Pixverse v5.5. Text-to-video, image-to-video, and transition mode (first+last frame morphing). 360p-1080p resolution, 5/8/10s durations. Supports prompt optimization and audio generation.
Added Dec 4, 2025
Approx. Price
$0.850 per video
Model Type
both
Preview Examples
4
Generation controls available for this model.
Resolution/Aspect Options
4
Default Duration
5
3 duration options
Tunable Settings
5
Aspect Ratio (T2V)
Default
16:9
Options (5)
Landscape (16:9), Standard (4:3), Square (1:1), Portrait (3:4) +1 more
Aspect ratio for text-to-video
Duration
Default
5
Options (3)
5 seconds, 8 seconds, 10 seconds
Video length (10s unavailable at 1080p)
Generate Audio
Default
No
Enable audio generation (I2V only)
Prompt Optimization
Default
auto
Options (3)
Auto, Enabled, Disabled
System-level prompt optimization
Resolution
Default
720p
Options (4)
360p, 540p, 720p, 1080p
Video quality level
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#25 / 83
ELO
1199.0
Appearances
3,956
95% CI
-9/9
Image to Video
#17 / 76
ELO
1270.0
Appearances
4,811
95% CI
-10/10
Release Date 2025-12 · Matched as PixVerse V5.5
Artificial Analysis APIAn anime scene on a city rooftop at sunset. Start with a wide shot of a pastel orange sky and distant skyline, wind gently moving laundry lines and antenna cables. Cut to a medium shot of a teenage girl in a school uniform standing at the edge, hair and ribbon blowing in the wind, anime style linework and shading. She turns toward the camera and says softly, 'I'll change everything, starting today.' Soft piano and cicadas in the background, Japanese-anime voice acting, subtle camera shake and zoom for emotional emphasis.
Text-to-video
A fast-paced cyberpunk chase at night. Begin with a wide aerial shot of a neon-lit alley full of holographic signs and rain, a runner in a glowing jacket dashing through the crowd. Cut to a low tracking shot at ground level, water splashing in slow motion as they jump over a puddle, neon reflections everywhere. Final shot: dynamic side view as they leap over a gap between rooftops, the camera whipping past to reveal giant holographic billboards behind them. Style: hyper-realistic cyberpunk, strong magenta and teal lights. Sound: heavy electronic beat, rain, distant sirens, their breath and footsteps clearly audible, no dialogue.
Text-to-video
Use the uploaded anime battle mage illustration as the first frame. Keep the character's face, pose, outfit and background consistent. Start with a medium shot, then slowly dolly the camera in toward his outstretched hand as glowing blue energy builds up, swirling around his arm. In the last third of the clip, let the energy burst outward in a shockwave of light and particles, with slight camera shake and motion blur. Style: high-energy anime action, strong contrast, neon blue and purple highlights. Sound: rising synth and orchestral music, electric crackling, a powerful impact sound at the peak of the blast, no dialogue.
Image-to-video
Create a transformation transition from the casual version of the character in the first image to the armored sci-fi hero in the second image. Keep the face, pose and camera framing consistent as holographic shards, light streaks and metallic plates swirl around the body, gradually replacing the hoodie and jeans with the glowing armor. Realistic cinematic look, cool blue and white lights, rising synth sound and a sharp "whoosh" at the peak of the morph, no dialogue.
Transition (first+last frame)