Skywork AI SkyReels V4 unified video model for text-to-video, image-to-video, and reference-to-video generation with optional synchronized sound. Supports 480p, 720p, or 1080p output and 3-15 second clips.
Added May 24, 2026
Approx. Price
$0.240 per video
Model Type
both
Settings
Generation controls available for this model.
Output Format
Default Duration
5
13 duration options
Aspect Ratio
Default
16:9
Options (3)
16:9, 9:16, 1:1
Output aspect ratio for text and reference modes
Duration
Default
5
Options (13)
3 seconds, 4 seconds, 5 seconds, 6 seconds +9 more
3-15 seconds
Generate Sound
Default
No
Enable synchronized sound output. Fast mode disables sound.
Quality Mode
Default
std
Options (2)
Standard, Fast
Standard or faster generation
Resolution
Default
1080p
Options (3)
480p, 720p, 1080p
Output resolution
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#21 / 81
ELO
1209.0
Appearances
3,904
95% CI
-9/9
Image to Video
#11 / 75
ELO
1283.0
Appearances
3,452
95% CI
-10/10
Release Date 2026-03 · Matched as SkyReels V4
Artificial Analysis APIRelated video models
Compare SkyReels V4 with similar models from the same provider or model family.
P-Video Edit
pruna-ai/p-video/editInstruction-based editing for videos up to 15 seconds, with optional reference-image guidance, Draft and Full quality modes, prompt enhancement, and source-audio preservation.
MiniMax H3 Max Turbo
minimax/h3-max-turboMiniMax H3 Max Turbo brings H3 Max prompt understanding and aesthetics to video generation at roughly twice the speed and half the cost while targeting 97% of its quality. Create 5–15 second 480p or 768p clips from text or a starting image, with optional first/last-frame transitions.
MiniMax H3 Spicy Image-to-Video
wavespeed-ai/minimax-h3/image-to-video-spicyOpen-weights MiniMax H3 image-to-video generation with expressive unrestricted motion, native stereo audio, optional last-frame control, 3–15 second clips, and 480p or 768p output.
Gemini Omni Flash 1.1
google/gemini-omni-flash/v1.1Google’s multimodal video model for text-to-video, image animation with optional end frames, multimodal reference generation, and instruction-based video editing. Generates synchronized native audio at resolutions from 360p through 4K.
MiniMax H3 Max
minimax/h3-maxMiniMax H3 Max generates 5–15 second videos at 480p or 768p from a text prompt or a first-frame image, with optional first/last-frame transitions.
Wan 3.0 Prime
alibaba/wan-3.0-primeAccelerated Wan 3.0 video generation in one model. Automatically routes text, first/last-frame images, or multimodal image, video, and audio references to the matching Prime endpoint.