Powered by Black Forest Labs

FLUX 3 Video · Keyframes on a Timeline, Sound Included

Black Forest Labs — the team behind the FLUX image models — built a video model. On OVOV it renders 5 to 20 seconds at HD or FHD, writes its own synchronised audio, and lets you pin up to ten keyframes along the timeline instead of settling for a first and last frame.

Duration
Aspect
Resolution

AI video examples on OVOV

Real generations from our video models — Veo 3.1, Kling and Seedance. Hover any clip to play, click the speaker icon to hear the audio.

Hover to play · Click speaker to unmute

AI video examples on OVOV

Real generations from our video models — Veo 3.1, Kling and Seedance. Hover any clip to play, click the speaker icon to hear the audio.

Cinematic

Alien Fantasy World

Fragrance

Luxury Perfume Ad

Product

Product Launch Teaser

Travel

Maldives Travel Commercial

Action

Eastern Wuxia Duel

Film

Hollywood Racing Movie

Sci-Fi

Spaceship to the Stars

Lifestyle

Golden Retriever & Butterflies

Food

Sushi Chef at Work

Fashion

Red Dress on the Cliffs

Game Trailer

Midnight Duel

Vlog

Handheld Selfie Vlog

Food

Mouth-watering Food Close-up

Dance

Urban Street Dance

Makeup

Luxury Lipstick Ad

Why FLUX 3 Video is worth a look

Up to ten ordered keyframes, a full HD tier, twenty seconds of runway and a soundtrack written in the same pass — from the team that made the FLUX image models.

Ordered Keyframes, Up to Ten

Upload one image and it becomes the starting frame. Upload two and they become the first and last frame. Upload up to ten and the extra frames are distributed evenly along the timeline, so you are choreographing the whole clip rather than only its ends.

Native Audio, On by Default

FLUX 3 Video writes ambience, effects and motion-matched sound alongside the picture, synchronised to what is on screen. You can switch audio off if you plan to score the clip yourself — the price stays the same either way.

HD and FHD Output

Two resolution tiers: HD at roughly 1280×704 and FHD at roughly 1920×1088. Rough the idea out at HD, then spend FHD credits once the prompt and the keyframes are settled.

5 to 20 Seconds

Four fixed lengths: 5, 10, 15 or 20 seconds. Most of our video models cap out at 15, so the top tier here leaves room for a setup, a turn and a payoff inside one generation.

Seven Ratios, Two of Them Ultrawide

16:9, 9:16, 1:1, 4:3, 3:4, plus 21:9 and 2:1 for cinematic openers and letterboxed title cards. Set the frame before you generate — composition is planned for the ratio you pick.

From the FLUX Team

Black Forest Labs built the FLUX image models that already run on OVOV. FLUX 3 Video is the same lab moving into motion, so the prompt habits that work on their stills carry over.

From prompt or keyframes to a finished clip

Write the shot, optionally pin the frames it has to hit, and FLUX 3 Video renders picture and sound together — nothing to assemble afterwards.

1

Write the shot, or pin the frames

Start from a prompt on its own, or upload between one and ten keyframe images in the order they should appear. Then choose length (5, 10, 15 or 20 seconds), aspect ratio and HD or FHD.

2

FLUX 3 Video renders picture and sound

The model plans motion, lighting and pacing across the whole duration — passing through your keyframes in order if you supplied them — then renders the video with its matching audio track.

3

Download and use it

Take the finished video with audio baked in — no watermark, commercial rights included. If a generation fails or is rejected by content moderation, your credits come straight back in full.

What FLUX 3 Video is good for

Ordered keyframes, an FHD tier and two ultrawide ratios cover the work where the shot has to land on specific images at specific moments — and still sound like something.

Storyboards That Hit Their Marks

When the clip has to pass through images you already have — a logo, a product state, a character pose — pin them as keyframes in order and let the model fill in the motion between them.

  • Up to ten keyframes spread evenly along the timeline
  • Two images gives you classic first-frame-to-last-frame motion
  • Twenty seconds of runway for a multi-beat sequence

FHD Spots and Ultrawide Openers

A brand spot at roughly 1920×1088, or a 21:9 title sequence that reads as film rather than feed. Sound arrives attached, so there is no scoring pass before you can show it to anyone.

