Prompt only what should change in the painted area.
-
Klein v2 · 9B Base · euler. Edit, Compose, and Refine are separate graphs. Shares the desktop GPU with video.
+
Klein v2 · 9B Base · euler. Edit, Compose, Refine, and Generate are separate graphs. Shares the desktop GPU with video.
+
+
Size · near 1 MP
+
+
+ {{ aspect }} · {{ pair[0] }}×{{ pair[1] }}
+
+
+
+
+ SFW scene
+
+
+ SNOF T2I
+
+
+
Strength (denoise)
@@ -750,11 +795,11 @@
SNOFS CLIP
-
+
Consistency Model
-
+
Consistency CLIP
@@ -770,7 +815,7 @@
Seed
-
+
Scale to MP
@@ -1327,6 +1372,13 @@
>
Use as input still
+
+ Send to Edit
+
Promise; clear: () => void } | null>(null)
@@ -2532,14 +2593,15 @@ const stillBHint = computed(() => {
return 'Still A is the edit image. Still B is style or background.'
})
const editV2Blocked = computed(() => {
- if (!file.value || !prompt.value.trim() || !folderId.value) return true
+ if (!prompt.value.trim() || !folderId.value) return true
+ if (v2Mode.value !== 'generate' && !file.value) return true
if (v2Mode.value === 'compose' && !editRefFile.value) return true
if (v2Mode.value === 'refine' && !refineMaskDirty.value) return true
if (!comfyOk.value && !imageComfyOk.value) return true
return false
})
const editV2BlockReason = computed(() => {
- if (!file.value) return 'Load still A first.'
+ if (v2Mode.value !== 'generate' && !file.value) return 'Load still A first.'
if (v2Mode.value === 'compose' && !editRefFile.value) return 'Compose requires still B. This will not fall back to one-image generation.'
if (v2Mode.value === 'refine' && !refineMaskDirty.value) return 'Paint a mask on Still A first. Refine will not fall back to Edit.'
if (!prompt.value.trim()) return 'Write a prompt first.'
@@ -2550,7 +2612,7 @@ const editV2BlockReason = computed(() => {
})
const editV2SubmitLabel = computed(() => {
const occupied = videoBusy.value || editBusy.value || studioJobs.value.some(job => job.status === 'running')
- const label = v2Mode.value === 'refine' ? 'Refine image' : v2Mode.value === 'compose' ? 'Compose image' : 'Edit image'
+ const label = v2Mode.value === 'generate' ? 'Generate image' : v2Mode.value === 'refine' ? 'Refine image' : v2Mode.value === 'compose' ? 'Compose image' : 'Edit image'
return occupied ? `Queue ${label.toLowerCase()}` : label
})
const generateLabel = computed(() => {
@@ -2608,6 +2670,7 @@ const composedIdentityPrompt = computed(() => {
})
const promptPlaceholder = computed(() => {
if (studioMode.value === 'editv2') {
+ if (v2Mode.value === 'generate') return 'A red cube on a white table, studio light.'
if (v2Mode.value === 'refine') return 'Prompt only what should change in the painted area.'
if (v2Mode.value === 'compose' && v2Task.value === 'outfit') return 'Keep everything the same except the clothes from still B.'
if (v2Mode.value === 'compose' && v2Task.value === 'face_lock') return 'Keep the body and scene from still A. Use the face from still B.'
@@ -3347,17 +3410,19 @@ function currentPresetSnapshot() {
loraStack: [],
settings: {
mode: v2Mode.value,
- task: v2Mode.value === 'compose' ? v2Task.value : v2Mode.value === 'refine' ? 'refine' : 'scene',
+ task: v2Mode.value === 'compose' ? v2Task.value : v2Mode.value === 'refine' ? 'refine' : v2Mode.value === 'generate' ? 't2i' : 'scene',
negative: v2Negative.value,
snofsModel: clampImageV2Strength(v2SnofsModel.value, IMAGE_V2_SNOFS_MODEL),
snofsClip: clampImageV2Strength(v2SnofsClip.value, IMAGE_V2_SNOFS_CLIP),
- consistencyModel: clampImageV2Strength(v2ConsistencyModel.value, IMAGE_V2_CONSISTENCY_MODEL),
- consistencyClip: clampImageV2Strength(v2ConsistencyClip.value, IMAGE_V2_CONSISTENCY_CLIP),
+ 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),
- megapixels: clampImageScaleMegapixels(v2Megapixels.value, 1),
+ megapixels: v2Mode.value === 'generate' ? undefined : clampImageScaleMegapixels(v2Megapixels.value, 1),
turbo: v2Turbo.value === true,
- strength: v2Mode.value === 'refine' ? clampImageV2Denoise(v2Denoise.value) : undefined
+ strength: v2Mode.value === 'refine' ? clampImageV2Denoise(v2Denoise.value) : undefined,
+ width: v2Mode.value === 'generate' ? v2Width.value : undefined,
+ height: v2Mode.value === 'generate' ? v2Height.value : undefined
}
}
}
@@ -3396,18 +3461,23 @@ function applyGenerationPreset(preset: GenerationPreset) {
const skipped = preset.loraStack.length - stack.length
if (preset.kind === 'imagev2') {
const settings = preset.settings as ImageV2PresetSettings
- v2Mode.value = settings.mode === 'compose' ? 'compose' : settings.mode === 'refine' ? 'refine' : 'edit'
- v2Task.value = v2Mode.value === 'compose' ? (settings.task || 'scene') : v2Mode.value === 'refine' ? 'refine' : 'scene'
+ v2Mode.value = settings.mode === 'compose' ? 'compose' : settings.mode === 'refine' ? 'refine' : settings.mode === 'generate' ? 'generate' : 'edit'
+ 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 = clampImageV2Strength(settings.snofsModel, IMAGE_V2_SNOFS_MODEL)
v2SnofsClip.value = clampImageV2Strength(settings.snofsClip, IMAGE_V2_SNOFS_CLIP)
