muapi Logomuapi Logo
muapi Logomuapi Logo

Kling 4.0 Flash Reference to Video API: Image-to-Video

Generate Kling 4.0 Flash videos from reference images, videos and elements. 3-20s, 720p, native audio. Pay per generation, no subscription. Kling 4.0 Flash Reference-to-Video generates 3-20 second 720p clips with native audio from reference images, reference videos and named elements, all addressable in the prompt with @tags.

Interactive model controls

Kling 4.0 Flash Reference-to-Video generates 3-20 second 720p clips with native audio from reference images, reference videos and named elements, all addressable in the prompt with @tags.

📝

Overview

About this model

Kling 4.0 Flash Reference-to-Video generates 3-20 second 720p clips with native audio from your own materials: up to 10 reference images, 5 reference videos and 7 named elements (2-4 images or a 3-8 second character video each), with at most 15 materials in total. Mention each material in the prompt with @image_1, @video_1 or @name, and bind character audio through an element's voice_url. With no materials it behaves as plain text-to-video. For 1080p, 30-second clips and standalone voices use Kling 4.0 Reference to Video; to animate a single still use Kling 4.0 Flash Keyframe to Video.

1Characters: Keep a named character consistent across scenes with image or video elements.
2Voice: Bind a reference voice to a character through the element's voice_url.
3Video-guided shots: Reuse the motion and setting of a reference video, with or without its original sound.
4Ads: Combine product, model and background references into one fast, low-cost shot.
💰

Pricing & Value

Cost analysis

muapiapp$0.094 per second ($0.47 per 5s clip)

$0.094/s of output video for text, keyframe and reference-image requests; $0.126/s when reference videos or video elements are included. 720p only.

** Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Promptstring

Video description (max 8000 chars). Reference materials with @image_1, @video_1 or @name for elements/voices.

Default Value@Hero sits at the desk in @video_1, picks up the doll from @image_1, and greets using @Narrator
Reference Image URLsarray

Up to 10 reference images. Mention as @image_1, @image_2, ... in array order.

Default Valueundefined
Reference Video URLsarray

Up to 5 reference videos (2-30s each, 30s combined). Mention as @video_1, @video_2, ...

Default Valueundefined
Keep Original Soundboolean

Keep the original audio of the reference videos (only applies when video_urls is set).

Default Valuefalse
Elementsarray

Up to 7 named subjects (at most 3 can use video). Each needs 2-4 images or one 3-8 second video, not both. Mention each as @name.

Default Value-
Durationint

Video length in seconds (3-20).

Default Value5
ResolutionEnum (1 options)

Output resolution (Kling 4.0 Flash is 720p only).

Default Value720p
Aspect RatioEnum (5 options)

Output aspect ratio. Defaults to auto when reference media is provided, otherwise 16:9.

Default Value-
📖

Implementation Guide

Developer documentation

How to Use Kling 4.0 Flash Reference to Video

  1. Collect materials: Provide any of image_urls (up to 10), video_urls (up to 5, 2-20s combined with video elements) and elements (up to 7, at most 3 with video).

  2. Mention them in the prompt: @image_1, @video_1 follow array order; @Hero uses the name of an element. Every mention must match a material in the request.

  3. Configure output: duration (3-20s), aspect_ratio (auto, 16:9, 9:16, 1:1, 21:9) and keep_original_sound. Output is always 720p.

  4. Submit and collect the result: poll /api/v1/predictions/{request_id}/result or pass a webhook_url.

curl -X POST https://api.muapi.ai/api/v1/kling-4.0-flash-reference-to-video \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{"prompt": "@Hero sits at the desk, picks up the doll from @image_1 and greets the camera", "image_urls": ["https://example.com/doll.png"], "elements": [{"name": "Hero", "image_urls": ["https://example.com/hero-front.jpg", "https://example.com/hero-side.jpg"], "tag": "character", "voice_url": "https://example.com/hero-voice.mp3"}], "duration": 10}'
❓

Common Questions

Frequently asked

What are the duration and resolution limits?

3 to 20 seconds per clip at 720p only.

How many references can I use?

Up to 10 images, 5 videos and 7 elements (at most 3 video elements), with at most 15 materials in total. Reference videos plus video elements cannot exceed 5, and their combined duration must be 2-20 seconds.

How do I reference materials in the prompt?

Use @image_1, @video_1 in array order, or @name for elements. A mention with no matching material is rejected.

How do I add a voice?

Standalone voices are not supported on Flash. Set voice_url on a character element to bind reference audio to that character.

How is pricing calculated?

Per second of output video: $0.094/s with reference images or no references, and $0.126/s when reference videos or video elements are included. A 5-second clip costs $0.47 or $0.63.

How do I get the result?

The endpoint is asynchronous. Poll /api/v1/predictions/{request_id}/result or pass a webhook_url to be notified when the video is ready.