Vivix
Vivix W1
At a glance
Strengths
- Perfect 5.00 on lip-sync: all four spoken and sung lines are word for word in the audio, checked by transcription, with native audio on every clip.
- Multi-shot continuity at 4.96: the cafe sequence, the bench at midday and dusk, the watch and the man in the yellow jacket all keep the same subject across cuts.
- On-screen text is spelled correctly in all four tests.
- The cheapest model we have tested: $0.0033 per second on the standard tier and $0.0133 on the ultrafast one at the credit pack price we paid, and a clip takes about 10 seconds to generate.
Watch-outs
- It cuts to a second shot in prompts that describe a single take: 9 of the 32 single-shot text-to-video clips change angle around the midpoint.
- Hands are its weakest category (4.29): a third hand appears on the cutting board, and the fingers open together instead of one by one.
- The ice cube does not melt, the 360-degree orbit stops at about 270, and the 180-degree product spin at about 100.
When to use it: Dialogue, sequences of shots that must keep the same character and place, and fast iteration. Less suited to a single unbroken take.
Capabilities
| Native audio | Yes |
| Multi-shot sequences | No |
| Image to video | Yes |
| Public API | Yes |
| Max resolution | 720p |
| Max duration | 15s |
Benchmark scores
| Overall | 4.82 / 5 |
| Prompt fidelity | 4.70 |
| Visual quality | 4.94 |
| Physics & motion | 4.59 |
| Subject consistency | 4.97 |
| Audio & sync | 5.00 |
| Average attempts to a usable clip | 1.00 |
| Average generation time | 10s |
| Average cost per run | $0.097 |
| Scored runs | 40 |
By prompt category
| Category | Score | Runs |
|---|---|---|
| Lip-sync | 5.00 | 4 |
| Multi-shot | 4.96 | 4 |
| Faces | 4.92 | 4 |
| On-screen text | 4.92 | 4 |
| Style | 4.92 | 4 |
| Camera | 4.88 | 4 |
| Image to video | 4.88 | 4 |
| Animals | 4.83 | 4 |
| Liquids | 4.58 | 4 |
| Hands | 4.29 | 4 |
Cite this
Free to cite and reuse with a link back. Data is updated as new runs and prices come in, so include the date.
SlopTV. (2026). Vivix W1 benchmark results. Retrieved October 12, 2026, from https://sloptv.co/model/vivix-w1<a href="https://sloptv.co/model/vivix-w1">Vivix W1 benchmark results</a> (SlopTV)The clips
Every score above links to the actual generation it came from. Nothing here is a mockup.
Hands avg 4.29/5
Chopping a pepper
FAILURE MODE: a third hand rests on the board at the bottom of the frame, next to the knife tip, while two other hands hold the knife and the pepper. The blade does pass through the pepper and the slices are plausible. Verified frame by frame.
Counting fingers
Five digits in the open hand, four fingers plus the thumb, verified frame by frame. The thumb opens first and the other four unfold together rather than one at a time, and the picture sits inside a dark rounded border that nobody asked for.
Fretting a guitar chord
Fingertips press the strings and the hand shifts between chord shapes with stable geometry, with matching acoustic guitar audio. Checked frame by frame; slight sliding between positions.
Tying shoelaces
Ends with a finished bow, which few models reach, and finger counts hold during the crossings. The clip cuts to a close-up at about 3.7 seconds, a second shot that was not requested.
Faces avg 4.92/5
Face in a crowd
The man stays still and sharp while an out-of-focus crowd crosses behind him in a train station. Background figures hold together with minor blending between passers-by. Checked frame by frame.
Elderly portrait, slow blink
Deep wrinkles stay sharp under hard side light and there is one complete blink, verified frame by frame. The camera then moves into an extreme close-up of one eye, tighter than the portrait asked for.
Glasses reflection
Round glasses with a window reflection that shifts across the lenses as the head tilts, without warping the frames or the eyes.
Turn and smile
Turns from profile to camera with the same face throughout and breaks into a smile that becomes a laugh.
Liquids avg 4.58/5
Pouring coffee
Continuous pour into clear glass with a level that rises plausibly and backlit steam. Cuts to a second angle at about 3.5 seconds, which the prompt did not ask for.