- v2ConsistencyModel.value = clampImageV2Strength(settings.consistencyModel, IMAGE_V2_CONSISTENCY_MODEL)
- v2ConsistencyClip.value = clampImageV2Strength(settings.consistencyClip, IMAGE_V2_CONSISTENCY_CLIP)
+ 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)
v2Megapixels.value = clampImageScaleMegapixels(settings.megapixels, 1)
v2Turbo.value = settings.turbo === true
if (v2Mode.value === 'refine') v2Denoise.value = clampImageV2Denoise(settings.strength)
+ if (v2Mode.value === 'generate') {
+ const size = clampImageV2Size(settings.width, settings.height)
+ v2Width.value = size.width
+ v2Height.value = size.height
+ }
void ensureRefineCanvas()
imageV2PresetId.value = preset.id
imageV2PresetName.value = preset.name
@@ -5196,12 +5266,35 @@ async function editImage() {
}
function setV2Mode(mode: ImageV2Mode) {
+ const previous = v2Mode.value
v2Mode.value = mode
if (mode === 'edit') v2Task.value = 'scene'
if (mode === 'refine') {
v2Task.value = 'refine'
void ensureRefineCanvas()
}
+ if (mode === 'generate') {
+ v2Task.value = 't2i'
+ v2ConsistencyModel.value = 0
+ v2ConsistencyClip.value = 0
+ } else if (previous === 'generate' && v2ConsistencyModel.value === 0 && v2ConsistencyClip.value === 0) {
+ v2ConsistencyModel.value = IMAGE_V2_CONSISTENCY_MODEL
+ v2ConsistencyClip.value = IMAGE_V2_CONSISTENCY_CLIP
+ }
+}
+
+function setGenerateSize(aspect: ImageV2GenerateAspect) {
+ const [width, height] = IMAGE_V2_GENERATE_ASPECTS[aspect]
+ v2Width.value = width
+ v2Height.value = height
+}
+
+function applyGenerateLook(kind: 'sfw' | 'snofs') {
+ const look = kind === 'sfw' ? IMAGE_V2_GENERATE_SFW : IMAGE_V2_GENERATE_SNOFS
+ v2SnofsModel.value = look.snofsModel
+ v2SnofsClip.value = look.snofsClip
+ v2ConsistencyModel.value = 0
+ v2ConsistencyClip.value = 0
}
function applyRefinePreset(kind: 'face' | 'hand' | 'heavy') {
@@ -5238,6 +5331,19 @@ async function ensureRefineCanvas() {
}
}
+async function sendToEdit() {
+ if (!editResultUrl.value) return
+ studioMode.value = 'editv2'
+ outputFocus.value = 'edit'
+ try {
+ await useEditAsInput()
+ setV2Mode('edit')
+ toast('Output is Still A. Write an edit prompt.')
+ } catch {
+ toast('Could not send that still to Edit')
+ }
+}
+
async function sendToRefine() {
if (!editResultUrl.value) return
studioMode.value = 'editv2'
@@ -5268,8 +5374,8 @@ async function editImageV2() {
try {
const body = new FormData()
body.append('mode', v2Mode.value)
- body.append('task', v2Mode.value === 'refine' ? 'refine' : v2Mode.value === 'compose' ? v2Task.value : 'scene')
- body.append('image_a', file.value as File)
+ 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') {
const maskBlob = await refinePainter.value?.exportPng()
@@ -5280,15 +5386,20 @@ async function editImageV2() {
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('prompt', prompt.value.trim())
body.append('negative', v2Negative.value)
body.append('snofs_model', String(clampImageV2Strength(v2SnofsModel.value, IMAGE_V2_SNOFS_MODEL)))
body.append('snofs_clip', String(clampImageV2Strength(v2SnofsClip.value, IMAGE_V2_SNOFS_CLIP)))
- body.append('consistency_model', String(clampImageV2Strength(v2ConsistencyModel.value, IMAGE_V2_CONSISTENCY_MODEL)))
- body.append('consistency_clip', String(clampImageV2Strength(v2ConsistencyClip.value, IMAGE_V2_CONSISTENCY_CLIP)))
+ body.append('consistency_model', String(v2Mode.value === 'generate' ? 0 : clampImageV2Strength(v2ConsistencyModel.value, IMAGE_V2_CONSISTENCY_MODEL)))
+ body.append('consistency_clip', String(v2Mode.value === 'generate' ? 0 : clampImageV2Strength(v2ConsistencyClip.value, IMAGE_V2_CONSISTENCY_CLIP)))
body.append('steps', String(clampImageSteps(v2Steps.value, IMAGE_V2_STEPS_DEFAULT)))
body.append('cfg', String(clampImageCfg(v2Cfg.value, IMAGE_V2_CFG_DEFAULT)))
- body.append('megapixels', String(clampImageScaleMegapixels(v2Megapixels.value, 1)))
+ if (v2Mode.value !== 'generate') body.append('megapixels', String(clampImageScaleMegapixels(v2Megapixels.value, 1)))
body.append('turbo', String(v2Turbo.value === true))
body.append('seed', seedInput.value || 'random')
body.append('folderId', folderId.value)
@@ -5328,7 +5439,7 @@ async function editImageV2() {
editChainLabel.value = ''
editOverallProgress.value = 0
editCompletedChainStep.value = 0
- editActiveChainPlan.value = [{ label: v2Mode.value === 'refine' ? 'Refine' : v2Mode.value === 'compose' ? 'Compose' : 'Edit', prompt: prompt.value.trim() }]
+ editActiveChainPlan.value = [{ label: v2Mode.value === 'generate' ? 'Generate' : v2Mode.value === 'refine' ? 'Refine' : v2Mode.value === 'compose' ? 'Compose' : 'Edit', prompt: prompt.value.trim() }]
startTimer('edit')
editDownloadName.value = downloadName
editJobId.value = started.jobId
diff --git a/server/api/v2/generate.post.ts b/server/api/v2/generate.post.ts
index b32045e..1383b3c 100644
--- a/server/api/v2/generate.post.ts
+++ b/server/api/v2/generate.post.ts
@@ -13,6 +13,7 @@ import {
IMAGE_V2_TURBO_STEPS,
IMAGE_V2_DENOISE_DEFAULT,
clampImageV2Denoise,
+ clampImageV2Size,
clampImageV2Strength,
parseImageV2Mode,
parseImageV2Task,
@@ -109,9 +110,12 @@ export default defineEventHandler(async (event) => {
