Viggle-Animate

Put the person from a still into a driving video. No pose estimation, no segmentation, no masks — the only preprocessing is repainting the clip's first frame. 4 sampling steps. Takes 4–10 s of driving video; anything longer is cut to 10.1 s.

Model card and weights · viggle.ai

driving video — motion, framing and background are kept

character — who to put in it

…or frame 0, already painted (skips gpt-image-2)

seed

_{Sign in to render — 5 a day per account. Rendering repaints your first frame with an image model this Space pays for.}

step 1: repainted first frame

step 2: render

examples — click one for its driving clip, its painted first frame and the render

driving video — motion, framing and background are kept	…or frame 0, already painted (skips gpt-image-2)	step 2: render

What it produces

Every example above, rendered at 4 steps with seed 42. Each is a single paint and a single render; only the last three swap in a person.

a corgi

0:00 / 0:00

a giant panda

0:00 / 0:00

a penguin

0:00 / 0:00

an airliner — wings for arms, landing gear for legs

0:00 / 0:00

a walking robot

0:00 / 0:00

claymation

0:00 / 0:00

two characters at once — cel-shaded cat and corgi

0:00 / 0:00

the same frame, painted photoreal over the anime set

0:00 / 0:00

a wide arena shot, both fighters replaced

0:00 / 0:00

the same shot, gold and chrome robots

0:00 / 0:00

a light-up toy, held in both hands

0:00 / 0:00

a bow headwrap and floral leggings, driven by a bearded man

0:00 / 0:00

a flat 2D anime character

0:00 / 0:00

_{Model card and weights · viggle.ai}