SI Super Intelligence video studio
FLUX 3 Max online: text or a photo to video with sound
Sign in, then try 100 credits for $4.99 or subscribe from $10.39 a month billed yearly. No API key.
Sent to the model as you write it. Any language works.0/2000
Settings
Made with FLUX 3 Max
Unedited FLUX 3 Max clips we made on October 20, 2026 (720p, sound on), each with the exact prompt we sent.
Rainy morning vlog
Format 16:9, 10 seconds.
A 10-second ultra-photorealistic live-action smartphone vlog. A European brunette in her mid-20s on a rainy morning. 0-4s: she looks out a rain-streaked window holding a fresh mug of coffee and says to the camera: "Good morning... apparently, it's raining." 4-10s: she walks down a wet city street under a black umbrella, puddles and reflections, traffic passing, turns the phone to herself and says: "First coffee. Then lecture." Natural handheld movement, subtle shake, autofocus changes, realistic rain and wet clothing, natural expressions. Natural diegetic audio only: rain on the umbrella, footsteps in puddles, passing cars, her voice. No music, no narration, no subtitles, no logos, no watermark. Every person is an original fictional adult.
Adapted from a prompt by @nawalsehar
Anime katsudon ASMR
Format 16:9, 10 seconds.
A 10-second fast-paced cinematic Japanese anime cooking video of katsudon. High-quality original anime film style, warm summer light in a Japanese kitchen, ultra-detailed food textures, visible steam, macro close-ups, smooth camera moves, quick match cuts on motion and shape. 0-2s: a breaded pork cutlet is lowered into hot golden oil, intense bubbling. 2-4s: the fried cutlet is sliced on a wooden board, the crust cracks, steam escapes. 4-6s: the slices are placed over onions simmering in amber dashi. 6-8s: beaten golden egg is poured over and sets, glossy and trembling. 8-10s: the finished katsudon in a blue-and-white bowl over rice, topped with mitsuba, slow push-in as steam rises. Audio: bright 1980s Japanese city-pop instrumental with synced ASMR cooking sounds: frying sizzle, knife crunch, bubbling dashi, egg pouring, a soft ceramic clink. No text, captions, logos or UI.
Adapted from a prompt by @Goodmanprotocol
Seoul night camcorder vlog
Format 9:16, 10 seconds.
A 10-second ultra-realistic personal home video of an ordinary summer evening, filmed by a friend on an early-2000s consumer DV camcorder: strong handheld shake, imperfect framing, autofocus hunting, exposure shifts, faded colors, mild noise. A young woman in her early 20s, minimal makeup, long black hair in a messy side ponytail, pastel-blue short top, loose cream pajama pants, black sneakers, thin silver necklace. A quiet older Seoul residential lane at dusk: narrow concrete street, potted plants, bicycles, utility poles and overhead wires, a tiny bakery with warm light. 0-3s: she steps out of the bakery holding a warm pastry and takes her first bite, then smiles because it tastes good. 3-6s: she notices her friend filming and playfully holds the pastry toward the camera. 6-10s: a neighborhood cat follows her for a few steps; she crouches and gently pets it, laughing. Sound: camcorder mic hiss, cicadas, distant traffic, her soft laugh. Keep her face, hair and clothes the same throughout. Every person is an original fictional adult. No text, no logos, no watermark.
Adapted from a prompt by @AIwithkhan
Selfie skincare talk
Format 9:16, 10 seconds.
A 10-second vertical ultra-photorealistic close-up selfie vlog, filmed on a phone held at arm's length. Not an ad: a young woman in her mid 20s talking to her own camera at the end of the day. Light-brown wavy hair with a few strands on her cheek, freckles, bare face, small hoop earrings, oversized white linen shirt. Villa bedroom at golden hour, white wall and soft blurred greenery behind her, low warm sun from frame-left, no ring light. Close-up throughout. 0-3s: she pushes hair off her face, lifts a plain frosted light-blue glass jar with no label beside her cheek and says: "Okay. Last thing, then bed." 3-6s: macro on two fingertips dragging through thick mint-blue gel, a thread of gel stretches and snaps; she says: "It's cold, by the way." 6-10s: she taps the gel onto her cheek and presses it in, winces at the cold, then smiles at the screen. Natural handheld drift, one quick autofocus hunt. Sound: her voice close to the phone mic, quiet room tone. Every person is an original fictional adult. No logos, no brand names, no text on the jar, no captions.
Adapted from a prompt by @abxxai
Scorpion to high heel
Format 9:16, 10 seconds.
A 10-second close-up vertical shot of a magical transformation. A woman's bare foot steps down onto a large ornate scorpion made of polished black obsidian, dark red rubies and gold metal accents, resting on a polished marble floor. As her foot touches it, the scorpion seamlessly morphs and wraps around her foot, transforming into a luxury jeweled high-heeled shoe and anklet: the tail curves around her ankle into a gem-studded strap, the claws form the pointed toe, the body shapes into a sleek jeweled stiletto heel. Cinematic lighting, photorealistic, luxury fashion aesthetic, rich depth of field, bright sunlight filtering through a grand glass greenhouse palace in the background. Sound: crystalline chimes, metallic clicks as the pieces lock into place, a soft shimmer. No text, no logos.
Adapted from a prompt by @juliaevee
Hand-drawn chocolate bread
Format 16:9, 10 seconds.
