FLUX 3 Video is here. Serious, fun, creative, real, cinematic, whatever you need it to be. Native audio, Text to Video, Image to Video with multiple frames, video continuation, dialogue in multiple languages. Comes with Draft mode so you can explore ideas fast at a fraction of Show more
Video Models
FLUX 3 Text / Image / Start-End / Extend to Video Generator
Generate video with FLUX 3, Black Forest Labs' multimodal frontier model, on Dreamega AI. Write a prompt for text-to-video, animate a reference image for image-to-video, bridge a start frame and an end frame, or continue an existing MP4 clip with video extend. Every mode renders 5 to 20 seconds at 720p or 1080p with native synchronized audio and multilingual dialogue.
Flux Model Series
Flux 2 Max
Top-tier Flux 2 image generation with maximum quality and detail
Flux 2 Pro
Professional Flux 2 image generation with enhanced prompt adherence
Flux 2 Flex
Flexible Flux 2 model for versatile image creation and editing
Flux 2 Klein
Compact Flux 2 model optimized for fast generation
Flux Kontext
Context-aware Flux model for text-to-image and image editing
Flux Krea
Creative Flux model fine-tuned for artistic and stylized outputs
Flux Pro Ultra
Ultra-high-resolution Flux Pro image generation
Flux Dev
Open-weight Flux model ideal for development and experimentation
Flux Schnell
Fastest Flux model for rapid image generation
FLUX 3 Video Gallery
Browse clips generated with FLUX 3 from text prompts. Every example renders in a single pass with native synchronized audio.
AI Video
Courier Fifty Years Late
A bicycle courier reaches an apartment door in a thunderstorm and meets an older version of himself, generated from text.
Prompt
“A young bicycle courier arrives at an apartment door during a thunderstorm, but the digital display shows a date fifty years in the future. The scene opens with a fast tracking shot following him through wet neon streets, then becomes completely still as the door opens. An elderly man with the same face stands inside and looks at him in shock. The camera slowly rotates around both characters while lightning illuminates the corridor. The food bag begins glowing, and nearby objects float into the air. Emotional science-fiction mystery, realistic acting, controlled camera movement, cinematic neon lighting.”
Live PipelineTake 01 / 02
FLUX 3 Image to Video Gallery
See how FLUX 3 brings still images to life. The first clip animates a single reference image; the second bridges a start frame and an end frame with a prompt-guided transition.
Source Feeds01 Inputs
Pipeline
00%
Program · On AirAI · Generated
Output
Transcript · 01
Robot on the Abandoned Platform
The old robot sits alone on an abandoned train platform, holding a faded ticket. Its head slowly rises as distant lights appear along the tracks. The station signs begin illuminating one by one, and a futuristic train silently enters the platform. The camera begins with a close-up of the ticket, tracks across the robot's weathered body, then cranes upward as the train arrives. Emotional science-fiction, quiet storytelling, atmospheric fog, warm and cold light contrast.
Live PipelineTake 01 / 01
FLUX 3 Video Extend Gallery
Continue an existing clip into a new shot. FLUX 3 picks up where the source video ends and keeps characters, lighting and motion continuous.
Source Feeds01 Inputs
Pipeline
00%
Program · On AirAI · Generated
Output
Transcript · 01
Museum Skeleton Comes Alive
Continue directly as the dinosaur skeleton begins moving. It carefully steps down from the exhibition platform, sending small bones and dust across the floor. The paleontologist runs through the gallery while other fossil displays begin moving behind glass cases. The camera tracks beside her, then swings around as she reaches the museum entrance and finds a living prehistoric jungle outside instead of the city. Maintain the same character, clothing, museum layout, lighting, and movement continuity.
FLUX 3 YouTube Videos
Watch community demos, reviews and tutorials showcasing what FLUX 3 can do
- FLUX 3 Is Here — Everything You NEED to Know - ElevenLabs
- Introducing FLUX 3 - Black Forest Labs
- Black Forest Labs FLUX 3: First Look - Bryan Software
- 100+ FLUX 3 AI Videos Scarily Close to Real Life - Airt
- Flux 3 Review: Everything You Need to Know (2026) - Thrive Media
- FLUX 3 - Incredible AI Video Model - Demo Reel - Jerrod Lew
FLUX 3 YouTube Videos
Watch community demos, reviews and tutorials showcasing what FLUX 3 can do
FLUX 3 Popular Reviews on X
See what people are saying about FLUX 3 on X (Twitter)
Introducing FLUX 3. One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style. FLUX 3 Video is now available in early access (link below). Jointly trained in one unified architecture, our model can be extended to Show more
FLUX 3 Video is #2 in the world. To celebrate, FLUX 3 Video is free to use in our playground until Sunday 16th, 11:59pm PT (link in the thread). This is just the beginning of what’s coming. Up next: 4K, video editing, and multiple images & videos as reference input.
Last week, @bfl_ai launched their first video model, FLUX 3 Video. They have been testing an update on @arena, and the new version is ranked #2 in the Text-to-Video Arena! With 1496 pts, the updated FLUX 3 Video is just 16 pts behind the #1 spot, Gemini Omni Flash (1512 pts).