const mode = parseImageV2Mode(fields.mode)
if (!mode) {
- throw createError({ statusCode: 400, statusMessage: 'mode must be edit, compose, or refine' })
+ throw createError({ statusCode: 400, statusMessage: 'mode must be edit, compose, refine, or generate' })
}
- const task = parseImageV2Task(fields.task, mode === 'refine' ? 'refine' : 'scene')
+ const task = parseImageV2Task(
+ fields.task,
+ mode === 'generate' ? 't2i' : mode === 'refine' ? 'refine' : 'scene'
+ )
const prompt = String(fields.prompt || '').trim()
if (!prompt) {
throw createError({ statusCode: 400, statusMessage: 'A prompt is required' })
@@ -131,11 +135,11 @@ export default defineEventHandler(async (event) => {
}
const ownerKey = libraryOwnerKey(event)
- const imageA = await resolveImageRef(ownerKey, fields.image_a, uploadedA)
- const imageB = mode === 'refine' ? null : await resolveImageRef(ownerKey, fields.image_b, uploadedB)
+ const imageA = mode === 'generate' ? null : await resolveImageRef(ownerKey, fields.image_a, uploadedA)
+ const imageB = mode === 'refine' || mode === 'generate' ? null : await resolveImageRef(ownerKey, fields.image_b, uploadedB)
const mask = mode === 'refine' ? await resolveImageRef(ownerKey, fields.mask, uploadedMask) : null
- if (!imageA) {
+ if (mode !== 'generate' && !imageA) {
throw createError({ statusCode: 400, statusMessage: 'image_a is required' })
}
if (mode === 'refine' && !mask) {
@@ -173,25 +177,34 @@ export default defineEventHandler(async (event) => {
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 megapixels = mode === 'generate' ? 0 : 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 generateSize = clampImageV2Size(fields.width, fields.height, fields.aspect)
+ const size = mode === 'generate'
+ ? { width: generateSize.width, height: generateSize.height }
+ : imageDimensions(imageA!.data)
const clipName = String(fields.name || '').trim().slice(0, 80)
const v2Mode = mode as ImageV2Mode
- const v2Task = (mode === 'refine' ? 'refine' : mode === 'edit' ? 'scene' : task) as ImageV2Task
+ 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 generateConsistencyModel = clampImageV2Strength(fields.consistency_model, mode === 'generate' ? 0 : IMAGE_V2_CONSISTENCY_MODEL)
+ const generateConsistencyClip = clampImageV2Strength(fields.consistency_clip, mode === 'generate' ? 0 : IMAGE_V2_CONSISTENCY_CLIP)
- const still = await rememberInputStill({
- ownerKey,
- folderId,
- filename: imageA.filename,
- data: imageA.data,
- width: size?.width || 0,
- height: size?.height || 0,
- hideInput
- })
+ const still = imageA
+ ? await rememberInputStill({
+ ownerKey,
+ folderId,
+ filename: imageA.filename,
+ data: imageA.data,
+ width: size?.width || 0,
+ height: size?.height || 0,
+ hideInput
+ })
+ : null
const savedRef = imageB
? await rememberInputStill({
ownerKey,
@@ -219,7 +232,7 @@ export default defineEventHandler(async (event) => {
prompt,
name: clipName,
folderId,
- aspect: 'auto',
+ aspect: mode === 'generate' ? (generateSize.aspect || '1:1') : 'auto',
width: size?.width || 0,
height: size?.height || 0,
steps,
@@ -244,15 +257,15 @@ export default defineEventHandler(async (event) => {
negative: String(fields.negative || '').trim(),
referenceStillId: savedRef?.id,
referenceStillFilename: savedRef?.filename,
- scaleToTotalPixels: true,
+ scaleToTotalPixels: mode !== 'generate',
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),
+ consistencyModel: generateConsistencyModel,
+ consistencyClip: generateConsistencyClip,
maskStillId: savedMask?.id,
maskStillFilename: savedMask?.filename,
refineStrength
@@ -275,7 +288,11 @@ export default defineEventHandler(async (event) => {
cfg,
mode: v2Mode,
task: v2Task,
- workflow: v2Mode === 'refine' ? 'klein_v2_refine.json' : v2Mode === 'compose' ? 'klein_v2_compose.json' : 'klein_v2_edit.json',
+ workflow: v2Mode === 'generate'
+ ? 'klein_v2_generate.json'
+ : v2Mode === 'refine' ? 'klein_v2_refine.json' : v2Mode === 'compose' ? 'klein_v2_compose.json' : 'klein_v2_edit.json',
+ width: size?.width || 0,
+ height: size?.height || 0,
strength: refineStrength,
hideThumbnail,
folderLocked
diff --git a/server/assets/klein_v2_generate.json b/server/assets/klein_v2_generate.json
new file mode 100644
index 0000000..9d31c9b
--- /dev/null
+++ b/server/assets/klein_v2_generate.json
@@ -0,0 +1,127 @@
+{
+ "4": {
+ "inputs": {
+ "unet_name": "flux-2-klein-base-9b-fp8.safetensors",
+ "weight_dtype": "default"
+ },
+ "class_type": "UNETLoader",
+ "_meta": { "title": "Load Flux.2 Klein 9B Base" }
+ },
+ "5": {
+ "inputs": {
+ "clip_name": "qwen_3_8b_fp8mixed.safetensors",
+ "type": "flux2",
+ "device": "default"
+ },
+ "class_type": "CLIPLoader",
+ "_meta": { "title": "Load Qwen 3 8B CLIP" }
+ },
+ "6": {
+ "inputs": { "vae_name": "full_encoder_small_decoder.safetensors" },
+ "class_type": "VAELoader",
+ "_meta": { "title": "Load Klein VAE" }
+ },
+ "7": {
+ "inputs": {
+ "lora_name": "klein_snofs_v1_4.safetensors",
+ "strength_model": 0.65,
+ "strength_clip": 0.35,
+ "model": ["4", 0],
+ "clip": ["5", 0]
