AIMarch 27, 2025
A group of 18-year-old college students created an AI 3D drawing tool in 36 hours
Turn your roughest sketches into stunning 3D worlds by vibe drawing
GENERATOR
OPENAIMarch 26, 2025
The native image function of GPT-4o is officially launched
Introducing 4o Image Generation
AIMarch 25, 2025
Reve - The AI art tool that outperforms MidJourney and Flux
Halfmoon is Reve Image — and it’s the best image model in the world
ADOBEMarch 18, 2025
Sketch2Sound: Controllable audio generation based on time-varying signals and sound imitation
Controllable Audio Generation via Time-Varying Signals and Sonic Imitations
METAMarch 15, 2025
Meta's latest released video generation model VideoJAM
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
AIMarch 11, 2025
Sesame CSM - An incredibly powerful speech model, soon to be open-sourced~
A Conversational Speech Generation Model
PIKAMarch 3, 2025
Pika 2.2 Latest Video Model + Pikaswaps - Replace Elements in Videos + Pikadditions - Add Elements to Videos
Pika 2.2 is HERE, with 10-second generations, 1080p resolution, and Pikaframes—key frame transitions anywhere from 1-10 seconds.
AIFebruary 15, 2025
Sony's MMAudio model — generating sound effects for videos
MMAudio generates synchronized audio given video and/or text inputs.
BYTEDANCEFebruary 7, 2025
ByteDance's OmniHuman-1: Generating realistic human videos from a single human image
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
AIFebruary 5, 2025
Alibaba's EMO2: Audio-Driven Talking Head Generation
EMO2: End-Effector Guided Audio-Driven Avatar Video Generation
POPULAR
LLM
See MoreGENERATOR
Explore generative AI tools for images, videos, music, and creative content.
AIMarch 27, 2025
A group of 18-year-old college students created an AI 3D drawing tool in 36 hours
Turn your roughest sketches into stunning 3D worlds by vibe drawing
OPENAIMarch 26, 2025
The native image function of GPT-4o is officially launched
Introducing 4o Image Generation
AIMarch 25, 2025
Reve - The AI art tool that outperforms MidJourney and Flux
Halfmoon is Reve Image — and it’s the best image model in the world
ADOBEMarch 18, 2025
Sketch2Sound: Controllable audio generation based on time-varying signals and sound imitation
Controllable Audio Generation via Time-Varying Signals and Sonic Imitations
METAMarch 15, 2025
Meta's latest released video generation model VideoJAM
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
AIMarch 11, 2025
Sesame CSM - An incredibly powerful speech model, soon to be open-sourced~
A Conversational Speech Generation Model
PIKAMarch 3, 2025
Pika 2.2 Latest Video Model + Pikaswaps - Replace Elements in Videos + Pikadditions - Add Elements to Videos
Pika 2.2 is HERE, with 10-second generations, 1080p resolution, and Pikaframes—key frame transitions anywhere from 1-10 seconds.
AIFebruary 15, 2025
Sony's MMAudio model — generating sound effects for videos
MMAudio generates synchronized audio given video and/or text inputs.
BYTEDANCEFebruary 7, 2025
ByteDance's OmniHuman-1: Generating realistic human videos from a single human image
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
AIFebruary 5, 2025
Alibaba's EMO2: Audio-Driven Talking Head Generation
EMO2: End-Effector Guided Audio-Driven Avatar Video Generation
POPULAR
AI TOOLS
LLM
See MoreTrial of Google's video generation model VOE2
GOOGLEMarch 23, 2025
AI-Researcher: LLM-driven全自动 scientific research assistant
AIMarch 30, 2025