }
+  },
+  "2": {
+    "inputs": {
+      "upscale_method": "lanczos",
+      "megapixels": 1,
+      "resolution_steps": 1,
+      "image": ["1", 0]
+    },
+    "class_type": "ImageScaleToTotalPixels",
+    "_meta": { "title": "Scale Image A" }
+  },
+  "4": {
+    "inputs": {
+      "unet_name": "krea2_turbo_mxfp8.safetensors",
+      "weight_dtype": "default"
+    },
+    "class_type": "UNETLoader",
+    "_meta": { "title": "Load Krea 2 Turbo" }
+  },
+  "5": {
+    "inputs": {
+      "clip_name": "qwen3vl_4b_fp8_scaled.safetensors",
+      "type": "krea2",
+      "device": "default"
+    },
+    "class_type": "CLIPLoader",
+    "_meta": { "title": "Load Krea 2 CLIP" }
+  },
+  "6": {
+    "inputs": { "vae_name": "qwen_image_vae.safetensors" },
+    "class_type": "VAELoader",
+    "_meta": { "title": "Load Qwen Image VAE" }
+  },
+  "9": {
+    "inputs": {
+      "text": "",
+      "clip": ["5", 0]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": { "title": "Positive Prompt" }
+  },
+  "10": {
+    "inputs": {
+      "text": "",
+      "clip": ["5", 0]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": { "title": "Negative Prompt" }
+  },
+  "11": {
+    "inputs": {
+      "pixels": ["2", 0],
+      "vae": ["6", 0]
+    },
+    "class_type": "VAEEncode",
+    "_meta": { "title": "VAE Encode A" }
+  },
+  "15": {
+    "inputs": {
+      "seed": 1,
+      "steps": 8,
+      "cfg": 1,
+      "sampler_name": "euler",
+      "scheduler": "simple",
+      "denoise": 0.75,
+      "model": ["4", 0],
+      "positive": ["9", 0],
+      "negative": ["10", 0],
+      "latent_image": ["11", 0]
+    },
+    "class_type": "KSampler",
+    "_meta": { "title": "KSampler" }
+  },
+  "20": {
+    "inputs": {
+      "samples": ["15", 0],
+      "vae": ["6", 0]
+    },
+    "class_type": "VAEDecode",
+    "_meta": { "title": "VAE Decode" }
+  },
+  "21": {
+    "inputs": {
+      "filename_prefix": "aigen-v2-krea-edit",
+      "images": ["20", 0]
+    },
+    "class_type": "SaveImage",
+    "_meta": { "title": "Save Image" }
+  }
+}

