muapi Logomuapi Logo
muapi Logomuapi Logo

FLUX 3 Omni: Image-to-Video

Generate consistent images and video from multiple references with FLUX 3 Omni Reference. Coming soon on Muapi — reserve your API key today.

📝

Overview

About this model

FLUX 3 Omni exposes Black Forest Labs' Omni Reference mode — a single endpoint that accepts multiple reference images and video clips at once and generates new images or video that keep the same subject, style, and scene consistent across every output. Built on FLUX 3's unified multimodal architecture, Omni Reference extends the instruction-driven editing of FLUX 3 Image to Image to multi-reference, cross-modal inputs, letting a single character, product, or setting stay visually consistent whether the output is a still image or a full video clip. Black Forest Labs lists Omni Reference as coming soon.

1Character Consistency: Keep a character's appearance identical across a series of generated images or clips.
2Product Placement: Combine multiple product reference photos into one consistent generated scene.
3Style Transfer: Apply a reference clip's visual style to new generated output.
4Brand Continuity: Maintain consistent visual identity across a multi-asset marketing campaign.
5Multi-Shot Sequences: Reference earlier frames or clips to keep later generations visually coherent.
💰

Pricing & Value

Cost analysis

muapiTBD at launch

Coming soon — early access via Black Forest Labs, general availability pricing not yet published.

Fal.aiNot available

FLUX 3 Omni is not yet available on Fal.ai.

ReplicateNot available

FLUX 3 Omni is not yet available on Replicate.

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

⚙️

Technical Details

Configuration schema

Promptstring

Text prompt describing the desired output, guided by the reference images/videos.

Default ValueKeep this character and outfit consistent while placing them in a rooftop garden at sunset.
Image URLsarray

Reference image(s) to guide subject, style, or scene.

Default Valuehttps://d3adwkbyhxyrtq.cloudfront.net/ai-images/186/712345784292/4a8c5c70-abcc-4920-873e-b0e219986453.jpg
Video URLsarray

Reference video(s) to guide motion, style, or scene.

Default Valuehttps://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/flux-3-video.mp4
Aspect RatioEnum (6 options)

Aspect ratio of the output.

Default Value16:9
ResolutionEnum (2 options)

Output resolution.

Default Value720p
📖

Implementation Guide

Developer documentation

How to Use FLUX 3 Omni (Coming Soon)

  1. Provide reference images and/or videos via images_list and videos_list.

  2. Write a prompt describing the desired output, guided by those references.

  3. Set aspect_ratio and resolution.

  4. Submit the request once live:

curl -X POST https://api.muapi.ai/api/v1/flux-3-omni \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Keep this character and outfit consistent in a rooftop garden at sunset", "images_list": ["https://example.com/character.jpg"], "aspect_ratio": "16:9"}'
  1. Poll /api/v1/predictions/{id}/result until completed.
❓

Common Questions

Frequently asked

What is FLUX 3 Omni?

FLUX 3 Omni exposes Black Forest Labs' Omni Reference mode — it takes multiple reference images and video clips and generates new images or video that keep the same subject, style, and scene consistent across outputs.

Is FLUX 3 Omni available yet?

No — Black Forest Labs lists Omni Reference as coming soon. Muapi will enable the endpoint as soon as Black Forest Labs opens general API access.

How many reference images or videos can I use?

The planned input schema supports up to 10 reference images and up to 4 reference video clips per request, though final limits may change before launch.

Does FLUX 3 Omni output images, video, or both?

Both — Omni Reference is designed to generate either an image or a video clip depending on your prompt and settings, while keeping subject and style consistent with the supplied references.

How is this different from FLUX 3 Image to Image?

FLUX 3 Image to Image edits a single image with an instruction. FLUX 3 Omni accepts multiple images and videos as references simultaneously and can output either modality, making it suited to cross-modal consistency rather than single-image edits.

How do I get early access to FLUX 3 Omni through Muapi?

Create a free Muapi account and generate an API key today. This endpoint will activate automatically for existing users as soon as Black Forest Labs opens general availability — no separate waitlist required.