A 10-second original Japanese-style hand-drawn 2D cooking animation, exactly 4 scenes of 2.5 seconds each with clean hard cuts. Fully hand-drawn look: soft clear pencil outlines with slight line wobble, clean 2-3 tone cel coloring in warm mid tones, painted kitchen backgrounds, subtle analog film grain. Only the forearms and two hands of an adult woman are visible, ivory linen sleeves, no face. Warm morning light from a window at top left, white quartz counter, worn oak board. Scene 1: a knife chops a dark chocolate block into small pieces. Scene 2: low macro at the bowl rim, the chocolate melts into hot cream as a brown spatula stirs three widening circles into glossy ganache. Scene 3: two hands fold cocoa flour and liquid into a shaggy dough. Scene 4: the hands knead the dough smooth and elastic, then a fingertip presses the risen dome and the dent slowly springs back. Sound: quiet kitchen room tone and contact sounds only: dry knife cuts, wet spatula, dough sticking, a bowl ring. No music, no dialogue, no text, captions, labels or logos.
Adapted from a prompt by @riotboy2024
Latte art pour
Format 16:9, 5 seconds.
A cinematic shot of a barista pouring latte art into a white cup in a sunlit cafe, slow push-in from a low angle, steam rising, warm morning light through the window. Sound: soft espresso machine hiss, cups clinking, quiet cafe chatter. Every person is an original fictional adult.
Earbuds product ad
Format 9:16, 5 seconds.
A premium product ad: a matte black wireless earbud case rotates slowly on a wet black stone, the lid opens and the earbuds glow softly, water droplets and rim light, macro close-up, then a clean hero shot. Sound: subtle bass hit, soft whoosh, a satisfying click when the lid opens. No text, no logos.
Photo to video: a wave hello
Format 9:16, 5 seconds.
Made from this photo (image to video)
The young woman smiles, lifts her hand and waves at the camera, then says in a warm voice: "Hey, this is FLUX 3 Max." A light breeze moves her hair. Soft street ambience, distant traffic. Handheld camera slowly pushes in.
Photo to video: dog runs to camera
Format 3:4, 5 seconds.
Made from this photo (image to video)
The golden retriever wags its tail, tilts its head, then runs happily toward the camera across the grass. Sound: happy panting, a short bark, birds chirping in the backyard. Camera stays at dog eye level.
How to make a video with FLUX 3 Max
- Pick what to start from: text only, an image as the first frame, or a first and a last frame.
- Write your prompt in your own words, in any language, up to 2,000 characters. Not sure what to write? Try one of the examples.
- Choose the length (5 to 20 seconds), 720p or 1080p, the format (16:9, 9:16, 1:1 and more) and whether you want sound.
- Press Generate and sign in with Google or email. Our test videos took 17 to 31 seconds on the model, plus a few safety checks here.
What you get
- An MP4 video, 5 to 20 seconds, at 720p or 1080p (1080p is upscaled from 720p by the model), with sound if you leave it on.
- No watermark and no Flux3Max SI logo in the video.
- Kept for 30 days in your history; download it as many times as you like.
Prices
There is no free video, but a new account can try 100 credits for $4.99 once (two 5-second 720p videos). Subscribe: Basic gives 250 credits a month for $12.99, Pro 600 for $29.99, Studio 1,450 for $69.99, and yearly billing takes 20% off (Basic works out to $10.39 a month); plan credits reset every month. Or buy a pack once: 160 credits for $9.99, 340 for $19.99 or 900 for $49.99; these never expire. A 5-second 720p video uses 50 credits. See all prices.
Questions
Is FLUX 3 Max free to use?
There is no free video here, but a first try is $4.99: sign in and buy 100 credits once (two 5-second 720p videos). After that, plans start at $10.39 a month billed yearly and packs at $9.99. On fal’s own API FLUX 3 Max is paid per second: $0.0425 a second at 720p until November 7, 2026, then $0.17.
How much does a FLUX 3 Max video cost here?
A second of video takes 10 credits at 720p and 17 at 1080p, so a 5-second 720p video uses 50. A new account can try 100 credits for $4.99 once. Credit packs, paid once: 160 credits for $9.99, 340 for $19.99, 900 for $49.99. Plans give 250 to 1,450 credits a month, from $10.39 a month billed yearly. Pricing has the full table.
How long does it take?
In our tests on fal, a 5-second 720p video came back in 17 to 26 seconds and a 10-second one in 23 to 31, queue included. Our safety checks add a little on top. You can leave the page: the video waits in your history.
Can I turn my own photo into a video?
Yes. Pick Image to video and upload a JPG, PNG or WebP under 25 MB; it becomes the first frame. Add a second image as the last frame if you want the video to end on it. Tick the box confirming you have the right to use the photo.
Does FLUX 3 Max make sound?
Yes. Sound is on by default and follows what you describe: rain, cooking, music, voices. Switch it off to get a silent clip; the price is the same.
FLUX 3 Max or Seedance 2.5?
fal says FLUX 3 Max ties Seedance 2.5 for first place in Artificial Analysis’s preliminary image-to-video arena (1,139 Elo) and makes a 10-second clip in about 11 seconds, against about 278 for Seedance 2.5. Both numbers are fal’s and preliminary.
What does SI stand for in Flux3Max SI?
Super Intelligence. It is the name of our studio: one place to use the most capable new AI video models without code or an API key, starting with FLUX 3 Max, with image models and other makers' models to follow. The videos are made by those models; we run them for you.
Is Flux3Max SI made by fal or Black Forest Labs?
No. Flux3Max SI is an independent service that runs FLUX 3 Max through fal's API. It is not affiliated with, endorsed by or sponsored by fal or Black Forest Labs. FLUX is a trademark of Black Forest Labs.
Can I put a real person or a celebrity in the video?
Your own photo, or one of someone who agreed, yes: tick the box that says you have the right to use it. Public figures and anyone under 18 are not allowed, prompts that name real people are refused, and every image and video passes an automated safety check.
What if a video fails?
Its credits come back automatically, and you can try again.