Image
HiDream Edit
Credit-based pricing. Supports reference images, batch up to 4.

Output
image
Aspect ratio
1:1, 16:9, 9:16, 4:3, 3:4
Resolution
1024, 2048
Max batch
4
Inputs
- Reference image (required)
- Batch up to 4 per request
Example prompt
Transform her into a Victorian-era aristocrat wearing an elaborate emerald green silk gown with gold embroidery and a pearl necklace, ornate upswept hair adorned with jeweled pins, standing in a grand 19th century parlour with velvet drapes, gilded mirrors, and candlelit chandeliers, oil painting realismTry this prompt →
LLM-ready
API & LLM schema
Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/hidream-i1-full/image-to-image.
POST
/api/v1/generate27 fields · 3 required| Field | Type | Requirement | Contract |
|---|---|---|---|
model_id | constant | Required | ArtEmotion model identifier. |
extra | object | Optional | Model-specific settings may also be nested here. |
max_credits | number | Optional | Reject before submission if the estimated list price exceeds this cap. · Range: 1–… |
webhook_url | string | Optional | Format: uri |
webhook_secret | string | Optional | Optional model input. |
folder_id | string | Optional | Optional model input. |
prompt | string | Required | Optional model input. |
num_inference_steps | number | Optional | Number of inference steps. More = higher quality, slower. · Default: 50 · Range: 1–50 |
guidance_scale | number | Optional | How closely to follow the prompt. Higher = more faithful, less creative. · Default: 5 · Range: 0–20 |
strength | number | Optional | Denoising strength. 0 = identical to input, 1 = full transformation. · Default: 0.75 · Range: 0–1 |
negative_prompt | string | Optional | Elements to exclude from the image — colors, objects, styles, or qualities to avoid. · Default: |
enable_safety_checker | boolean | Optional | Filter potentially unsafe content from the output. · Default: true |
lora_path | string | Optional | URL or Hugging Face path to LoRA weights (e.g. username/repo or https://…). |
lora_scale | number | Optional | Strength of the LoRA effect. 1 = default weight, higher = stronger influence. · Default: 1 · Range: 0–4 |
lora_weight_name | string | Optional | Safetensors filename within the HuggingFace repo (only needed if the repo has multiple .safetensors files). |
lora_path_2 | string | Optional | URL or Hugging Face path to a second set of LoRA weights. |
lora_scale_2 | number | Optional | Strength of the second LoRA. · Default: 1 · Range: 0–4 |
lora_weight_name_2 | string | Optional | Safetensors filename for the second LoRA repo (optional). |
lora_path_3 | string | Optional | URL or Hugging Face path to a third set of LoRA weights. |
lora_scale_3 | number | Optional | Strength of the third LoRA. · Default: 1 · Range: 0–4 |
lora_weight_name_3 | string | Optional | Safetensors filename for the third LoRA repo (optional). |
output_format | string | Optional | The format of the generated image. · Allowed: jpeg, png · Default: jpeg |
seed | integer | Optional | The same seed and the same prompt will output the same image every time. |
aspect_ratio | string | Optional | Allowed: 1:1, 16:9, 9:16, 4:3, 3:4 |
resolution | string | Optional | Allowed: 1024, 2048 |
num_images | integer | Optional | Range: 1–4 |
reference_image_url | string | Required | Format: uri |
Minimal request example
{
"model_id": "fal-ai/hidream-i1-full/image-to-image",
"prompt": "Transform her into a Victorian-era aristocrat wearing an elaborate emerald green silk gown with gold embroidery and a pearl necklace, ornate upswept hair adorned with jeweled pins, standing in a grand 19th century parlour with velvet drapes, gilded mirrors, and candlelit chandeliers, oil painting realism",
"reference_image_url": "https://example.com/reference_image"
}Raw JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fhidream-i1-full%2Fimage-to-image",
