WaveSpeedAI Blog

Latest news on AI image and video generation models

Introducing Kuaishou Kling Video O3 Pro Text-to-Video on WaveSpeedAI

Kling Omni Video O3 is Kuaishou's advanced unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Text-to-Video mode generates cinem

2026-02-20 7 min read

Introducing Kuaishou Kling Video O3 Pro Video Edit on WaveSpeedAI

Kling Omni Video O3 Video-Edit enables conversational video editing through natural language commands. Remove objects, change backgrounds, modify styles, adjust

2026-02-20 1 min read

Introducing Kuaishou Kling Video O3 Std Image-to-Video on WaveSpeedAI

Kling Omni Video O3 (Standard) Image-to-Video transforms static images into dynamic cinematic videos using MVL (Multi-modal Visual Language) technology. Maintai

2026-02-20 6 min read

Introducing Kuaishou Kling Video O3 Std Reference To Video on WaveSpeedAI

Kling Omni Video O3 (Standard) Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subjec

2026-02-20 7 min read

Introducing Kuaishou Kling Video O3 Std Text-to-Video on WaveSpeedAI

Kling Omni Video O3 (Standard) is Kuaishou's advanced unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Text-to-Video mode gene

2026-02-20 6 min read

Introducing Kuaishou Kling Video O3 Std Video Edit on WaveSpeedAI

Kling Omni Video O3 Video-Edit (Standard) enables natural-language video edits: remove or replace objects, swap backgrounds, restyle scenes, change weather/ligh

2026-02-20 7 min read

Introducing Microsoft Vibevoice on WaveSpeedAI

Microsoft VibeVoice text-to-speech model generates long-form speech from text with multi-speaker dialogue support. Choose from 9 voice presets across English, C

2026-02-20 1 min read

Introducing MiniMax Music 2.5 on WaveSpeedAI

MiniMax Music 2.5 is a full-dimensional breakthrough in AI music generation with high-fidelity audio, humanized vocals, and precise creative control. Ready-to-u

2026-02-20 6 min read

Introducing Sourceful Riverflow 2.0 Pro Text-to-Image on WaveSpeedAI

Sourceful Riverflow 2.0 Pro is an agentic image model optimized for robust, high-precision text-to-image generations. Ready-to-use REST inference API, best perf

2026-02-20 1 min read

Introducing Sourceful Riverflow 2.0 Pro Edit on WaveSpeedAI

Sourceful Riverflow 2.0 Pro Edit is an agentic image model optimized for robust, high-precision image editing and transformation. Ready-to-use REST inference AP

2026-02-20 1 min read

Introducing Vidu Q2 Pro Image-to-Video Fast on WaveSpeedAI

Vidu Q2 Pro Fast Image to Video generates high-quality videos from a single image with faster generation speed. Ready-to-use REST inference API, best performanc

2026-02-20 6 min read

Introducing Vidu Q2 Pro Start End To Video Fast on WaveSpeedAI

Vidu Q2 Pro Fast Start-End to Video generates smooth video transitions between start and end images with faster generation speed. Ready-to-use REST inference AP

2026-02-20 1 min read