server/assets/krea_v2_refine.json

@@ -0,0 +1,141 @@
+{
+  "1": {
+    "inputs": { "image": "" },
+    "class_type": "LoadImage",
+    "_meta": { "title": "Load Canvas" }
+  },
+  "30": {
+    "inputs": { "image": "" },
+    "class_type": "LoadImage",
+    "_meta": { "title": "Load Mask" }
+  },
+  "2": {
+    "inputs": {
+      "upscale_method": "lanczos",
+      "megapixels": 1,
+      "resolution_steps": 1,
+      "image": ["1", 0]
+    },
+    "class_type": "ImageScaleToTotalPixels",
+    "_meta": { "title": "Scale Canvas" }
+  },
+  "3": {
+    "inputs": { "image": ["2", 0] },
+    "class_type": "GetImageSize",
+    "_meta": { "title": "Get Canvas Size" }
+  },
+  "31": {
+    "inputs": {
+      "upscale_method": "lanczos",
+      "width": ["3", 0],
+      "height": ["3", 1],
+      "crop": "disabled",
+      "image": ["30", 0]
+    },
+    "class_type": "ImageScale",
+    "_meta": { "title": "Resize Mask to Canvas" }
+  },
+  "32": {
+    "inputs": {
+      "channel": "red",
+      "image": ["31", 0]
+    },
+    "class_type": "ImageToMask",
+    "_meta": { "title": "Mask Channel" }
+  },
+  "34": {
+    "inputs": {
+      "expand": 6,
+      "tapered_corners": true,
+      "mask": ["32", 0]
+    },
+    "class_type": "GrowMask",
+    "_meta": { "title": "Grow Mask" }
+  },
+  "4": {
+    "inputs": {
+      "unet_name": "krea2_turbo_mxfp8.safetensors",
+      "weight_dtype": "default"
+    },
+    "class_type": "UNETLoader",
+    "_meta": { "title": "Load Krea 2 Turbo" }
+  },
+  "5": {
+    "inputs": {
+      "clip_name": "qwen3vl_4b_fp8_scaled.safetensors",
+      "type": "krea2",
+      "device": "default"
+    },
+    "class_type": "CLIPLoader",
+    "_meta": { "title": "Load Krea 2 CLIP" }
+  },
+  "6": {
+    "inputs": { "vae_name": "qwen_image_vae.safetensors" },
+    "class_type": "VAELoader",
+    "_meta": { "title": "Load Qwen Image VAE" }
+  },
+  "9": {
+    "inputs": {
+      "text": "",
+      "clip": ["5", 0]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": { "title": "Positive Prompt" }
+  },
+  "10": {
+    "inputs": {
+      "text": "",
+      "clip": ["5", 0]
+    },
+    "class_type": "CLIPTextEncode",
+    "_meta": { "title": "Negative Prompt" }
+  },
+  "11": {
+    "inputs": {
+      "pixels": ["2", 0],
+      "vae": ["6", 0]
+    },
+    "class_type": "VAEEncode",
+    "_meta": { "title": "VAE Encode Canvas" }
+  },
+  "33": {
+    "inputs": {
+      "samples": ["11", 0],
+      "mask": ["34", 0]
+    },
+    "class_type": "SetLatentNoiseMask",
+    "_meta": { "title": "Mask Latent Noise" }
+  },
+  "15": {
+    "inputs": {
+      "seed": 1,
+      "steps": 8,
+      "cfg": 1,
+      "sampler_name": "euler",
+      "scheduler": "simple",
+      "denoise": 0.35,
+      "model": ["4", 0],
+      "positive": ["9", 0],
+      "negative": ["10", 0],
+      "latent_image": ["33", 0]
+    },
+    "class_type": "KSampler",
+    "_meta": { "title": "KSampler" }
+  },
+  "20": {
+    "inputs": {
+      "samples": ["15", 0],
+      "vae": ["6", 0]
+    },
+    "class_type": "VAEDecode",
+    "_meta": { "title": "VAE Decode" }
+  },
+  "21": {
+    "inputs": {
+      "filename_prefix": "aigen-v2-krea-refine",
+      "images": ["20", 0]
+    },
+    "class_type": "SaveImage",
+    "_meta": { "title": "Save Image" }
+  }
+}

server/utils/generationPresets.ts

@@ -22,6 +22,8 @@ import {
   IMAGE_V2_SNOFS_MODEL,
   IMAGE_V2_STEPS_DEFAULT,
   IMAGE_V2_KREA_CFG,
+  IMAGE_V2_KREA_COMPOSE_DENOISE,
+  IMAGE_V2_KREA_EDIT_DENOISE,
   IMAGE_V2_KREA_STEPS,
   IMAGE_V2_DENOISE_DEFAULT,
   clampImageV2Denoise,
@@ -118,7 +120,7 @@ function sanitizeImageV2Settings(raw: unknown): ImageV2PresetSettings {
   const rec = raw && typeof raw === 'object' ? raw as Record<string, unknown> : {}
   const mode = parseImageV2Mode(rec.mode) || 'edit'
   const turbo = rec.turbo === true
-  const engine = mode === 'generate' ? parseImageV2Engine(rec.engine, 'flux') : 'flux'
+  const engine = parseImageV2Engine(rec.engine, 'flux')
   return {
     mode,
     engine,
@@ -132,7 +134,12 @@ function sanitizeImageV2Settings(raw: unknown): ImageV2PresetSettings {
     cfg: engine === 'krea' ? clampImageCfg(rec.cfg, IMAGE_V2_KREA_CFG) : turbo ? 1 : clampImageCfg(rec.cfg, IMAGE_V2_CFG_DEFAULT),
     megapixels: mode === 'generate' ? undefined : clampImageScaleMegapixels(rec.megapixels ?? rec.scaleMegapixels, 1),
     turbo,
-    strength: mode === 'refine' ? clampImageV2Denoise(rec.strength, IMAGE_V2_DENOISE_DEFAULT) : undefined,
+    strength: mode === 'generate' || (mode !== 'refine' && engine !== 'krea')
+      ? undefined
+      : clampImageV2Denoise(
+        rec.strength,
+        mode === 'compose' ? IMAGE_V2_KREA_COMPOSE_DENOISE : mode === 'edit' ? IMAGE_V2_KREA_EDIT_DENOISE : IMAGE_V2_DENOISE_DEFAULT
+      ),
     width: mode === 'generate' ? clampImageV2Size(rec.width, rec.height, rec.aspect).width : undefined,
     height: mode === 'generate' ? clampImageV2Size(rec.width, rec.height, rec.aspect).height : undefined
   }