"title": "HiDream Edit generation request",
"description": "Request body accepted by POST /api/v1/generate for fal-ai/hidream-i1-full/image-to-image.",
"type": "object",
"properties": {
"model_id": {
"type": "string",
"const": "fal-ai/hidream-i1-full/image-to-image",
"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 inference steps. More = higher quality, slower.",
"default": 50,
"type": "number",
"minimum": 1,
"maximum": 50,
"multipleOf": 1
},
"guidance_scale": {
"title": "Guidance Scale",
"description": "How closely to follow the prompt. Higher = more faithful, less creative.",
"default": 5,
"type": "number",
"minimum": 0,
"maximum": 20,
"multipleOf": 0.1
},
"strength": {
"title": "Strength",
"description": "Denoising strength. 0 = identical to input, 1 = full transformation.",
"default": 0.75,
"type": "number",
"minimum": 0,
"maximum": 1,
"multipleOf": 0.01
},
"negative_prompt": {
"title": "Negative Prompt",
"description": "Elements to exclude from the image — colors, objects, styles, or qualities to avoid.",
"default": "",
"type": "string"
},
"enable_safety_checker": {
"title": "Safety Checker",
"description": "Filter potentially unsafe content from the output.",
"default": true,
"type": "boolean"
},
"lora_path": {
"title": "LoRA Path",
"description": "URL or Hugging Face path to LoRA weights (e.g. username/repo or https://…).",
"type": "string"
},
"lora_scale": {
"title": "LoRA Scale",
"description": "Strength of the LoRA effect. 1 = default weight, higher = stronger influence.",
"default": 1,
"type": "number",
"minimum": 0,
"maximum": 4,
"multipleOf": 0.05
},
"lora_weight_name": {
"title": "LoRA Weight Name",
"description": "Safetensors filename within the HuggingFace repo (only needed if the repo has multiple .safetensors files).",
"type": "string"
},
"lora_path_2": {
"title": "LoRA Path 2",
"description": "URL or Hugging Face path to a second set of LoRA weights.",
"type": "string"
},
"lora_scale_2": {
"title": "LoRA Scale 2",
"description": "Strength of the second LoRA.",
"default": 1,
"type": "number",
"minimum": 0,
"maximum": 4,
"multipleOf": 0.05
},
"lora_weight_name_2": {
"title": "LoRA Weight Name 2",
"description": "Safetensors filename for the second LoRA repo (optional).",
"type": "string"
},
"lora_path_3": {
"title": "LoRA Path 3",
"description": "URL or Hugging Face path to a third set of LoRA weights.",
"type": "string"
},
"lora_scale_3": {
"title": "LoRA Scale 3",
"description": "Strength of the third LoRA.",
"default": 1,
"type": "number",
"minimum": 0,
"maximum": 4,
"multipleOf": 0.05
},
"lora_weight_name_3": {
"title": "LoRA Weight Name 3",
"description": "Safetensors filename for the third LoRA repo (optional).",
"type": "string"
},
"output_format": {
"title": "Output Format",
"description": "The format of the generated image.",
"default": "jpeg",
"type": "string",
"enum": [
"jpeg",
"png"
]
},
"seed": {
"title": "Seed",
"description": "The same seed and the same prompt will output the same image every time.",
"type": "integer"
},
"aspect_ratio": {
"type": "string",
"enum": [
"1:1",
"16:9",
"9:16",
"4:3",
"3:4"
]
},
"resolution": {
"type": "string",
"enum": [
"1024",
"2048"
]
},
"num_images": {
"type": "integer",
"minimum": 1,
"maximum": 4
},
"reference_image_url": {
"type": "string",
"format": "uri"
}
},
"required": [
"model_id",
"prompt",
"reference_image_url"
],
"additionalProperties": false
}FAQ
How much does HiDream Edit 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 HiDream Edit fails?
Yes — failed generations are never charged. The credits are released back to your balance automatically.
Can I call HiDream Edit from the API?
Yes. Use POST /api/v1/generate with model_id: "fal-ai/hidream-i1-full/image-to-image". 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 HiDream Edit?
Start now →No commitment. New accounts get 50 free credits on signup. See pricing.