Gradio

T2V — Text-to-Video

Prompt

Resolution

Duration (s)

0.5 5.1

Output

⌚ ZeroGPU reservation: ~110s

Send to:

I2V — Image-to-Video

Source image

Motion prompt

Resolution

Duration (s)

0.5 5.1

Output

⌚ ZeroGPU reservation: ~120s

Send to:

TI2V — Text+Image to Video (Wan 2.2-5B, via upstream wan package)

Optional image (omit for T2V-only)

Prompt

TI2V-5B is locked to 1280×704 (landscape) or 704×1280 (portrait), 121 frames @ 24 fps.

Orientation

Landscape (1280x704) Portrait (704x1280)

Output

⌚ ZeroGPU reservation: ~60s

Send to:

FLF2V — First-Last-Frame to Video (Wan 2.1 only)

Start frame

End frame

Transition prompt

Output

⌚ ZeroGPU reservation: ~150s

Send to:

V2V — Video-to-Video Restyle

Source video

Restyle prompt

Strength

0.1 1

Output

⌚ ZeroGPU reservation: ~90s

Send to:

VACE — Versatile Animation Control & Editing (Wan 2.1 only)

S2V — Speech to Video (Wan 2.2, via upstream wan package)

Reference character

Driving audio

Optional pose video

Scene / style prompt

Resolution

Duration: auto (driven by audio length)

Output

⌚ ZeroGPU reservation: ~240s (audio-driven)

Send to:

Animate — Character Animation & Replacement (Wan 2.2)

Character reference

Driving / template video

Mode

Character Swap Pose Retarget Replacement (bg+mask)

Resolution

Low 480p Medium 720p

Duration (s)

1 20

Optional prompt

Output

⌚ ZeroGPU reservation: ~300s (xlarge tier)

Send to:

pose

face

bg

mask

Gallery — session history

Generated videos will appear here.

Selected

Params will appear here.

Settings — Model Manager

Model load status appears here.