server/utils/imageChainV2.ts

@@ -65,16 +65,12 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
 
     await withImageComfyHost(job.imageComfyHost, async () => {
       const generate = params.mode === 'generate'
-      const engine = generate ? parseImageV2Engine(params.engine, 'flux') : 'flux'
-      if (engine === 'krea' && params.mode !== 'generate') {
-        throw new Error('Krea is available on Generate first.')
-      }
+      const engine = parseImageV2Engine(params.engine, 'flux')
+      const engineLabel = engine === 'krea' ? 'Krea' : 'Flux'
       emitChainJob(job, {
         type: 'status',
         message: generate
-          ? engine === 'krea'
-            ? 'Queueing Krea generate on Beast...'
-            : 'Queueing Flux generate on Beast...'
+          ? `Queueing ${engineLabel} generate on Beast...`
           : params.mode === 'refine'
             ? 'Uploading canvas and mask to Beast...'
             : params.mode === 'compose' ? 'Uploading stills A and B to Beast...' : 'Uploading still A to Beast...',
@@ -101,10 +97,10 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
         emitChainJob(job, {
           type: 'status',
           message: params.mode === 'refine'
-            ? 'Queueing Klein v2 refine on Beast...'
+            ? `Queueing ${engineLabel} v2 refine on Beast...`
             : params.mode === 'compose'
-              ? `Queueing Klein v2 compose (${params.task}) on Beast...`
-              : 'Queueing Klein v2 edit on Beast...',
+              ? `Queueing ${engineLabel} v2 compose (${params.task}) on Beast...`
+              : `Queueing ${engineLabel} v2 edit on Beast...`,
           progress: 12
         })
       }
@@ -165,7 +161,7 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
         isCancelled: () => job.status === 'cancelled'
       })
 
-      emitChainJob(job, { type: 'status', message: 'Saving Klein v2 still...', progress: 94 })
+      emitChainJob(job, { type: 'status', message: `Saving ${engineLabel} v2 still...`, progress: 94 })
       const buffer = await downloadEditedImage(output)
       const size = imageDimensions(buffer)
       const still = await saveStill({
@@ -193,7 +189,7 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
           cfg: params.cfg,
           megapixels: params.mode === 'generate' ? undefined : params.megapixels,
           turbo: params.turbo === true,
-          strength: params.mode === 'refine' ? params.strength : undefined,
+          strength: params.mode === 'generate' ? undefined : params.strength,
           width: params.mode === 'generate' ? params.width : undefined,
           height: params.mode === 'generate' ? params.height : undefined,
           seed: params.seed,