Action: An early version of FLUX 3 is now running on robots. @mimicrobotics was one of the first partners to gain early access to FLUX 3. Together we developed FLUX-mimic, a video-action model combining the FLUX 3 backbone with mimic's expertise in robot learning for dexterous Show more
Black Forest Labs just announced FLUX 3: a unified multimodal model for image, video, audio and action prediction. Founded in Freiburg, Germany, one of the few globally significant European companies in the AI sector. The current release is gated early access, not open source. Show more
FLUX 3 Video is here. Serious, fun, creative, real, cinematic, whatever you need it to be. Native audio, Text to Video, Image to Video with multiple frames, video continuation, dialogue in multiple languages. Comes with Draft mode so you can explore ideas fast at a fraction of
Black Forest Labs video model, which I posted about when it was first teased on their site back in August 2024, is about to arrive in the form of a multimodal Flux 3. A placeholder page was briefly up yesterday at bfl.ai/models/flux-3 before being quickly taken down. It Show more
Reel · Specifications
What's FLUX 3
Black Forest Labs' multimodal frontier model for video with native audio, served on Dreamega AI
- · 015-20sClip Length
- · 021080pMax Resolution
- · 034Modes: Text / Image / Start-End / Extend
- · 047Aspect Ratios
FLUX 3 is Black Forest Labs' first multimodal frontier model: instead of training separate image, video and audio systems, it learns all three jointly in one unified architecture, with the same backbone also used for robot action prediction. The video release generates clips of up to 20 seconds with native synchronized audio, multilingual dialogue with lip-sync, and cinematic camera control. On Dreamega AI it is available in four modes: Text-to-Video builds a clip from a written prompt, Image-to-Video animates a reference image, Start-End to Video bridges two keyframes, and Video Extend continues an existing MP4 clip. Every mode renders 5 to 20 seconds at 720p or 1080p.
Reel · Capabilities
FLUX 3's Powerful Features
What Black Forest Labs' multimodal model brings to text, image and clip driven video generation
- Feature 01 / 08
One Multimodal Model
FLUX 3 learns images, video and audio together in a single unified architecture rather than bolting separate systems together, so motion, sound and picture come from the same understanding of the scene.
- Feature 02 / 08
Native Synchronized Audio
Dialogue, sound effects and ambience are generated in the same pass as the video, tied to what happens on screen. Audio is on by default and adds nothing to the credit cost.
- Feature 03 / 08
Multilingual Dialogue with Lip-Sync
Characters can speak in English, Chinese, Spanish, French, German, Japanese, Portuguese, Russian, Italian, Hindi and more, with lip movement matched to the spoken words.
- Feature 04 / 08
Up to 20 Seconds per Clip
Pick any whole-second length from 5 to 20 seconds and the full clip renders in one generation, long enough for a multi-beat scene or a complete camera move.
- Feature 05 / 08
Start-End Frame Control
Upload a start frame and an end frame and FLUX 3 generates the transition between them, following your prompt for the action, camera movement and mood in between.
- Feature 06 / 08
Video Extend
Continue an existing MP4 clip of up to 15 seconds into a new 5 to 20 second shot while keeping the same characters, clothing, lighting and movement continuity.
- Feature 07 / 08
720p and 1080p Output
Choose 720p for drafts and social delivery or 1080p for final work. Billing is per second at each tier, so short tests stay cheap and only finals cost full price.
- Feature 08 / 08
Seven Aspect Ratios
Render 21:9, 2:1, 16:9, 4:3, 1:1, 3:4 or 9:16 to cover ultrawide film, widescreen, square feeds and vertical shorts without reframing afterwards.
How to Use FLUX 3 Text to Video
Generate a 5 to 20 second clip with sound from a written description
Write Your Prompt
Describe the scene, subject, camera movement, lighting and mood. Include spoken lines in quotes if you want dialogue, and name the language.
FAQ
Frequently Asked Questions
Common questions about FLUX 3 video generation
Still have questions?
FLUX.2 is Black Forest Labs' image generation and editing family. FLUX 3 is a new multimodal frontier model that learns images, video and audio jointly in one architecture, and its first release is a video model: clips of up to 20 seconds with native synchronized audio and multilingual dialogue. Dreamega serves it through WaveSpeed.
Four. Text-to-Video builds a clip from a written prompt. Image-to-Video animates a reference image you upload while keeping the subject's appearance. Start-End to Video generates the transition between a start frame and an end frame. Video Extend continues an existing MP4 clip of up to 15 seconds into a new shot.
Output is 720p or 1080p. Duration is any whole number of seconds from 5 to 20, and the clip renders in a single generation. Seven aspect ratios are available: 21:9, 2:1, 16:9, 4:3, 1:1, 3:4 and 9:16.
Yes. Audio is produced together with the picture and is on by default, covering dialogue, sound effects and ambience. Dialogue can be in many languages, including English, Chinese, Spanish, French, German, Japanese, Portuguese, Russian, Italian and Hindi, with lip-sync. You can switch audio off if you want silent footage.
Video Extend accepts a single MP4 file of up to 15 seconds and 50 MB. The new clip continues from where the input ends, so describe the next action in your prompt and set the aspect ratio to match the source video.
Billing is per second of generated video in every mode: 26 credits per second at 720p and 44 credits per second at 1080p. A 5-second 720p clip costs 130 credits and a 10-second 1080p clip costs 440. Audio generation is included at no extra charge.
Pricing · Choose Yours
Flexible AI Pricing
Pay-as-you-go credits or subscription plans. No hidden fees, cancel anytime.
One Time supports crypto payment (BTC, USDT, ETH, 350+)
Monthly billing