Scoody

Video generation

Choose a model for a new shot. Start with a prompt, a still image or a video reference. If composition matters, check whether the model accepts keyframes.

Supported inputs and settings can vary by model mode.

FLUX 3 Video

Black Forest Labs

Generates video from a text prompt, animates a source image, and transforms an existing clip.

  • First frame
  • First and last frames
  • Multiple keyframes
  • 720p / 1080p
Model documentation

Generates video from a text prompt, animates a source image, transforms an existing clip, edits the contents of a scene, and extends a shot.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • 360p / 720p / 1080p / 4K
  • 3–10 s
Model documentation

Generates video from a text prompt, animates a source image, transforms an existing clip, edits the contents of a scene, and extends a shot.

  • First frame
  • Image references
  • 480p / 720p
  • 1–15 s
Model documentation

HappyHorse-1.0

Alibaba

Generates video from a text prompt, animates a source image, transforms an existing clip, and edits the contents of a scene.

  • First frame
  • Image references
  • 720p / 1080p
  • 3–15 s
Model documentation

Generates video from a text prompt, animates a source image, transforms an existing clip, and uses audio as an input for video.

  • First frame
  • Image references
  • Video references
  • Audio references
  • 480p / 768p / 1080p / 2k
Model documentation

Generates video from a text prompt, animates a source image, and transforms an existing clip.

  • First frame
  • First and last frames
  • Image references
  • Video references
Model documentation

Generates video from a text prompt, animates a source image, and transforms an existing clip.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • 4k
  • 3–15 s
Model documentation

Generates video from a text prompt, animates a source image, transforms an existing clip, and edits the contents of a scene.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • 1080p
  • 3–15 s
Model documentation

Generates video from a text prompt, animates a source image, transforms an existing clip, and edits the contents of a scene.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • 720p
  • 3–15 s
Model documentation

Generates video from a text prompt, animates a source image, and transforms an existing clip.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • 3–15 s
Model documentation

Generates video from a text prompt, animates a source image, and transforms an existing clip.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • 3–15 s
Model documentation

Kling VIDEO 4.0

Kling AI

Generates video from a text prompt, animates a source image, transforms an existing clip, and edits the contents of a scene.

  • First frame
  • First and last frames
  • Multiple keyframes
  • Image references
  • Video references
  • 720p / 1080p
  • 3–30 s
Model documentation

Generates video from a text prompt, animates a source image, transforms an existing clip, and edits the contents of a scene.

  • First frame
  • Image references
  • Video references
  • 3–20 s
Model documentation

Generates video from a text prompt, animates a source image, transforms an existing clip, and edits the contents of a scene.

  • First frame
  • First and last frames
  • Image references
  • Video references
Model documentation

Generates video from a text prompt, animates a source image, transforms an existing clip, and edits the contents of a scene.

  • First frame
  • First and last frames
  • Image references
  • Video references
Model documentation

LTX-2

Lightricks

Generates video from a text prompt and animates a source image.

  • First frame
  • Multiple keyframes
  • 1–20 s
Model documentation

LTX-2.3

Lightricks

Generates video from a text prompt, animates a source image, transforms an existing clip, uses audio as an input for video, and extends a shot.

  • First frame
  • First and last frames
  • Multiple keyframes
  • 1–20 s
Model documentation

LTX-2.3 Fast

Lightricks

Generates video from a text prompt, animates a source image, and uses audio as an input for video.

  • First frame
  • First and last frames
  • Multiple keyframes
  • 1–20 s
Model documentation

LTX-2.5 Fast

Lightricks

Generates video from a text prompt, animates a source image, and uses audio as an input for video.

  • First frame
  • First and last frames
  • Image references
Model documentation

LTX-2.5 Pro

Lightricks

Generates video from a text prompt, animates a source image, uses audio as an input for video, edits the contents of a scene, and extends a shot.

  • First frame
  • First and last frames
  • Image references
Model documentation

MiniMax H3

MiniMax

Generates video from a text prompt, animates a source image, transforms an existing clip, uses audio as an input for video, and edits the contents of a scene.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 768p / 1440p
  • 4–15 s
Model documentation

MiniMax H3 Fast

MiniMax

Generates video from a text prompt, animates a source image, transforms an existing clip, and uses audio as an input for video.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 768p
  • 4–15 s
Model documentation

Generates video from a text prompt, animates a source image, transforms an existing clip, and uses audio as an input for video.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 768p
  • 4–15 s
Model documentation

MiniMax H3 Lite

MiniMax

Generates video from a text prompt, animates a source image, transforms an existing clip, and uses audio as an input for video.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 768p
  • 4–15 s
Model documentation

MiniMax H3 Max

MiniMax

Generates video from a text prompt, animates a source image, transforms an existing clip, and uses audio as an input for video.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 768p
  • 5–15 s
Model documentation

P-Video

Pruna AI

Generates video from a text prompt, animates a source image, and uses audio as an input for video.