+ },
+ "class_type": "LoraLoader",
+ "_meta": { "title": "SNOFS" }
+ },
+ "8": {
+ "inputs": {
+ "lora_name": "Flux2-Klein-9B-consistency-V2.safetensors",
+ "strength_model": 0,
+ "strength_clip": 0,
+ "model": ["7", 0],
+ "clip": ["7", 1]
+ },
+ "class_type": "LoraLoader",
+ "_meta": { "title": "Consistency" }
+ },
+ "9": {
+ "inputs": {
+ "text": "",
+ "clip": ["8", 1]
+ },
+ "class_type": "CLIPTextEncode",
+ "_meta": { "title": "Positive Prompt" }
+ },
+ "10": {
+ "inputs": {
+ "text": "",
+ "clip": ["8", 1]
+ },
+ "class_type": "CLIPTextEncode",
+ "_meta": { "title": "Negative Prompt" }
+ },
+ "14": {
+ "inputs": {
+ "width": 1024,
+ "height": 1024,
+ "batch_size": 1
+ },
+ "class_type": "EmptyFlux2LatentImage",
+ "_meta": { "title": "Empty Flux 2 Latent" }
+ },
+ "15": {
+ "inputs": { "noise_seed": 1 },
+ "class_type": "RandomNoise",
+ "_meta": { "title": "RandomNoise" }
+ },
+ "16": {
+ "inputs": { "sampler_name": "euler" },
+ "class_type": "KSamplerSelect",
+ "_meta": { "title": "KSamplerSelect" }
+ },
+ "17": {
+ "inputs": {
+ "steps": 24,
+ "width": 1024,
+ "height": 1024
+ },
+ "class_type": "Flux2Scheduler",
+ "_meta": { "title": "Flux2Scheduler" }
+ },
+ "18": {
+ "inputs": {
+ "cfg": 4,
+ "model": ["8", 0],
+ "positive": ["9", 0],
+ "negative": ["10", 0]
+ },
+ "class_type": "CFGGuider",
+ "_meta": { "title": "CFG Guider" }
+ },
+ "19": {
+ "inputs": {
+ "noise": ["15", 0],
+ "guider": ["18", 0],
+ "sampler": ["16", 0],
+ "sigmas": ["17", 0],
+ "latent_image": ["14", 0]
+ },
+ "class_type": "SamplerCustomAdvanced",
+ "_meta": { "title": "SamplerCustomAdvanced" }
+ },
+ "20": {
+ "inputs": {
+ "samples": ["19", 0],
+ "vae": ["6", 0]
+ },
+ "class_type": "VAEDecode",
+ "_meta": { "title": "VAE Decode" }
+ },
+ "21": {
+ "inputs": {
+ "filename_prefix": "aigen-v2-generate",
+ "images": ["20", 0]
+ },
+ "class_type": "SaveImage",
+ "_meta": { "title": "Save Image" }
+ }
+}
diff --git a/server/utils/generationPresets.ts b/server/utils/generationPresets.ts
index 40b4785..cc07379 100644
--- a/server/utils/generationPresets.ts
+++ b/server/utils/generationPresets.ts
@@ -23,6 +23,7 @@ import {
IMAGE_V2_STEPS_DEFAULT,
IMAGE_V2_DENOISE_DEFAULT,
clampImageV2Denoise,
+ clampImageV2Size,
clampImageV2Strength,
parseImageV2Mode,
parseImageV2Task,
@@ -116,17 +117,19 @@ function sanitizeImageV2Settings(raw: unknown): ImageV2PresetSettings {
const turbo = rec.turbo === true
return {
mode,
- task: mode === 'compose' ? parseImageV2Task(rec.task, 'scene') : mode === 'refine' ? 'refine' : 'scene',
+ task: mode === 'compose' ? parseImageV2Task(rec.task, 'scene') : mode === 'refine' ? 'refine' : mode === 'generate' ? 't2i' : 'scene',
negative: String(rec.negative || '').slice(0, 2000),
snofsModel: clampImageV2Strength(rec.snofsModel ?? rec.snofs_model, IMAGE_V2_SNOFS_MODEL),
snofsClip: clampImageV2Strength(rec.snofsClip ?? rec.snofs_clip, IMAGE_V2_SNOFS_CLIP),
- consistencyModel: clampImageV2Strength(rec.consistencyModel ?? rec.consistency_model, IMAGE_V2_CONSISTENCY_MODEL),
- consistencyClip: clampImageV2Strength(rec.consistencyClip ?? rec.consistency_clip, IMAGE_V2_CONSISTENCY_CLIP),
+ consistencyModel: clampImageV2Strength(rec.consistencyModel ?? rec.consistency_model, mode === 'generate' ? 0 : IMAGE_V2_CONSISTENCY_MODEL),
+ consistencyClip: clampImageV2Strength(rec.consistencyClip ?? rec.consistency_clip, mode === 'generate' ? 0 : IMAGE_V2_CONSISTENCY_CLIP),
steps: turbo ? 8 : clampImageSteps(rec.steps, IMAGE_V2_STEPS_DEFAULT),
cfg: turbo ? 1 : clampImageCfg(rec.cfg, IMAGE_V2_CFG_DEFAULT),
- megapixels: clampImageScaleMegapixels(rec.megapixels ?? rec.scaleMegapixels, 1),
+ megapixels: mode === 'generate' ? undefined : clampImageScaleMegapixels(rec.megapixels ?? rec.scaleMegapixels, 1),
turbo,
- strength: mode === 'refine' ? clampImageV2Denoise(rec.strength, IMAGE_V2_DENOISE_DEFAULT) : undefined
+ strength: mode === 'refine' ? clampImageV2Denoise(rec.strength, IMAGE_V2_DENOISE_DEFAULT) : undefined,
+ width: mode === 'generate' ? clampImageV2Size(rec.width, rec.height, rec.aspect).width : undefined,
+ height: mode === 'generate' ? clampImageV2Size(rec.width, rec.height, rec.aspect).height : undefined
}
}
diff --git a/server/utils/imageChainV2.ts b/server/utils/imageChainV2.ts
index e56b62f..3a08e6f 100644
--- a/server/utils/imageChainV2.ts
+++ b/server/utils/imageChainV2.ts
@@ -13,7 +13,7 @@ import type { EditImageFile } from '~/server/utils/imageChain'
export type EditV2RunParams = {
mode: ImageV2Mode
task: ImageV2Task
- image: EditImageFile
+ image?: EditImageFile | null
reference: EditImageFile | null
mask?: EditImageFile | null
prompt: string
@@ -27,6 +27,9 @@ export type EditV2RunParams = {
consistencyClip: number
megapixels: number
strength?: number
+ width?: number
+ height?: number
+ turbo?: boolean
}
export async function runEditV2(job: Job, params: EditV2RunParams) {
@@ -41,6 +44,9 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
if (params.mode === 'edit' && params.reference) {
throw new Error('Edit mode takes one image. Use Compose for two stills.')
