someaistuff.

Explore models.

2,847 models1,620 with prices34 metricsUpdated Oct 22, 2026 ↗
Ranked results

621 models · newest firstPage 26 / 26

More filters
fal-aiListed Oct 22

Hunyuan Video

Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. This endpoint generates videos from text descriptions.

No reported score
No reported score
Price not listed
+Compare
fal-aiListed Oct 17

CogVideoX-5B

Generate videos from images and prompts using CogVideoX-5B

No reported score
No reported score
Price not listed
+Compare
fal-aiListed Oct 17

CogVideoX-5B

Generate videos from videos and prompts using CogVideoX-5B

No reported score
No reported score
Price not listed
+Compare
fal-aiListed Oct 4

LTX Video (preview)

Generate videos from prompts using LTX Video 0.9.1

No reported score
No reported score
Price not listed
+Compare
fal-aiListed Apr 11

MuseTalk

MuseTalk is a real-time high quality audio-driven lip-syncing model. Use MuseTalk to animate a face with your own audio.

No reported score
No reported score
Listed from $0.00/ compute second · USDfal
+Compare
fal-aiListed Apr 11

Sad Talker

Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

No reported score
No reported score
Listed from $0.00/ compute second · USDfal
+Compare