  • First frame
  • 720p / 1080p
  • 1–10 s
Model documentation

P-Video-2

Pruna AI

Generates video from a text prompt, animates a source image, and uses audio as an input for video.

  • First frame
  • First and last frames
  • 720p / 1080p
  • 1–20 s
Model documentation

P-Video-2-Pro

Pruna AI

Generates video from a text prompt, animates a source image, transforms an existing clip, and uses audio as an input for video.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 768p
  • 5–15 s
Model documentation

PixVerse V3.5

PixVerse

Generates video from a text prompt and animates a source image.

  • First frame
  • First and last frames
  • 360p / 540p / 720p / 1080p
Model documentation

PixVerse V4

PixVerse

Generates video from a text prompt and animates a source image.

  • First frame
  • First and last frames
  • 360p / 540p / 720p / 1080p
Model documentation

PixVerse V4.5

PixVerse

Generates video from a text prompt and animates a source image.

  • First frame
  • First and last frames
  • 360p / 540p / 720p / 1080p
Model documentation

PixVerse V5

PixVerse

Generates video from a text prompt and animates a source image.

  • First frame
  • First and last frames
  • 360p / 540p / 720p / 1080p
Model documentation

PixVerse V5.5

PixVerse

Generates video from a text prompt and animates a source image.

  • First frame
  • First and last frames
  • 360p / 540p / 720p / 1080p
Model documentation

PixVerse V5.6

PixVerse

Generates video from a text prompt and animates a source image.

  • First frame
  • First and last frames
  • 360p / 540p / 720p / 1080p
Model documentation

PixVerse V6

PixVerse

Generates video from a text prompt, animates a source image, transforms an existing clip, and edits the contents of a scene.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • 360p / 540p / 720p / 1080p
  • 1–15 s
Model documentation

Ray3.2

Luma

Generates video from a text prompt, animates a source image, transforms an existing clip, and edits the contents of a scene.

  • First frame
  • First and last frames
  • Multiple keyframes
  • 360p / 540p / 720p / 1080p
Model documentation

Seedance 2.0

ByteDance

Generates video from a text prompt, animates a source image, transforms an existing clip, uses audio as an input for video, edits the contents of a scene, and extends a shot.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 720p / 1080p / 4k
  • 4–15 s
Model documentation

Seedance 2.0 Fast

ByteDance

Generates video from a text prompt, animates a source image, transforms an existing clip, uses audio as an input for video, edits the contents of a scene, and extends a shot.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 720p
  • 4–15 s
Model documentation

Seedance 2.0 Mini

ByteDance

Generates video from a text prompt, animates a source image, transforms an existing clip, and uses audio as an input for video.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 720p
  • 4–15 s
Model documentation

Seedance 2.5

ByteDance

Generates video from a text prompt, animates a source image, transforms an existing clip, uses audio as an input for video, and edits the contents of a scene.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 720p / 1080p
Model documentation

SkyReels V4

Skywork

Generates video from a text prompt, animates a source image, transforms an existing clip, uses audio as an input for video, edits the contents of a scene, and extends a shot.

  • First frame
  • First and last frames
  • Multiple keyframes
  • 480p / 720p / 1080p
  • 3–15 s
Model documentation

Veo 3.1

Google

Generates video from a text prompt, animates a source image, transforms an existing clip, edits the contents of a scene, and extends a shot.

  • First frame
  • First and last frames
  • Image references
  • 720p / 1080p / 4K
Model documentation

Veo 3.1 Fast

Google

Generates video from a text prompt, animates a source image, transforms an existing clip, edits the contents of a scene, and extends a shot.

  • First frame
  • First and last frames
  • Image references
  • 720p / 1080p / 4K
Model documentation

Vidu Q1

Vidu

Generates video from a text prompt and animates a source image.

  • First frame
  • First and last frames
Model documentation

Vidu Q3

Vidu

Generates video from a text prompt and animates a source image.

  • First frame
  • First and last frames
  • 360p / 540p / 720p / 1080p
  • 1–16 s
Model documentation

Wan2.5-Preview

Alibaba

Generates video from a text prompt, animates a source image, and uses audio as an input for video.

  • First frame
  • 480p / 720p / 1080p
Model documentation

Wan2.6

Alibaba

Generates video from a text prompt, animates a source image, transforms an existing clip, and uses audio as an input for video.

  • First frame
  • Video references
  • 720p / 1080p
Model documentation

Wan2.7

Alibaba

Generates video from a text prompt, animates a source image, transforms an existing clip, and uses audio as an input for video.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • 720p / 1080p
  • 2–15 s
Model documentation

Wan3.0

Alibaba

Generates video from a text prompt, animates a source image, transforms an existing clip, uses audio as an input for video, edits the contents of a scene, and extends a shot.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 720p / 1080p
Model documentation

Wan3.0 Prime

Alibaba

Generates video from a text prompt, animates a source image, transforms an existing clip, uses audio as an input for video, edits the contents of a scene, and extends a shot.

  • First frame
  • First and last frames
  • Image references
  • Video references
  • Audio references
  • 480p / 720p / 1080p
Model documentation