}
+ if (params.mode !== 'generate' && !params.image) {
+ throw new Error('This v2 mode requires still A.')
+ }
try {
await ensureComfyReady((status) => {
@@ -55,15 +61,18 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
job.imageComfyHost = getComfyHost()
await withImageComfyHost(job.imageComfyHost, async () => {
+ const generate = params.mode === 'generate'
emitChainJob(job, {
type: 'status',
- message: params.mode === 'refine'
- ? 'Uploading canvas and mask to Beast...'
- : params.mode === 'compose' ? 'Uploading stills A and B to Beast...' : 'Uploading still A to Beast...',
- progress: 8
+ message: generate
+ ? 'Queueing Klein v2 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...',
+ progress: generate ? 12 : 8
})
- const uploaded = await uploadImage(params.image, job.id)
- const uploadedRef = params.mode === 'refine'
+ const uploaded = generate || !params.image ? null : await uploadImage(params.image, job.id)
+ const uploadedRef = generate || params.mode === 'refine'
? null
: params.reference
? await uploadImage({
@@ -71,7 +80,7 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
filename: `ref_${params.reference.filename || 'image_b.png'}`
}, job.id)
: null
- const uploadedMask = params.mode === 'refine' && params.mask
+ const uploadedMask = !generate && params.mode === 'refine' && params.mask
? await uploadImage({
...params.mask,
filename: `mask_${params.mask.filename || 'refine-mask.png'}`
@@ -79,23 +88,25 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
: null
if (job.status === 'cancelled') throw new Error('Job interrupted.')
- emitChainJob(job, {
- type: 'status',
- message: params.mode === 'refine'
- ? 'Queueing Klein v2 refine on Beast...'
- : params.mode === 'compose'
- ? `Queueing Klein v2 compose (${params.task}) on Beast...`
- : 'Queueing Klein v2 edit on Beast...',
- progress: 12
- })
+ if (!generate) {
+ emitChainJob(job, {
+ type: 'status',
+ message: params.mode === 'refine'
+ ? 'Queueing Klein v2 refine on Beast...'
+ : params.mode === 'compose'
+ ? `Queueing Klein v2 compose (${params.task}) on Beast...`
+ : 'Queueing Klein v2 edit on Beast...',
+ progress: 12
+ })
+ }
await ensureComfyLoraNames('image')
- await assertImageScaleToTotalPixelsNode()
+ if (!generate) await assertImageScaleToTotalPixelsNode()
const built = buildImageV2Workflow({
mode: params.mode,
task: params.task,
prompt: params.prompt,
negative: params.negative,
- imageAName: uploaded.name,
+ imageAName: uploaded?.name,
imageBName: uploadedRef?.name,
maskName: uploadedMask?.name,
strength: params.strength,
@@ -107,6 +118,9 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
cfg: params.cfg,
seed: params.seed,
megapixels: params.megapixels,
+ width: params.width,
+ height: params.height,
+ turbo: params.turbo === true,
filenamePrefix: `aigen_v2_${job.id.slice(0, 8)}`
})
const queued = await queuePrompt(built.graph, job.clientId)
@@ -154,8 +168,8 @@ export async function runEditV2(job: Job, params: EditV2RunParams) {
job.stillId = still?.id
await purgeComfyArtifacts({
video: { filename: output.filename, subfolder: output.subfolder, type: output.type },
- imageName: uploaded.name,
- imageSubfolder: uploaded.subfolder,
+ imageName: uploaded?.name,
+ imageSubfolder: uploaded?.subfolder,
extraImageNames: [uploadedRef?.name, uploadedMask?.name].filter((name): name is string => Boolean(name)),
promptId: job.promptId
})
diff --git a/server/utils/imageWorkflowV2.ts b/server/utils/imageWorkflowV2.ts
index 4059341..c6b9b23 100644
--- a/server/utils/imageWorkflowV2.ts
+++ b/server/utils/imageWorkflowV2.ts
@@ -1,6 +1,7 @@
import editTemplate from '../assets/klein_v2_edit.json'
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 { IMAGE_SCALE_TO_TOTAL_PIXELS } from '~/server/utils/comfy'
import { cachedComfyLoraNames } from '~/server/utils/loras'
import { resolveComfyLoraName, loraIdentityKey } from '~/utils/loras'
@@ -13,7 +14,10 @@ import {
IMAGE_V2_SNOFS_LORA,
IMAGE_V2_SNOFS_MODEL,
IMAGE_V2_DENOISE_DEFAULT,
+ IMAGE_V2_GENERATE_HEIGHT,
+ IMAGE_V2_GENERATE_WIDTH,
clampImageV2Denoise,
+ clampImageV2Size,
clampImageV2Strength,
composeImageV2Prompt,
type ImageV2Mode,
@@ -41,16 +45,20 @@ const CONSISTENCY = '8'
export const IMAGE_V2_EDIT_WORKFLOW = 'klein_v2_edit.json'
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 interface ImageV2BuildParams {
mode: ImageV2Mode
task: ImageV2Task
prompt: string
negative?: string
- imageAName: string
+ imageAName?: string
imageBName?: string
maskName?: string
strength?: number
+ width?: number
+ height?: number
+ turbo?: boolean
snofsModel?: number
snofsClip?: number
consistencyModel?: number
@@ -102,8 +110,30 @@ function graphHasMaskInput(graph: WorkflowGraph) {
})
}
+function bypassLoraNode(graph: WorkflowGraph, id: string, modelFrom: string, clipFrom: string) {
+ delete graph[id]
+ for (const node of Object.values(graph)) {
+ for (const [key, value] of Object.entries(node.inputs)) {
+ if (!Array.isArray(value) || value[0] !== id) continue
+ node.inputs[key] = value[1] === 1 ? [clipFrom, 1] : [modelFrom, 0]
+ }
+ }
+}
+
export function assertImageV2Graph(graph: WorkflowGraph, mode: ImageV2Mode, imageBName?: string) {
const loaders = loadImageNames(graph)
+ if (mode === 'generate') {
+ if (loaders.length) {
+ throw createError({
+ statusCode: 500,
+ statusMessage: 'Generate graph has a required LoadImage. Refusing to run an edit fallback.'