server/utils/imageWorkflowV2.ts

@@ -3,6 +3,9 @@ import composeTemplate from '../assets/klein_v2_compose.json'
 import refineTemplate from '../assets/klein_v2_refine.json'
 import generateTemplate from '../assets/klein_v2_generate.json'
 import kreaGenerateTemplate from '../assets/krea_v2_generate.json'
+import kreaEditTemplate from '../assets/krea_v2_edit.json'
+import kreaComposeTemplate from '../assets/krea_v2_compose.json'
+import kreaRefineTemplate from '../assets/krea_v2_refine.json'
 import { IMAGE_SCALE_TO_TOTAL_PIXELS } from '~/server/utils/comfy'
 import { imageComfyFetch } from '~/server/utils/imageComfy'
 import { cachedComfyLoraNames } from '~/server/utils/loras'
@@ -16,7 +19,9 @@ import {
   IMAGE_V2_KREA_CFG,
   IMAGE_V2_KREA_CLIP,
   IMAGE_V2_KREA_CLIP_TYPE,
+  IMAGE_V2_KREA_COMPOSE_DENOISE,
   IMAGE_V2_KREA_CONCEPT_LORA,
+  IMAGE_V2_KREA_EDIT_DENOISE,
   IMAGE_V2_KREA_STEPS,
   IMAGE_V2_KREA_UNET_CANDIDATES,
   IMAGE_V2_KREA_VAE,
@@ -62,6 +67,9 @@ export const IMAGE_V2_COMPOSE_WORKFLOW = 'klein_v2_compose.json'
 export const IMAGE_V2_REFINE_WORKFLOW = 'klein_v2_refine.json'
 export const IMAGE_V2_GENERATE_WORKFLOW = 'klein_v2_generate.json'
 export const IMAGE_V2_KREA_GENERATE_WORKFLOW = 'krea_v2_generate.json'
+export const IMAGE_V2_KREA_EDIT_WORKFLOW = 'krea_v2_edit.json'
+export const IMAGE_V2_KREA_COMPOSE_WORKFLOW = 'krea_v2_compose.json'
+export const IMAGE_V2_KREA_REFINE_WORKFLOW = 'krea_v2_refine.json'
 
 export interface ImageV2BuildParams {
   mode: ImageV2Mode
@@ -249,6 +257,30 @@ function graphFileNames(graph: WorkflowGraph) {
   return names
 }
 
+function assertKreaShared(graph: WorkflowGraph) {
+  if (Object.values(graph).some(node => node.class_type === 'EmptyFlux2LatentImage' || node.class_type === 'Flux2Scheduler' || node.class_type === 'ReferenceLatent')) {
+    throw createError({ statusCode: 500, statusMessage: 'Krea graph contains a Klein latent, scheduler, or reference node. Refusing to run.' })
+  }
+  const clip = graph['5']
+  if (!clip || clip.class_type !== 'CLIPLoader' || String(clip.inputs.type || '') !== IMAGE_V2_KREA_CLIP_TYPE) {
+    throw createError({ statusCode: 500, statusMessage: 'Krea graph CLIPLoader type must be krea2.' })
+  }
+  const sampler = graph['15']
+  if (!sampler || sampler.class_type !== 'KSampler') {
+    throw createError({ statusCode: 500, statusMessage: 'Krea graph is missing KSampler.' })
+  }
+  const banned = graphFileNames(graph).filter((name) => {
+    const id = modelIdentity(name)
+    return /flux-?2-klein|klein_snofs|flux2-klein-9b-consistency|qwen_3_8b|full_encoder_small_decoder/i.test(id)
+  })
+  if (banned.length) {
+    throw createError({
+      statusCode: 500,
+      statusMessage: 'Krea graph includes a Klein model or LoRA. Refusing to run.'
+    })
+  }
+}
+
 function assertKreaGenerateGraph(graph: WorkflowGraph) {
   const loaders = loadImageNames(graph)
   if (loaders.length) {
@@ -261,29 +293,29 @@ function assertKreaGenerateGraph(graph: WorkflowGraph) {
   if (!latent) {
     throw createError({ statusCode: 500, statusMessage: 'Krea generate graph is missing EmptyLatentImage.' })
   }
-  if (Object.values(graph).some(node => node.class_type === 'EmptyFlux2LatentImage' || node.class_type === 'Flux2Scheduler')) {
-    throw createError({ statusCode: 500, statusMessage: 'Krea generate graph contains a Klein latent or scheduler. Refusing to run.' })
+  assertKreaShared(graph)
+}
+
+function assertKreaItiGraph(graph: WorkflowGraph, mode: ImageV2Mode) {
+  const loaders = loadImageNames(graph)
+  if (!loaders.length) {
+    throw createError({ statusCode: 500, statusMessage: 'Krea image-to-image graph is missing LoadImage.' })
   }
-  const clip = graph['5']
-  if (!clip || clip.class_type !== 'CLIPLoader' || String(clip.inputs.type || '') !== IMAGE_V2_KREA_CLIP_TYPE) {
-    throw createError({ statusCode: 500, statusMessage: 'Krea generate graph CLIPLoader type must be krea2.' })
+  if (!Object.values(graph).some(node => node.class_type === 'VAEEncode')) {
+    throw createError({ statusCode: 500, statusMessage: 'Krea image-to-image graph is missing VAEEncode.' })
   }
-  const banned = graphFileNames(graph).filter((name) => {
-    const id = modelIdentity(name)
-    return /flux-?2-klein|klein_snofs|flux2-klein-9b-consistency|qwen_3_8b|full_encoder_small_decoder/i.test(id)
-  })
-  if (banned.length) {
-    throw createError({
-      statusCode: 500,
-      statusMessage: 'Krea generate graph includes a Klein model or LoRA. Refusing to run.'
-    })
+  if (mode === 'compose' && !Object.values(graph).some(node => node.class_type === 'ImageStitch')) {
+    throw createError({ statusCode: 500, statusMessage: 'Krea compose graph is missing ImageStitch. Refusing to drop still B.' })
   }
+  assertKreaShared(graph)
 }
 
