Wan 2.2
🎞
19
Reference for Wan 2.2, Alibaba's open video models
Video generation demos
Text-to-video, image-to-video and audio-driven avatar Spaces: Wan, Veo, Sora, Seedance, Hailuo and Vidu.
-
-
Wan2.2-S2V
🗣Reference for Wan2.2-S2V, audio-driven video generation
-
Wan 2.1 Ultra Fast (image to video)
🎬40Wan 2.1 image-to-video at 480p, tuned for speed.
-
Wan 2.1 VACE 14B
🎬10VACE: all-in-one video creation and editing.
-
Wan 2.6 (image to video)
🎬4Alibaba Wan 2.6, animate a still image.
-
Wan 2.6 Flash (image to video)
🎬6The faster Wan 2.6 image-to-video variant, with audio.
-
Wan 2.5
🎬Alibaba Wan 2.5, text to video.
-
Wan 2.5 (image to video)
🎬2Alibaba Wan 2.5, animate a still image.
-
Veo 3.1
🎬Google Veo 3.1, text to video with generated audio.
-
Veo 3.1 Fast (image to video)
🎬Animate a still image with Veo 3.1 Fast.
-
Sora 2
🎬2OpenAI's Sora 2, text to video with audio.
-
Hailuo 2.3 Fast
🎬MiniMax Hailuo 2.3, image to video, speed-optimised.
-
Vidu Q2
🎬Vidu Q2, text to video.
-
Vidu Q2 Pro (image to video)
🎬Vidu Q2 Pro, animate a still image.
-
Seedance 1.0
🎬8Reference for ByteDance Seedance 1.0 video models
-
Seedance Gallery
🎞2Unedited sample output from ByteDance Seedance 1.0
-
InfiniteTalk
🎬Drive a portrait from an audio track — lip sync and head...
-
Video Watermark Remover
🎬Remove watermarks from a video you own the rights to.