+ })
+ }
+ const latent = Object.values(graph).find(node => node.class_type === 'EmptyFlux2LatentImage')
+ if (!latent) {
+ throw createError({ statusCode: 500, statusMessage: 'Generate graph is missing EmptyFlux2LatentImage.' })
+ }
+ }
if (mode === 'refine') {
const mask = graph[LOAD_MASK]
if (!mask || mask.class_type !== 'LoadImage' || !String(mask.inputs.image || '').trim()) {
@@ -140,7 +170,7 @@ export function assertImageV2Graph(graph: WorkflowGraph, mode: ImageV2Mode, imag
})
}
}
- if (mode !== 'refine' && imageBName && loaders.length < 2) {
+ if (mode !== 'refine' && mode !== 'generate' && imageBName && loaders.length < 2) {
throw createError({
statusCode: 500,
statusMessage: 'image_b was sent but the executed graph has no second image input.'
@@ -161,43 +191,65 @@ export function assertImageV2Graph(graph: WorkflowGraph, mode: ImageV2Mode, imag
export function buildImageV2Workflow(params: ImageV2BuildParams) {
const compose = params.mode === 'compose'
const refine = params.mode === 'refine'
+ const generate = params.mode === 'generate'
if (refine && !String(params.maskName || '').trim()) {
throw createError({ statusCode: 400, statusMessage: 'Refine requires a mask. Refusing to fall back to Edit.' })
}
- const graph = structuredClone(refine ? refineTemplate : compose ? composeTemplate : editTemplate) as WorkflowGraph
+ const graph = structuredClone(
+ generate ? generateTemplate : refine ? refineTemplate : compose ? composeTemplate : editTemplate
+ ) as WorkflowGraph
const prompt = composeImageV2Prompt(params.mode, params.task, params.prompt)
const negative = String(params.negative || '')
const snofsModel = clampImageV2Strength(params.snofsModel, IMAGE_V2_SNOFS_MODEL)
const snofsClip = clampImageV2Strength(params.snofsClip, IMAGE_V2_SNOFS_CLIP)
- const consistencyModel = clampImageV2Strength(params.consistencyModel, IMAGE_V2_CONSISTENCY_MODEL)
- const consistencyClip = clampImageV2Strength(params.consistencyClip, IMAGE_V2_CONSISTENCY_CLIP)
+ const consistencyModel = clampImageV2Strength(
+ params.consistencyModel,
+ generate ? 0 : IMAGE_V2_CONSISTENCY_MODEL
+ )
+ const consistencyClip = clampImageV2Strength(
+ params.consistencyClip,
+ generate ? 0 : IMAGE_V2_CONSISTENCY_CLIP
+ )
const steps = clampImageSteps(params.steps, 24)
const cfg = clampImageCfg(params.cfg, 4)
const strength = refine ? clampImageV2Denoise(params.strength, IMAGE_V2_DENOISE_DEFAULT) : undefined
- const workflowFile = refine ? IMAGE_V2_REFINE_WORKFLOW : compose ? IMAGE_V2_COMPOSE_WORKFLOW : IMAGE_V2_EDIT_WORKFLOW
+ const size = generate ? clampImageV2Size(params.width, params.height) : null
+ const workflowFile = generate
+ ? IMAGE_V2_GENERATE_WORKFLOW
+ : refine ? IMAGE_V2_REFINE_WORKFLOW : compose ? IMAGE_V2_COMPOSE_WORKFLOW : IMAGE_V2_EDIT_WORKFLOW
- setInput(graph, LOAD_A, 'image', params.imageAName)
+ if (!generate) 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, SCHEDULER_DENOISE, 'denoise', strength)
}
+ if (generate && size) {
+ setInput(graph, '14', 'width', size.width)
+ setInput(graph, '14', 'height', size.height)
+ setInput(graph, SCHEDULER, 'width', size.width)
+ setInput(graph, SCHEDULER, 'height', size.height)
+ }
setInput(graph, PROMPT, 'text', prompt)
setInput(graph, NEGATIVE, 'text', negative)
setInput(graph, NOISE, 'noise_seed', params.seed)
setInput(graph, SCHEDULER, 'steps', steps)
setInput(graph, CFG, 'cfg', cfg)
- setInput(graph, SAVE, 'filename_prefix', params.filenamePrefix || 'aigen-v2')
- patchScaleMegapixels(graph, params.megapixels ?? 1)
+ setInput(graph, SAVE, 'filename_prefix', params.filenamePrefix || (generate ? 'aigen-v2-generate' : 'aigen-v2'))
+ if (!generate) patchScaleMegapixels(graph, params.megapixels ?? 1)
setInput(graph, SNOFS, 'lora_name', resolveRequiredLora(IMAGE_V2_SNOFS_LORA, 'SNOFS'))
setInput(graph, SNOFS, 'strength_model', snofsModel)
setInput(graph, SNOFS, 'strength_clip', snofsClip)
- setInput(graph, CONSISTENCY, 'lora_name', resolveRequiredLora(IMAGE_V2_CONSISTENCY_LORA, 'Consistency'))
- setInput(graph, CONSISTENCY, 'strength_model', consistencyModel)
- setInput(graph, CONSISTENCY, 'strength_clip', consistencyClip)
+ if (generate && consistencyModel <= 0 && consistencyClip <= 0) {
+ bypassLoraNode(graph, CONSISTENCY, SNOFS, SNOFS)
+ } else {
+ setInput(graph, CONSISTENCY, 'lora_name', resolveRequiredLora(IMAGE_V2_CONSISTENCY_LORA, 'Consistency'))
+ setInput(graph, CONSISTENCY, 'strength_model', consistencyModel)