Honey drizzle
Thick, slow ribbons from a wooden dipper that pool over the butter and run down the side of the stack like real honey.
Ice melting in whisky
Photorealistic cut glass and whisky, but no visible melting: the cube looks the same until the clip cuts to a macro of the base of the glass, where a single drop runs down. Condensation does not build. Verified frame by frame.
Wave on rocks
Chaotic, non-repeating spray and foam on rigid dark rocks under an overcast sky. Shown as two shots with a cut at about 3.5 seconds.
On-screen text avg 4.92/5
Book chapter heading
"CHAPTER ONE" is spelled correctly and stays stable while the camera pushes in.
Neon sign OPEN 24H
"OPEN 24H" reads correctly throughout on a wet street at night. The flicker is there: frame brightness jumps repeatedly during the clip, measured frame by frame.
Bakery sign
"FRESH BREAD DAILY" reads correctly on the painted sign in morning light. Small chalkboards in the window carry illegible pseudo-text.
Printed t-shirt
"SLOP" stays legible on the white t-shirt in every frame. The clip cuts from a medium shot to a close-up of the chest instead of one continuous walk toward the camera. Verified frame by frame.
Multi-shot avg 4.96/5
Cafe, three shots
Three shots in the asked order, wide, medium, then hands around the cup, with the same woman, the same red coat and the same cafe. Checked frame by frame.
Same bench, day and dusk
Midday then dusk on the same bench with matching framing and surroundings.
Watch, wide then macro
Wide then macro on the same blue-dial watch, with matching hands, markers and strap. The lettering on the dial is not real text. Checked frame by frame.
Alley, two angles
From behind down the alley, then front-on as he turns the corner, same man and same yellow jacket. Checked frame by frame.
Lip-sync avg 5/5
Bearded man, long line
Audio says the exact line, transcribed word for word, and the bearded jaw moves with it without warping.
Direct address to camera
Audio says the exact line, transcribed word for word, with eye contact held to the end.
Sung line
Sung "hold on to me", confirmed in the audio, with sustained open vowels and visible breath.
Two-person exchange
Both lines are in the audio in order, spoken by different people, and each mouth stays still while the other speaks.
Camera avg 4.88/5
Crane to skyline
Smooth vertical rise from street level that reveals a stable golden-hour skyline.
Dolly in to a door
Steady push-in down the hallway with the door closed, centred and in proportion.
Handheld follow
Natural handheld shake following a child through tall grass, with coherent running motion.
360 orbit
The camera travels about 270 degrees, from the front past her back to the opposite profile, in one take, but does not close the full 360. The woman, her sweater and the chair hold together. Verified frame by frame.
Animals avg 4.83/5
Pigeon takeoff
The pigeon lifts off cleanly, feet separating from the stone, with wings fully extended at the top of the stroke.
Cat jumping to a counter
Natural take-off and landing with a consistent tabby, but the leap is split across a cut to a second angle rather than shown as one continuous motion. Verified frame by frame.
Dog shaking off water
Wet fur and droplets flying outward in a plausible spray. A cut moves the dog from the lawn to a wet deck halfway through. Checked frame by frame.
Galloping horse
Side profile with four distinct legs and a plausible gallop for the first half; then the camera moves in and the lower legs leave the frame.
Style avg 4.92/5
Anime walk cycle
Clean anime style and the character does cross the frame from left to right, with face and outfit unchanged. Cuts to a medium close-up at about 3.5 seconds.
Claymation wave
Reads as real clay stop-motion, with tool marks and grooves on the palm and face while the figure waves.
1970s film look
Convincing 1970s look with grain, halation and period colour on a coastal road. Cuts from a front view to a rear tracking shot at about 4.3 seconds.
Rotating mug
Plain white mug turns continuously and the handle travels all the way around without jumping or duplicating.
Image to video avg 4.88/5
Animate a landscape
Clouds drift and grass sways while the terrain stays fixed, with no camera move. Compared with the reference image.
Animate a vintage photo
Stays black and white with the original grain and tonality, adding only subtle motion. Compared with the reference image.
Animate a portrait
Same face from first to last frame, with a natural blink and slight hair motion. Compared with the reference image.
Product photo to spin
Rotates about 90 to 120 degrees, until the handle disappears behind the cup, short of the 180 asked for. The geometry stays rigid. Verified frame by frame.