 export function assertImageV2Graph(graph: WorkflowGraph, mode: ImageV2Mode, imageBName?: string, engine: ImageV2Engine = 'flux') {
   const loaders = loadImageNames(graph)
   if (mode === 'generate' && engine === 'krea') {
     assertKreaGenerateGraph(graph)
+  } else if (engine === 'krea') {
+    assertKreaItiGraph(graph, mode)
   } else if (mode === 'generate') {
     if (loaders.length) {
       throw createError({
@@ -310,7 +342,7 @@ export function assertImageV2Graph(graph: WorkflowGraph, mode: ImageV2Mode, imag
         statusMessage: 'Refine graph has no mask input. Refusing to run.'
       })
     }
-    if (!('denoise' in (graph[SCHEDULER]?.inputs || {}))) {
+    if (!('denoise' in (graph[SCHEDULER]?.inputs || {})) && !('denoise' in (graph['15']?.inputs || {}))) {
       throw createError({
         statusCode: 500,
         statusMessage: 'Refine graph has no denoise on the sampler. Refusing to run.'
@@ -367,22 +399,99 @@ function applyKreaConceptLora(graph: WorkflowGraph, loraName: string, model: num
   setInput(graph, '15', 'model', ['7', 0])
 }
 
-function buildKreaGenerateWorkflow(params: ImageV2BuildParams) {
+function applyKreaConceptIfNeeded(graph: WorkflowGraph, params: ImageV2BuildParams) {
+  const conceptName = isXaigenStudio() ? String(params.kreaConceptLora || '').trim() : ''
+  const snofsModel = conceptName ? clampImageV2Strength(params.snofsModel, 0) : 0
+  const snofsClip = conceptName ? clampImageV2Strength(params.snofsClip, 0) : 0
+  if (!conceptName || (snofsModel <= 0 && snofsClip <= 0)) return { snofsModel: 0, snofsClip: 0 }
+  const resolved = resolveRequiredLora(conceptName, 'Krea concept')
+  if (/klein_snofs|flux2-klein-9b-consistency|flux-?2-klein/i.test(loraIdentityKey(resolved))) {
+    throw createError({ statusCode: 500, statusMessage: 'Refusing to load a Klein LoRA into the Krea graph.' })
+  }
+  applyKreaConceptLora(graph, resolved, snofsModel, snofsClip)
+  return { snofsModel, snofsClip, name: resolved }
+}
+
+function requireKreaModels(params: ImageV2BuildParams) {
   if (!params.kreaUnetName || !params.kreaClipName || !params.kreaVaeName) {
     throw createError({
       statusCode: 503,
       statusMessage: 'Krea models were not resolved. Refusing to fall back to Flux.'
     })
   }
+}
+
+function buildKreaItiWorkflow(params: ImageV2BuildParams) {
+  requireKreaModels(params)
+  const refine = params.mode === 'refine'
+  const compose = params.mode === 'compose'
+  if (refine && !String(params.maskName || '').trim()) {
+    throw createError({ statusCode: 400, statusMessage: 'Refine requires a mask. Refusing to fall back to Edit.' })
+  }
+  if (compose && !String(params.imageBName || '').trim()) {
+    throw createError({ statusCode: 400, statusMessage: 'Compose requires still B. Refusing to fall back to Edit.' })
+  }
+  const graph = structuredClone(
+    refine ? kreaRefineTemplate : compose ? kreaComposeTemplate : kreaEditTemplate
+  ) as WorkflowGraph
+  const prompt = composeImageV2Prompt(params.mode, params.task, params.prompt)
+  const negative = String(params.negative || '')