+ setInput(graph, CONSISTENCY, 'strength_clip', consistencyClip)
+ }
- assertImageV2Graph(graph, params.mode, refine ? undefined : params.imageBName)
+ assertImageV2Graph(graph, params.mode, generate || refine ? undefined : params.imageBName)
const loaders = loadImageNames(graph)
console.log(JSON.stringify({
@@ -205,18 +257,22 @@ export function buildImageV2Workflow(params: ImageV2BuildParams) {
workflow: workflowFile,
mode: params.mode,
task: params.task,
- canvas: { id: LOAD_A, file: graph[LOAD_A]?.inputs.image },
+ canvas: generate ? undefined : { id: LOAD_A, file: graph[LOAD_A]?.inputs.image },
mask: refine ? { id: LOAD_MASK, file: graph[LOAD_MASK]?.inputs.image } : undefined,
+ size: generate ? { width: size?.width ?? IMAGE_V2_GENERATE_WIDTH, height: size?.height ?? IMAGE_V2_GENERATE_HEIGHT } : undefined,
strength,
+ turbo: params.turbo === true,
loadImage: Object.fromEntries(loaders.map(item => [item.id, { title: item.title, file: item.image }])),
loras: {
snofs: { name: graph[SNOFS]?.inputs.lora_name, model: snofsModel, clip: snofsClip },
- consistency: { name: graph[CONSISTENCY]?.inputs.lora_name, model: consistencyModel, clip: consistencyClip }
+ consistency: graph[CONSISTENCY]
+ ? { name: graph[CONSISTENCY]?.inputs.lora_name, model: consistencyModel, clip: consistencyClip }
+ : { loaded: false, model: 0, clip: 0 }
},
steps,
cfg,
seed: params.seed,
- megapixels: clampImageScaleMegapixels(params.megapixels ?? 1)
+ megapixels: generate ? undefined : clampImageScaleMegapixels(params.megapixels ?? 1)
}))
return { graph, workflowFile, loaders, prompt, strength }
@@ -238,6 +294,7 @@ export const IMAGE_V2_NODE_LABELS: Record = {
'11': 'Encoding image A',
'24': 'Encoding image B',
'33': 'Applying mask',
+ '14': 'Building empty Klein latent',
'19': 'Sampling Klein v2',
'20': 'Decoding still',
'21': 'Saving still'
diff --git a/server/utils/studioQueue.ts b/server/utils/studioQueue.ts
index 265fd5b..f1300c7 100644
--- a/server/utils/studioQueue.ts
+++ b/server/utils/studioQueue.ts
@@ -52,8 +52,8 @@ export interface StudioJobPayload {
scaleToTotalPixels?: boolean
scaleMegapixels?: number
imagePipeline?: 'v1' | 'v2'
- v2Mode?: 'edit' | 'compose' | 'refine'
- v2Task?: 'scene' | 'identity' | 'outfit' | 'face_lock' | 'refine'
+ v2Mode?: 'edit' | 'compose' | 'refine' | 'generate'
+ v2Task?: 'scene' | 'identity' | 'outfit' | 'face_lock' | 'refine' | 't2i'
snofsModel?: number
snofsClip?: number
consistencyModel?: number
@@ -679,14 +679,17 @@ async function startStudioEditJob(item: StudioJob) {
const { runEditV2 } = await import('~/server/utils/imageChainV2')
const payload = item.payload
- if (!payload.stillId || !existsSync(stillPath(item.ownerKey, payload.stillId))) {
+ const generate = payload.imagePipeline === 'v2' && payload.v2Mode === 'generate'
+ if (!generate && (!payload.stillId || !existsSync(stillPath(item.ownerKey, payload.stillId)))) {
throw new Error('The input still is missing from the library')
}
- const image = {
- filename: payload.stillFilename || 'still.png',
- data: readFileSync(stillPath(item.ownerKey, payload.stillId)),
- type: 'image/png'
- }
+ const image = payload.stillId && existsSync(stillPath(item.ownerKey, payload.stillId))
+ ? {
+ filename: payload.stillFilename || 'still.png',
+ data: readFileSync(stillPath(item.ownerKey, payload.stillId)),
+ type: 'image/png'
+ }
+ : null
const refId = payload.referenceStillId
const reference = refId && existsSync(stillPath(item.ownerKey, refId))
? {
@@ -697,7 +700,13 @@ async function startStudioEditJob(item: StudioJob) {
: null
if (payload.imagePipeline === 'v2') {
- const mode = payload.v2Mode === 'compose' ? 'compose' : payload.v2Mode === 'refine' ? 'refine' : 'edit'
+ const mode = payload.v2Mode === 'compose'
+ ? 'compose'
+ : payload.v2Mode === 'refine'
+ ? 'refine'
+ : payload.v2Mode === 'generate'
+ ? 'generate'
+ : 'edit'
const maskId = payload.maskStillId
const mask = mode === 'refine' && maskId && existsSync(stillPath(item.ownerKey, maskId))
? {
@@ -745,8 +754,8 @@ async function startStudioEditJob(item: StudioJob) {
void runEditV2(live, {
mode,
task: payload.v2Task || 'scene',
- image,
- reference: mode === 'refine' ? null : reference,
+ image: mode === 'generate' ? null : image,
+ reference: mode === 'refine' || mode === 'generate' ? null : reference,
mask,
prompt: payload.prompt,
negative: payload.negative || '',
@@ -755,10 +764,13 @@ async function startStudioEditJob(item: StudioJob) {
cfg: payload.cfg,