  • FHD output for pre-roll, landing pages and client delivery
  • 21:9 and 2:1 for cinematic openers and letterboxed cards
  • Ambience and effects generated with the picture

Vertical Social Cuts

TikTok, Reels and Shorts in 9:16 or 3:4, from a five-second hook to a twenty-second story, with native audio instead of a licensed music bed.

  • 9:16 and 3:4 vertical, or 1:1 for square feed posts
  • Draft at HD, publish the version that matters at FHD
  • A first frame pinned from your own product photo

Atmosphere and Place

Coastal drives, rain on a window, a market waking up — shots that need time to breathe, plus the wind, water and street noise that makes the place believable.

  • Twenty seconds for slow drifting camera moves
  • Environmental audio rendered alongside the visuals
  • FHD for hero videos that sit at the top of a page

Prompt writing guide for FLUX 3 Video

The model reads your prompt and your keyframes together. These habits keep the two pulling in the same direction instead of arguing.

Pin the frames that matter, describe the motion between them

Decide how much you want to pin down

Text on its own gives the model the whole scene to invent. Keyframes take that freedom away image by image. Neither is better — they just need different prompts.

  • Text only: describe setting, subject, camera and sound from scratch
  • With keyframes: describe the movement between them, not the frames themselves
  • Mixed intent is where prompts fail — do not describe a red jacket if your keyframe shows a blue one

Example

"With two keyframes (closed box, open box): "hands lift the flaps in one smooth motion, soft window light, cardboard scrape and a soft thud"."

Order your keyframes deliberately

Count matters as much as content. One image is a starting point. Two are the ends of a journey. Anything more is a schedule the model has to keep, spaced evenly across the length you chose.

  • One image: the clip starts here and moves wherever the prompt says
  • Two images: first and last frame, motion rendered between them
  • Three to ten: intermediate frames land at even intervals along the timeline
  • Upload them in the order they should appear — the sequence is the storyboard

Example

"Four keyframes across 20 seconds land at roughly 0s, 6.7s, 13.3s and 20s — so pick images that make sense five to seven seconds apart."

Plan the arc across the length you chose

Twenty seconds is a long time to hold one idea. Write the progression in the order it should happen, and the model has something to spend the duration on.

  • Open with the setting, bring in the subject, then the movement
  • Name what changes over time: light, weather, distance, speed
  • Five and ten seconds suit one continuous action; fifteen and twenty want a turn in the middle

Example

"The room starts dim and empty, morning light climbs the far wall, dust drifts through the beam, and the camera settles on a cup of coffee going cold."

Write the sound, not just the picture

Audio is generated by default and synchronised to the action, so anything you leave unsaid gets invented for you. One or two lines of sound direction usually keeps it in character.

  • Name the ambience: rain on glass, distant traffic, room tone
  • Name the sounds that match the motion: footsteps, engine, wind
  • Asking for quiet is valid direction — say so if you want it sparse
  • Turning audio off is an option, but it does not reduce the credit cost

Example

"Sound: steady rain on a tin roof, a low roll of thunder in the distance, no music."

Trade praise words for visual facts

Stunning, epic and cinematic tell the model nothing. Materials, colours, light direction and strong verbs do — the same discipline that works on the FLUX image models.

  • Skip: stunning, epic, breathtaking, gorgeous, masterpiece
  • Use verbs with force: slams, drifts, ignites, whips
  • Name the light source and the time of day

Example

"Avoid: "a stunning epic mountain shot". Prefer: "granite ridges under low side light, snow spilling off the crest in a thin plume"."

Choose length, ratio and resolution upfront

FLUX 3 Video offers 5, 10, 15 and 20 seconds, seven aspect ratios and two resolution tiers. Deciding before you generate saves credits and keeps the composition right.

  • 16:9 and 4:3 for landscape, 9:16 and 3:4 for vertical, 1:1 for feeds
  • 21:9 and 2:1 when you want the shot to read as cinema
  • Draft at HD (11 credits per second), finish at FHD (19)
  • Length is fixed to 5, 10, 15 or 20 seconds — round your storyboard to one of them

Example

"A 10-second 21:9 opener: headlights sweeping across a wet runway at dusk, low camera, tyre spray catching the light."

Frequently asked questions









Start Your AI Creative Journey Today

Join OVOV to generate images, videos, music, and voice with AI—unleash limitless creativity.
Sign up now and get 10 free credits instantly. No waiting, start creating right away.