someaistuff.

Explore models.

2,849 models1,625 with prices34 metricsUpdated Oct 22, 2026 ↗
Ranked results

149 models · newest firstPage 1 / 7

More filters
minimaxListed 14 days ago

H3 Max Relight

Relight any video with H3 Max from a lighting sphere image, while preserving the source subjects, motion, camera and audio.

No reported score
No reported score
Listed from $0.05/ second · USDfal480p · generated output second
+Compare
minimaxListed 20 days ago

H3 Max Turbo Extend Video

Extend an existing video with H3 Max Turbo: add 1 to 15 seconds of prompt-guided footage, with optional audio references and output resolutions from 480p to 2K.

No reported score
No reported score
Listed from $0.025/ second · USDfal480p · newly generated continuation second
+Compare
fal-aiListed Sep 14

ID-V2V

Restyle a video’s scene, lighting, and visual style from edited keyframes while preserving the source subjects’ identity, expressions, gaze, and motion. Developed by Eyeline Labs and Netflix researchers.

No reported score
No reported score
Listed from $0.20/ second · USDfal
+Compare
fal-aiListed Sep 14

ID-V2V Relight

Change a video’s lighting using a relit reference frame while preserving the scene, subjects, and original performance. ID-V2V Relight propagates the new illumination across the video.

No reported score
No reported score
Listed from $0.20/ second · USDfal
+Compare
briaListed Aug 27

Video

Remove background from videos filmed using chromakey, with automatic green spill suppression for clean, professional edges.

No reported score
No reported score
Listed from $0.05/ second · USDfal
+Compare
mirage-apiListed Aug 10

Avatar X

The Avatar X API offers access to Mirage's most advanced generation model yet, delivering industry-leading identity preservation and expressivity in AI video

No reported score
No reported score
Listed from $0.30/ second · USDfal
+Compare
mirage-apiListed Aug 10

Mirage Avatar X

The Avatar X API offers access to Mirage's most advanced generation model yet, delivering industry-leading identity preservation and expressivity in AI video

No reported score
No reported score
Listed from $0.30/ second · USDfal
+Compare
alibabaListed Aug 3

Wan 3.0

Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

No reported score
No reported score
Listed from $0.05/ second · USDfal480p · output second
✓Compare
alibabaListed Aug 3

Wan 3.0

Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

No reported score
No reported score
Listed from $0.05/ second · USDfal480p · output second
+Compare
decartListed Jul 15

Lucy 2.5

Real-time, prompt-driven video editing over WebRTC. Restyle, swap backgrounds, and add or replace objects live on a webcam or streamed feed at interactive latency.

No reported score
No reported score
Listed from $0.02/ second · USDfal
+Compare
FastVideoListed Jun 27

FastWan-QAD-FP8-1.3B

A fast, compact 480p text-to-video model — 5-second clips (landscape or portrait) from a text prompt. A 3-step, FP8 quantization-aware distillation of Wan2.1-T2V-1.3B by FastVideo (Hao AI Lab).

1.3BNo reported score
No reported score
Listed from $0.0025/ second · USDDeepInfraOutput video second; base configuration
+Compare
alibabaListed Jun 21

Happy Horse 1.1 Reference to Video

Happy Horse 1.1 is Alibaba's #1-ranked video model. This reference-to-video endpoint turns up to 9 reference images into 1080p video with synchronized native audio and multilingual lip-sync for consistent…

No reported score
No reported score
Listed from $0.14/ second · USDfal720p · output second
+Compare
alibabaListed Jun 21

Happy Horse 1.1 Image to Video

Happy Horse 1.1 is Alibaba's #1-ranked video model. This image-to-video endpoint animates a still image into 1080p video with synchronized native audio and multilingual lip-sync

No reported score
No reported score
Listed from $0.14/ second · USDfal720p · output second
+Compare
alibabaListed Jun 21

Happy Horse 1.1 Text to Video

Happy Horse 1.1 is Alibaba's #1-ranked video model. This text-to-video endpoint generates 1080p video with synchronized native audio and multilingual lip-sync from a text prompt alone.

No reported score
No reported score
Listed from $0.14/ second · USDfal720p · output second
+Compare
briaListed Jun 9

Bria's VRMBG 3.0 Realtime

Remove video backgrounds in real time with Bria’s VRMBG 3.0 model. Built for live streaming, real-time video apps, content creation, and low-latency workflows that need fast, accurate background removal.

No reported score
No reported score
Listed from $0.0042/ second · USDfal
+Compare
briaListed Jun 8

Bria's VRMBG 3.0

Remove backgrounds from any video with Bria's VRMBG 3.0. Fast, accurate background removal across talking heads, podcasts, product videos, commercials, and cinematic footage.

No reported score
No reported score
Listed from $0.05/ second · USDfal
+Compare
PixverseListed May 29

Pixverse-6-I2V

PixVerse V6 redefines AI video by shifting from isolated generation to a unified, model-driven workflow. Key upgrades include 15-second durations at 1080p resolution and a multi-shot engine. This transition…

No reported score
No reported score
Listed from $0.025/ second · USDDeepInfra360p · audio off · output second
+Compare
fal-aiListed May 5

Ffmpeg Api Images to Video

A fal.ai endpoint that stitches an ordered list of images into an MP4 video by holding each image for a specified number of frames at a configurable frame rate

No reported score
No reported score
Listed from $0.00/ compute second · USDfal
+Compare
PrunaAIListed Apr 30

p-video-avatar

Pruna's talking head video generation model. Provide a portrait image and either a speech script or an audio file, and the model generates a realistic video of the person speaking. Supports multiple voices,…

No reported score
No reported score
Listed from $0.0225/ second · USDDeepInfraOutput video second; base configuration
+Compare