snofsModel: payload.snofsModel ?? 0.65,
snofsClip: payload.snofsClip ?? 0.35,
- consistencyModel: payload.consistencyModel ?? 0.7,
- consistencyClip: payload.consistencyClip ?? 0.7,
+ consistencyModel: payload.consistencyModel ?? (mode === 'generate' ? 0 : 0.7),
+ consistencyClip: payload.consistencyClip ?? (mode === 'generate' ? 0 : 0.7),
megapixels: payload.scaleMegapixels ?? 1,
- strength: payload.refineStrength
+ strength: payload.refineStrength,
+ width: payload.width,
+ height: payload.height,
+ turbo: payload.turbo === true
}).catch((error) => {
const message = error instanceof Error ? error.message : String(error)
if (live && live.status !== 'error' && live.status !== 'cancelled' && live.status !== 'deferred') {
diff --git a/utils/imageV2.ts b/utils/imageV2.ts
index 63fa535..53b5421 100644
--- a/utils/imageV2.ts
+++ b/utils/imageV2.ts
@@ -1,5 +1,5 @@
-export const IMAGE_V2_MODES = ['edit', 'compose', 'refine'] as const
-export const IMAGE_V2_TASKS = ['scene', 'identity', 'outfit', 'face_lock', 'refine'] as const
+export const IMAGE_V2_MODES = ['edit', 'compose', 'refine', 'generate'] as const
+export const IMAGE_V2_TASKS = ['scene', 'identity', 'outfit', 'face_lock', 'refine', 't2i'] as const
export type ImageV2Mode = (typeof IMAGE_V2_MODES)[number]
export type ImageV2Task = (typeof IMAGE_V2_TASKS)[number]
@@ -38,8 +38,21 @@ export const IMAGE_V2_REFINE_HAND = {
}
export const IMAGE_V2_REFINE_HEAVY = { strength: 0.55 }
export const IMAGE_V2_REFINE_FACE_PROMPT = 'same face as the canvas, same glasses, same cheeks and jaw. Change only the face in the masked area.'
+export const IMAGE_V2_SIZE_SIDES = [768, 1024, 1280] as const
+export const IMAGE_V2_GENERATE_WIDTH = 1024
+export const IMAGE_V2_GENERATE_HEIGHT = 1024
+export const IMAGE_V2_GENERATE_ASPECTS = {
+ '1:1': [1024, 1024],
+ '3:4': [768, 1024],
+ '4:3': [1024, 768],
+ '16:9': [1280, 768],
+ '9:16': [768, 1280]
+} as const
+export type ImageV2GenerateAspect = keyof typeof IMAGE_V2_GENERATE_ASPECTS
+export const IMAGE_V2_GENERATE_SFW = { snofsModel: 0, snofsClip: 0 }
+export const IMAGE_V2_GENERATE_SNOFS = { snofsModel: 0.65, snofsClip: 0.35 }
-export const IMAGE_V2_ROLE_HEADERS: Record, string> = {
+export const IMAGE_V2_ROLE_HEADERS: Record, string> = {
outfit: 'Person, face, body, pose, and background from image 1. Clothing only from image 2. Fit the outfit from image 2 to the body in image 1. Do not copy image 2’s face, body shape, or pose.',
face_lock: 'Body, pose, and scene from image 1. Exact face from image 2.',
identity: 'Same person as image 1. Use image 2 only to reinforce the face. Follow the user’s pose/scene prompt.'
@@ -69,10 +82,36 @@ export function clampImageV2Denoise(raw: unknown, fallback = IMAGE_V2_DENOISE_DE
return Math.min(IMAGE_V2_DENOISE_MAX, Math.max(IMAGE_V2_DENOISE_MIN, Math.round(snapped * 100) / 100))
}
+export function snapImageV2Side(raw: unknown, fallback = IMAGE_V2_GENERATE_WIDTH) {
+ const value = Number(raw)
+ if (!Number.isFinite(value)) return fallback
+ return IMAGE_V2_SIZE_SIDES.reduce((best, side) => (
+ Math.abs(side - value) < Math.abs(best - value) ? side : best
+ ), IMAGE_V2_SIZE_SIDES[0])
+}
+
+export function parseImageV2Aspect(raw: unknown): ImageV2GenerateAspect | null {
+ const value = String(raw || '').trim()
+ return value in IMAGE_V2_GENERATE_ASPECTS ? value as ImageV2GenerateAspect : null
+}
+
+export function clampImageV2Size(width: unknown, height: unknown, aspect?: unknown) {
+ const preset = parseImageV2Aspect(aspect)
+ if (preset) {
+ const [w, h] = IMAGE_V2_GENERATE_ASPECTS[preset]
+ return { width: w, height: h, aspect: preset }
+ }
+ return {
+ width: snapImageV2Side(width, IMAGE_V2_GENERATE_WIDTH),
+ height: snapImageV2Side(height, IMAGE_V2_GENERATE_HEIGHT),
+ aspect: null as ImageV2GenerateAspect | null
+ }
+}
+
export function composeImageV2Prompt(mode: ImageV2Mode, task: ImageV2Task, prompt: string) {
const body = String(prompt || '').trim()
- if (mode === 'refine' || mode !== 'compose' || task === 'scene') return body
- const header = IMAGE_V2_ROLE_HEADERS[task as Exclude]
+ if (mode === 'generate' || mode === 'refine' || mode !== 'compose' || task === 'scene' || task === 't2i') return body
+ const header = IMAGE_V2_ROLE_HEADERS[task as Exclude]
return header ? `${header}\n\n${body}` : body
}
@@ -89,4 +128,6 @@ export type ImageV2PresetSettings = {
megapixels?: number
turbo?: boolean
strength?: number
+ width?: number
+ height?: number
}