Video
Bernini-R Reference Edit
Credit-based pricing. Supports reference images, reference video.
Output
video
Inputs
- Reference image (required)
- Reference video (required)
Example prompt
Replace the presenter's outfit with the jacket from the reference images, keep the lighting, motion and background unchangedTry this prompt →
LLM-ready
API & LLM schema
Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/bernini-r/reference-edit-video.
POST
/api/v1/generate17 fields · 4 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. |
negative_prompt | string | Optional | Leave blank to keep the model's tuned Wan2.2 default negative prompt. · Default: |
num_inference_steps | number | Optional | Number of denoising steps. · Default: 30 · Range: 1–50 |
max_image_size | number | Optional | Long-edge size in pixels — sets output size for generation and caps source/reference media for edits. Billing scales with this tier. · Allowed: 576, 848, 1280 · Default: 848 |
num_frames | number | Optional | Number of frames (snapped internally to 4k+1). Output length = frames ÷ FPS. · Default: 81 · Range: 5–121 |
frames_per_second | number | Optional | Output frames per second. · Default: 16 · Range: 4–30 |
acceleration | string | Optional | 'regular' enables MagCache step-skipping for faster generation at a small quality cost. · Allowed: none, regular · Default: none |
enable_prompt_expansion | boolean | Optional | Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts. · Default: false |
seed | integer | Optional | Seed for reproducibility. Random when omitted. |
reference_image_urls | array<string> | Required | Items: 0–5 |
video_url | string | Required | Format: uri |
Minimal request example
{
"model_id": "fal-ai/bernini-r/reference-edit-video",
"prompt": "Replace the presenter's outfit with the jacket from the reference images, keep the lighting, motion and background unchanged",
"reference_image_urls": [],
"video_url": "https://example.com/video"
}Raw JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fbernini-r%2Freference-edit-video",
"title": "Bernini-R Reference Edit generation request",
"description": "Request body accepted by POST /api/v1/generate for fal-ai/bernini-r/reference-edit-video.",
"type": "object",
"properties": {
"model_id": {
"type": "string",
"const": "fal-ai/bernini-r/reference-edit-video",
"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"
},
"negative_prompt": {
"title": "Negative Prompt",
"description": "Leave blank to keep the model's tuned Wan2.2 default negative prompt.",
"default": "",
"type": "string"
},
"num_inference_steps": {
"title": "Steps",
"description": "Number of denoising steps.",
"default": 30,
"type": "number",
"minimum": 1,
"maximum": 50,
"multipleOf": 1
},
"max_image_size": {
"title": "Output Size (long edge)",
"description": "Long-edge size in pixels — sets output size for generation and caps source/reference media for edits. Billing scales with this tier.",
"default": "848",
"type": "number",
"enum": [
576,
848,
1280
]
},
"num_frames": {
"title": "Num Frames",
"description": "Number of frames (snapped internally to 4k+1). Output length = frames ÷ FPS.",
"default": 81,
"type": "number",
"minimum": 5,
"maximum": 121,
"multipleOf": 1
},
"frames_per_second": {
"title": "FPS",
"description": "Output frames per second.",
"default": 16,
"type": "number",
"minimum": 4,
"maximum": 30,
"multipleOf": 1
},
"acceleration": {
"title": "Acceleration",
"description": "'regular' enables MagCache step-skipping for faster generation at a small quality cost.",
"default": "none",
"type": "string",
"enum": [
"none",
"regular"
]
},
"enable_prompt_expansion": {
"title": "Prompt Expansion",
"description": "Rewrite the prompt with an LLM before generation. The model is tuned on enhanced prompts.",
"default": false,
"type": "boolean"
},
"seed": {
"title": "Seed",
"description": "Seed for reproducibility. Random when omitted.",
"type": "integer"
},
"reference_image_urls": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"maxItems": 5
},
"video_url": {
"type": "string",
"format": "uri"
}
},
"required": [
"model_id",
"prompt",
"reference_image_urls",
"video_url"
],
"additionalProperties": false
}FAQ
How much does Bernini-R Reference 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 Bernini-R Reference Edit fails?
Yes — failed generations are never charged. The credits are released back to your balance automatically.
Can I call Bernini-R Reference Edit from the API?
Yes. Use POST /api/v1/generate with model_id: "fal-ai/bernini-r/reference-edit-video". 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 Bernini-R Reference Edit?
Start now →No commitment. New accounts get 50 free credits on signup. See pricing.