Flux 3 video
Flux 3 is an independent preview site for a multimodal AI image and video generator that combines text-to-image, image-to-video, native audio, and action prediction in a single creative workflow. The live playground currently uses FLUX.2 for image generation and Wan 2.2 for video generation while official FLUX 3 access remains coming soon.

Key facts
What is Flux 3 video?
Create images, video, and sound in one connected creative direction without switching between separate tools.
Who is Flux 3 video best for?
Brands, filmmakers, designers, social media teams, and creators
What are its main limitations?
- Not the official FLUX 3 model; uses FLUX.2 and Wan 2.2
- Video generation does not include native audio yet
- Limited video duration and resolution (4s 480p for 16 credits)
- Not open source
Limitations are based on product materials or editorial synthesis; confirm on the official site.
When was this information verified?
July 26, 2026
Sources
- Official homepageofficial homepage · Jul 26, 2026
Key features
- ✓Image generation with FLUX.2 from text and reference images
- ✓Video generation with Wan 2.2 from text or starting image
- ✓Native audio (conceptual, not yet available)
- ✓Action prediction (conceptual world model)
- ✓Reference & continue: preserve subjects and environments across media
- ✓Scene continuity for coherent edits across motion and sound
- ✓Aspect ratio controls (16:9, 9:16, 1:1) and format options (PNG, JPEG, WebP)
Use cases
- →Product visualization and campaign adaptation across formats
- →Pre-visualization for filmmaking and storyboarding
- →Social media content creation with consistent visual language
- →Rapid concept reviews for small creative teams
- →Iterative refinement of scenes using reference images
Pricing
Starter Credits
$0
- · 20 free credits after Google sign-in
- · 1 credit = $0.01 usage allowance
Pay-per-credit
From $0.01 per credit
- · FLUX.2 image generation from 2 credits
- · Wan 2.2 video generation from 16 credits
- · Cost increases with duration and resolution
Free starter credits upon sign-in; then pay-per-credit usage at $0.01 per credit, with image generation starting at 2 credits and video at 16 credits.
Pros
- +Unified multimodal workflow (image, video, audio, action)
- +Reference image support for continuity
- +Easy sign-in with Google and starter credits
- +Modern, creator-friendly interface
Cons
- −Not the official FLUX 3 model; uses FLUX.2 and Wan 2.2
- −Video generation does not include native audio yet
- −Limited video duration and resolution (4s 480p for 16 credits)
- −Not open source
- −No official API documented
Positioning
- Core value: Create images, video, and sound in one connected creative direction without switching between separate tools.
- Ideal for: Brands, filmmakers, designers, social media teams, and creators
- Product type: Web app (live playground)
Frequently asked questions
What is FLUX 3?
FLUX 3 is presented by Black Forest Labs as one multimodal model spanning image, video, audio and action prediction. BFL currently labels it Coming Soon and offers an early-access request.
What can I generate today?
Sign in with Google to receive 20 starter Credits. The live playground currently uses FLUX.2 for image generation and Wan 2.2 for video generation while the official FLUX 3 model remains Coming Soon.
Does live video generation include audio?
Not yet. The current Wan 2.2 video workflow creates silent MP4 video. Native audio is part of Black Forest Labs’ announced FLUX 3 direction, but this site does not claim access before an authorized API is available.
Is this an official Black Forest Labs website?
No. This independent preview experience is not affiliated with, endorsed by or operated by Black Forest Labs.
Can I use a reference image?
Yes. Add a JPG, PNG or WebP image for FLUX.2 image editing or as the starting frame for Wan 2.2 image-to-video. Reference video upload is not enabled in the current release.
How much does generation cost?
One Credit represents one cent of provider usage allowance. FLUX.2 text-to-image starts at 2 Credits, image editing at 3 Credits, and a 4-second 480p Wan 2.2 video costs 16 Credits. Video cost increases with duration and resolution.
You may also like
Curated suggestions based on similar categories.
Manga Translator
AI-powered manga translation tool that preserves context and layout, supporting over 50 languages, vertical/horizontal text detection, and batch processing of PDF/EPUB/CBZ files.
minia.art
minia.art is an AI-powered pixel art generator that creates grid-aligned, style-consistent, limited-color pixel art from text prompts. It is designed for casual creators who want game-ready sprites, scenes, avatars, wallpapers, and social media assets without needing to learn sprite editors.
ailogogenerator
AI Logo Generator creates a professional logo and full brand kit in 60 seconds from a one-sentence description. It generates four logo concepts, a color palette, typography system, and 17 photorealistic mockups using multiple AI models including Recraft, Ideogram, FLUX, and Nano Banana.
HiAPI
HiAPI is a developer-first AI API platform that provides access to multiple leading image, video, and audio generation models through a single API key. It features a unified async task API, persistent artifact storage, callbacks, and transparent pay-as-you-go pricing with top-up packages.
Gemini 3.6 Flash Family
Gemini 3.6 Flash is a multimodal AI model designed for token efficiency in coding, knowledge work, and multimodal tasks, reducing output token usage by 17% compared to its predecessor. It supports text, audio, images, code, and video with up to 1M input tokens and advanced reasoning capabilities.
Arkor
Arkor is a platform that hosts the entire loop for open-weight models: an OpenAI-compatible endpoint, request logs that become training data, managed fine-tuning, and serving for trained adapters. It is currently in alpha and free to use, with paid pricing coming soon.