+  const steps = clampImageSteps(params.steps, IMAGE_V2_KREA_STEPS)
+  const cfg = clampImageCfg(params.cfg, IMAGE_V2_KREA_CFG)
+  const denoise = clampImageV2Denoise(
+    params.strength,
+    refine ? IMAGE_V2_DENOISE_DEFAULT : compose ? IMAGE_V2_KREA_COMPOSE_DENOISE : IMAGE_V2_KREA_EDIT_DENOISE
+  )
+  const workflowFile = imageV2WorkflowFile(params.mode, 'krea')
+
+  setInput(graph, LOAD_A, 'image', params.imageAName || '')
+  if (compose) setInput(graph, LOAD_B, 'image', params.imageBName || '')
+  if (refine) setInput(graph, LOAD_MASK, 'image', params.maskName || '')
+  setInput(graph, '4', 'unet_name', params.kreaUnetName)
+  setInput(graph, '5', 'clip_name', params.kreaClipName)
+  setInput(graph, '5', 'type', IMAGE_V2_KREA_CLIP_TYPE)
+  setInput(graph, '6', 'vae_name', params.kreaVaeName)
+  setInput(graph, PROMPT, 'text', prompt)
+  setInput(graph, NEGATIVE, 'text', negative)
+  setInput(graph, '15', 'seed', params.seed)
+  setInput(graph, '15', 'steps', steps)
+  setInput(graph, '15', 'cfg', cfg)
+  setInput(graph, '15', 'sampler_name', 'euler')
+  setInput(graph, '15', 'scheduler', 'simple')
+  setInput(graph, '15', 'denoise', denoise)
+  setInput(graph, SAVE, 'filename_prefix', params.filenamePrefix || `aigen-v2-krea-${params.mode}`)
+  patchScaleMegapixels(graph, params.megapixels ?? 1)
+  const concept = applyKreaConceptIfNeeded(graph, params)
+
+  assertImageV2Graph(graph, params.mode, compose ? params.imageBName : undefined, 'krea')
+  const loaders = loadImageNames(graph)
+  console.log(JSON.stringify({
+    src: 'image-v2',
+    engine: 'krea',
+    workflow: workflowFile,
+    mode: params.mode,
+    task: params.task,
+    canvas: { id: LOAD_A, file: graph[LOAD_A]?.inputs.image },
+    mask: refine ? { id: LOAD_MASK, file: graph[LOAD_MASK]?.inputs.image } : undefined,
+    strength: denoise,
+    loadImage: Object.fromEntries(loaders.map(item => [item.id, { title: item.title, file: item.image }])),
+    loras: concept.name ? { concept: { name: concept.name, model: concept.snofsModel, clip: concept.snofsClip } } : { loaded: false },
+    steps,
+    cfg,
+    seed: params.seed,
+    megapixels: clampImageScaleMegapixels(params.megapixels ?? 1)
+  }))
+  return { graph, workflowFile, loaders, prompt, strength: denoise }
+}
+
+function buildKreaGenerateWorkflow(params: ImageV2BuildParams) {
+  requireKreaModels(params)
   const graph = structuredClone(kreaGenerateTemplate) as WorkflowGraph
   const prompt = composeImageV2Prompt('generate', 't2i', params.prompt)
   const negative = String(params.negative || '')
   const size = clampImageV2Size(params.width, params.height)
   const steps = clampImageSteps(params.steps, IMAGE_V2_KREA_STEPS)
   const cfg = clampImageCfg(params.cfg, IMAGE_V2_KREA_CFG)
-  const conceptName = isXaigenStudio() ? String(params.kreaConceptLora || '').trim() : ''
-  const snofsModel = conceptName ? clampImageV2Strength(params.snofsModel, 0) : 0
-  const snofsClip = conceptName ? clampImageV2Strength(params.snofsClip, 0) : 0
   const workflowFile = IMAGE_V2_KREA_GENERATE_WORKFLOW
 
