Skip to main content
ArtEmotion
Image

ERNIE-Image LoRA Turbo

Credit-based pricing. Supports batch up to 4.

ERNIE-Image LoRA Turbo preview
Output
image
Aspect ratio
1:1, 16:9, 9:16, 4:3, 3:4, Custom
Resolution
1024, 2048
Max batch
4

Inputs

  • Batch up to 4 per request

Example prompt

A cyberpunk Hong Kong night market, neon signs in Chinese characters reflected in rain-soaked cobblestones, steaming street food stalls, flying delivery drones overhead, crowds wearing glowing AR devices, ultra-detailed urban photography aesthetic
Try this prompt →
LLM-ready

API & LLM schema

Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/ernie-image/lora/turbo.

POST/api/v1/generate24 fields · 2 required
FieldTypeRequirementContract
model_idconstantRequiredArtEmotion model identifier.
extraobjectOptionalModel-specific settings may also be nested here.
max_creditsnumberOptionalReject before submission if the estimated list price exceeds this cap. · Range: 1–…
webhook_urlstringOptionalFormat: uri
webhook_secretstringOptionalOptional model input.
folder_idstringOptionalOptional model input.
promptstringRequiredOptional model input.
num_inference_stepsnumberOptionalNumber of denoising steps. Turbo model is optimized for 8 steps. · Default: 8 · Range: 1–20
guidance_scalenumberOptionalClassifier-free guidance scale. · Default: 1 · Range: 1–20
seedintegerOptionalRandom seed for reproducibility.
accelerationstringOptionalThe acceleration level to use for the image generation. · Allowed: none, regular, high · Default: regular
enable_prompt_expansionbooleanOptionalIf True, the prompt will be enhanced using an LLM for more detailed results. · Default: true
enable_safety_checkerbooleanOptionalEnable NSFW safety checking on the generated images. · Default: true
negative_promptstringOptionalNegative prompt to guide what should not be in the image. · Default:
output_formatstringOptionalOutput image format. · Allowed: jpeg, png · Default: jpeg
lora_pathstringOptionalURL or path to the first LoRA weights. · Default:
lora_scalenumberOptionalBlend strength for LoRA 1 (0 = off, 1 = full, up to 4). · Default: 1 · Range: 0–4
lora_path_2stringOptionalURL or path to the second LoRA weights. · Default:
lora_scale_2numberOptionalBlend strength for LoRA 2. · Default: 1 · Range: 0–4
lora_path_3stringOptionalURL or path to the third LoRA weights. · Default:
lora_scale_3numberOptionalBlend strength for LoRA 3. · Default: 1 · Range: 0–4
aspect_ratiostringOptionalAllowed: 1:1, 16:9, 9:16, 4:3, 3:4, Custom
resolutionstringOptionalAllowed: 1024, 2048
num_imagesintegerOptionalRange: 1–4
Minimal request example
{
  "model_id": "fal-ai/ernie-image/lora/turbo",
  "prompt": "A cyberpunk Hong Kong night market, neon signs in Chinese characters reflected in rain-soaked cobblestones, steaming street food stalls, flying delivery drones overhead, crowds wearing glowing AR devices, ultra-detailed urban photography aesthetic"
}
Raw JSON Schema
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fernie-image%2Flora%2Fturbo",
  "title": "ERNIE-Image LoRA Turbo generation request",
  "description": "Request body accepted by POST /api/v1/generate for fal-ai/ernie-image/lora/turbo.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "fal-ai/ernie-image/lora/turbo",
      "description": "ArtEmotion model identifier."
    },
    "extra": {
      "type": "object",
      "additionalProperties": true,
      "description": "Model-specific settings may also be nested here."
    },
    "max_credits": {
      "type": "number",
      "minimum": 1,
      "description": "Reject before submission if the estimated list price exceeds this cap."
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048
    },
    "webhook_secret": {
      "type": "string",
      "maxLength": 512
    },
    "folder_id": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "num_inference_steps": {
      "title": "Steps",
