AI models for image, video, audio and 3D

Browse model families and jump into their details.

Creator
Category

117 models shown

Gemini ImageGoogle DeepMind

Google's newest Nano Banana renders sharper text and holds faces steadier. Fuse up to 10 references and retouch a photo by saying what to change.

Image
View
GPT ImageOpenAI

Filmic light, correctly spelled type and surgical regional edits, from a first sentence to a finished hero frame

Image
View
Kling 3.0 VideoKuaishou

Cinematic shots with real physical weight, steady camera moves and sound that arrives with the picture, from a prompt or two keyframes

Video
View
Seedance 2ByteDance (Seed team)

Cinematic single takes where picture, speech and foley are born together, held unbroken for up to 30 seconds

Video
View
MiniMax H3MiniMax

Cast a face, borrow a camera move, cue the beat: one clean-lit cinematic shot of up to 15 seconds with identity that holds

Video
View
Cobalt-blue FORM perfume bottle with a silver spherical cap and red ribbon, generated with Seedream 5.0 Lite.
SeedreamByteDance (Seed team)

Ad-ready frames where the headline is designed into the layout, in about 14 languages, with up to 10 references fused into one image

Image
View

New models

MiniMax H3 RecastMiniMax

Drop new faces into a finished clip while the original timing, camera moves, cuts and soundtrack play on untouched

Video
View
A man in a cream suit on a red deckchair at the bottom of a drained blue swimming pool, reading a newspaper headlined NOTHING HAPPENED TODAY
FLUX.3 ImageBlack Forest Labs

Posters, packaging and hero art with type that reads like real print, plus edits that change one element and leave the rest alone

Image
View
MiniMax Music 3MiniMax

End-to-end full-length song generation with expressive vocal delivery, multi-verse progressions, and layered stereo arrangements

Audio
View
Kling O3 EditKuaishou Technology

Transform live footage and transfer kinetic camera motion with tag-based identity guidance

Video
View
Lyria 3.5Google DeepMind

Full-length studio musical arrangements and expressive vocal performances guided by structural timestamps and visual inspiration

Audio
View
Kling O3Kuaishou (Kling AI)

Characters and products that hold their look through grounded, commercial-grade motion, with an optional end frame and synced sound

Video
View

More models

FLUX.2

Black Forest Labs

Grok Imagine

xAI

ESRGAN Upscaler

Tencent ARC

Recraft V4

Recraft AI

Gemini Omni Video

Google DeepMind / Google

Meshy

Meshy

Topaz Image Upscale

Topaz Labs

Grok Imagine Image

xAI

Muse Image

Meta Superintelligence Labs

Background Remover

BRIA AI

Krea

Krea AI

Veo

Google DeepMind

FLUX.1 Kontext

Black Forest Labs

Rodin

Deemos Technology (Hyper3D)

Wan 3.0 Video

Alibaba (Tongyi Lab)

Sora 2

OpenAI

FLUX.3 Video

Black Forest Labs

Kling 2.X Video Tool

Kuaishou Technology

Hunyuan3D V3

Tencent

Tripo 3D

Tripo AI (VAST)

Z-Image

Alibaba Tongyi-MAI

Ideogram 4.5

Ideogram

Qwen Image 2

Alibaba (Qwen team)

Kling 3.0 Motion

Kuaishou Technology