   setInput(graph, '4', 'unet_name', params.kreaUnetName)
@@ -399,13 +508,7 @@ function buildKreaGenerateWorkflow(params: ImageV2BuildParams) {
   setInput(graph, '15', 'sampler_name', 'euler')
   setInput(graph, '15', 'scheduler', 'simple')
   setInput(graph, SAVE, 'filename_prefix', params.filenamePrefix || 'aigen-v2-krea')
-  if (conceptName && (snofsModel > 0 || snofsClip > 0)) {
-    const resolved = resolveRequiredLora(conceptName, 'Krea concept')
-    if (/klein_snofs|flux2-klein-9b-consistency|flux-?2-klein/i.test(loraIdentityKey(resolved))) {
-      throw createError({ statusCode: 500, statusMessage: 'Refusing to load a Klein LoRA into the Krea graph.' })
-    }
-    applyKreaConceptLora(graph, resolved, snofsModel, snofsClip)
-  }
+  const concept = applyKreaConceptIfNeeded(graph, params)
 
   assertImageV2Graph(graph, 'generate', undefined, 'krea')
   const loaders = loadImageNames(graph)
@@ -422,8 +525,8 @@ function buildKreaGenerateWorkflow(params: ImageV2BuildParams) {
       vae: params.kreaVaeName
     },
     loras: {
-      concept: graph['7']
-        ? { name: graph['7'].inputs.lora_name, model: snofsModel, clip: snofsClip }
+      concept: concept.name
+        ? { name: concept.name, model: concept.snofsModel, clip: concept.snofsClip }
         : { loaded: false, model: 0, clip: 0 }
     },
     steps,
@@ -434,8 +537,10 @@ function buildKreaGenerateWorkflow(params: ImageV2BuildParams) {
 }
 
 export function buildImageV2Workflow(params: ImageV2BuildParams) {
-  const engine = params.mode === 'generate' ? parseImageV2Engine(params.engine, 'flux') : 'flux'
-  if (params.mode === 'generate' && engine === 'krea') return buildKreaGenerateWorkflow(params)
+  const engine = parseImageV2Engine(params.engine, 'flux')
+  if (engine === 'krea') {
+    return params.mode === 'generate' ? buildKreaGenerateWorkflow(params) : buildKreaItiWorkflow(params)
+  }
   const compose = params.mode === 'compose'
   const refine = params.mode === 'refine'
   const generate = params.mode === 'generate'
@@ -536,6 +641,7 @@ export const IMAGE_V2_NODE_LABELS: Record<string, string> = {
   '30': 'Loading mask',
   '2': 'Scaling image A',
   '23': 'Scaling image B',
+  '27': 'Stitching stills',
   '31': 'Resizing mask',
   '4': 'Loading diffusion model',
   '5': 'Loading CLIP',