      "description": "Number of denoising steps. Turbo model is optimized for 8 steps.",
      "default": 8,
      "type": "number",
      "minimum": 1,
      "maximum": 20,
      "multipleOf": 1
    },
    "guidance_scale": {
      "title": "Guidance Scale",
      "description": "Classifier-free guidance scale.",
      "default": 1,
      "type": "number",
      "minimum": 1,
      "maximum": 20,
      "multipleOf": 0.1
    },
    "seed": {
      "title": "Seed",
      "description": "Random seed for reproducibility.",
      "type": "integer"
    },
    "acceleration": {
      "title": "Acceleration",
      "description": "The acceleration level to use for the image generation.",
      "default": "regular",
      "type": "string",
      "enum": [
        "none",
        "regular",
        "high"
      ]
    },
    "enable_prompt_expansion": {
      "title": "Enable Prompt Expansion",
      "description": "If True, the prompt will be enhanced using an LLM for more detailed results.",
      "default": true,
      "type": "boolean"
    },
    "enable_safety_checker": {
      "title": "Enable Safety Checker",
      "description": "Enable NSFW safety checking on the generated images.",
      "default": true,
      "type": "boolean"
    },
    "negative_prompt": {
      "title": "Negative Prompt",
      "description": "Negative prompt to guide what should not be in the image.",
      "default": "",
      "type": "string"
    },
    "output_format": {
      "title": "Output Format",
      "description": "Output image format.",
      "default": "jpeg",
      "type": "string",
      "enum": [
        "jpeg",
        "png"
      ]
    },
    "lora_path": {
      "title": "LoRA 1",
      "description": "URL or path to the first LoRA weights.",
      "default": "",
      "type": "string"
    },
    "lora_scale": {
      "title": "LoRA 1 Scale",
      "description": "Blend strength for LoRA 1 (0 = off, 1 = full, up to 4).",
      "default": 1,
      "type": "number",
      "minimum": 0,
      "maximum": 4,
      "multipleOf": 0.05
    },
    "lora_path_2": {
      "title": "LoRA 2",
      "description": "URL or path to the second LoRA weights.",
      "default": "",
      "type": "string"
    },
    "lora_scale_2": {
      "title": "LoRA 2 Scale",
      "description": "Blend strength for LoRA 2.",
      "default": 1,
      "type": "number",
      "minimum": 0,
      "maximum": 4,
      "multipleOf": 0.05
    },
    "lora_path_3": {
      "title": "LoRA 3",
      "description": "URL or path to the third LoRA weights.",
      "default": "",
      "type": "string"
    },
    "lora_scale_3": {
      "title": "LoRA 3 Scale",
      "description": "Blend strength for LoRA 3.",
      "default": 1,
      "type": "number",
      "minimum": 0,
      "maximum": 4,
      "multipleOf": 0.05
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "1:1",
        "16:9",
        "9:16",
        "4:3",
        "3:4",
        "Custom"
      ]
    },
    "resolution": {
      "type": "string",
      "enum": [
        "1024",
        "2048"
      ]
    },
    "num_images": {
      "type": "integer",
      "minimum": 1,
      "maximum": 4
    }
  },
  "required": [
    "model_id",
    "prompt"
  ],
  "additionalProperties": false
}

FAQ

How much does ERNIE-Image LoRA Turbo cost on ArtEmotion?

Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.

Do I get my credits back if ERNIE-Image LoRA Turbo fails?

Yes — failed generations are never charged. The credits are released back to your balance automatically.

Can I call ERNIE-Image LoRA Turbo from the API?

Yes. Use POST /api/v1/generate with model_id: "fal-ai/ernie-image/lora/turbo". See the API reference for the full schema.

Where are my generations stored?

Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.

Ready to generate with ERNIE-Image LoRA Turbo?

Start now →

No commitment. New accounts get 50 free credits on signup. See pricing.