Video model · February 2026
SkyReels V4 is a video model from Skywork AI. The web interface exposes V4 Fast and Std as selectable generation modes. This remains one model row because distinct API IDs or separate checkpoints are not established. The interface says Fast does not support native audio.
Video model · Jan 29, 2026
SkyReels V3 R2V 14B is a video model from Skywork AI. SkyReels V3 R2V 14B supports reference-image-to-video with multiple subjects. The project also documents audio-guided generation and video-to-video as other V3 tasks.
Video model · Apr 24, 2025
SkyReels V2 DF 14B is a video model from Skywork AI. The same Diffusion Forcing checkpoint supports text-to-video and image-to-video. It can also autoregressively extend videos; that is not counted as another model.
Video model · Apr 24, 2025
SkyReels V2 I2V 14B is a video model from Skywork AI. SkyReels V2 I2V 14B is its own image-to-video checkpoint, not an alias for the DF T2V weights.
Video model · Apr 24, 2025
SkyReels V2 T2V 14B is a video model from Skywork AI. SkyReels V2 T2V 14B uses distinct text-to-video weights. The vendor overview still marks a 1.3B T2V checkpoint as coming soon rather than released.
Video model · Apr 21, 2025
SkyReels V2 DF 1.3B is a video model from Skywork AI. One Diffusion Forcing checkpoint supports text-to-video, image-to-video, and autoregressive extension; these tasks do not create additional model rows.
Video model · Apr 21, 2025
SkyReels V2 I2V 1.3B is a video model from Skywork AI. SkyReels V2 I2V 1.3B supports image-to-video with a text prompt and a supplied first frame.