server/utils/studioQueue.ts

@@ -754,7 +754,7 @@ async function startStudioEditJob(item: StudioJob) {
       await markStudioLive(item.ownerKey, item.id, live.id)
       void runEditV2(live, {
         mode,
-        engine: mode === 'generate' && payload.engine === 'krea' ? 'krea' : 'flux',
+        engine: payload.engine === 'krea' ? 'krea' : 'flux',
         task: payload.v2Task || 'scene',
         image: mode === 'generate' ? null : image,
         reference: mode === 'refine' || mode === 'generate' ? null : reference,
@@ -766,8 +766,8 @@ async function startStudioEditJob(item: StudioJob) {
         cfg: payload.cfg,
         snofsModel: payload.snofsModel ?? (isXaigenStudio() ? 0.65 : 0),
         snofsClip: payload.snofsClip ?? (isXaigenStudio() ? 0.35 : 0),
-        consistencyModel: payload.consistencyModel ?? (mode === 'generate' ? 0 : 0.7),
-        consistencyClip: payload.consistencyClip ?? (mode === 'generate' ? 0 : 0.7),
+        consistencyModel: payload.consistencyModel ?? (mode === 'generate' || payload.engine === 'krea' ? 0 : 0.7),
+        consistencyClip: payload.consistencyClip ?? (mode === 'generate' || payload.engine === 'krea' ? 0 : 0.7),
         megapixels: payload.scaleMegapixels ?? 1,
         strength: payload.refineStrength,
         width: payload.width,

utils/imageV2.ts

@@ -56,6 +56,8 @@ export const IMAGE_V2_GENERATE_SNOFS = { snofsModel: 0.65, snofsClip: 0.35 }
 
 export const IMAGE_V2_KREA_STEPS = 8
 export const IMAGE_V2_KREA_CFG = 1
+export const IMAGE_V2_KREA_EDIT_DENOISE = 0.75
+export const IMAGE_V2_KREA_COMPOSE_DENOISE = 0.7
 export const IMAGE_V2_KREA_CLIP = 'qwen3vl_4b_fp8_scaled.safetensors'
 export const IMAGE_V2_KREA_CLIP_TYPE = 'krea2'
 export const IMAGE_V2_KREA_VAE = 'qwen_image_vae.safetensors'
@@ -88,7 +90,12 @@ export function parseImageV2Engine(raw: unknown, fallback: ImageV2Engine = 'flux
 }
 
 export function imageV2WorkflowFile(mode: ImageV2Mode, engine: ImageV2Engine = 'flux') {
-  if (mode === 'generate' && engine === 'krea') return 'krea_v2_generate.json'
+  if (engine === 'krea') {
+    if (mode === 'generate') return 'krea_v2_generate.json'
+    if (mode === 'refine') return 'krea_v2_refine.json'
+    if (mode === 'compose') return 'krea_v2_compose.json'
+    return 'krea_v2_edit.json'
+  }
   if (mode === 'generate') return 'klein_v2_generate.json'
   if (mode === 'refine') return 'klein_v2_refine.json'
   if (mode === 'compose') return 'klein_v2_compose.json'

utils/libraryGeneration.ts

@@ -130,8 +130,8 @@ export function stillModeLabel(still: { filename?: string; settings?: StillGener
           ? 'Refine'
           : 'Edit'
     const task = settings.mode === 'compose' ? composeTaskLabel(settings.task) : ''
-    const engine = settings.mode === 'generate' && settings.engine === 'krea' ? 'Krea' : ''
-    return [mode === 'Generate' && engine ? `Image v2 · ${mode} · ${engine}` : `Image v2 · ${mode}`, task].filter(Boolean).join(' · ')
+    const engine = settings.engine === 'krea' ? 'Krea' : settings.engine === 'flux' ? 'Flux' : ''
+    return [engine ? `Image v2 · ${mode} · ${engine}` : `Image v2 · ${mode}`, task].filter(Boolean).join(' · ')
   }
   if (settings?.kind === 'image') return 'Image edit'
   if (/aigen_v2_/i.test(String(still.filename || ''))) return 'Image v2'
@@ -151,7 +151,7 @@ export function stillSettingsRows(still: { width?: number; height?: number; sett
     } else if (still.width && still.height) {
       rows.push({ label: 'Output', value: `${still.width}×${still.height}` })
     }
-    if (settings.mode === 'generate' && settings.engine) {
+    if (settings.engine) {
       rows.push({ label: 'Engine', value: settings.engine === 'krea' ? 'Krea' : 'Flux' })
     }
     if (isXaigenStudio() && (settings.snofsModel != null || settings.snofsClip != null)) {