WaveSpeedAI Blog

Latest news on AI image and video generation models

Introducing Bria Fibo Video Upscaler on WaveSpeedAI

Bria Video Upscaler increases video resolution up to 8K with 2x or 4x upscaling. Ready-to-use REST inference API, best performance, no cold starts, affordable p

2026-02-20 6 min read

Introducing ByteDance Dreamactor V2 on WaveSpeedAI

ByteDance DreamActor V2 transfers motion from a driving video to characters in an image. Great performance for non-human and multiple characters. Ready-to-use R

2026-02-20 6 min read

Introducing Google Gemini 2.5 Flash Text To Speech on WaveSpeedAI

Google Gemini 2.5 Flash Text-to-Speech delivers fast, natural multi-speaker voice synthesis with 30+ voices across 24 languages at lower cost. Perfect for dialo

2026-02-20 1 min read

Introducing Google Gemini 2.5 Pro Text To Speech on WaveSpeedAI

Google Gemini 2.5 Pro Text-to-Speech delivers natural multi-speaker voice synthesis with 30+ voices across 24 languages. Perfect for dialogues, conversations, a

2026-02-20 6 min read

Introducing Half Moon AI Image Face Swap Multi on WaveSpeedAI

Half-Moon AI Image Multi-Face Swap swaps multiple faces in a photo based on gender matching. Ready-to-use REST inference API, best performance, no coldstarts, a

2026-02-20 1 min read

Introducing Half Moon AI Image Face Swap on WaveSpeedAI

Half-Moon AI Image Face Swap takes one person's face and realistically blends it onto another's in a photo. Ready-to-use REST inference API, best performance, n

2026-02-20 6 min read

Introducing Half Moon AI Video Face Swap Multi on WaveSpeedAI

Half-Moon AI Video Multi-Face Swap swaps multiple faces in a video based on gender matching. Ready-to-use REST inference API, best performance, no coldstarts, a

2026-02-20 1 min read

Introducing Half Moon AI Video Face Swap on WaveSpeedAI

Half-Moon AI Video Face Swap takes one person's face and realistically blends it onto another's in a video. Ready-to-use REST inference API, best performance, n

2026-02-20 5 min read

Introducing Ideogram V2a on WaveSpeedAI

Ideogram v2a is an image-generation model with state-of-the-art inpainting, precise prompt comprehension, and accurate text rendering. Ready-to-use REST inferen

2026-02-20 1 min read

Introducing Inworld 1.5 Max Text To Speech on WaveSpeedAI

Inworld 1.5 Max delivers premium text-to-speech synthesis with 56+ multilingual voices, adjustable speaking rate, and high-fidelity natural-sounding audio outpu

2026-02-20 7 min read

Introducing Inworld 1.5 Mini Text To Speech on WaveSpeedAI

Inworld 1.5 Mini delivers high-quality text-to-speech synthesis with 56+ multilingual voices, adjustable speaking rate, and natural-sounding audio output. Ready

2026-02-20 6 min read

Introducing Kuaishou Kling Image O3 Edit on WaveSpeedAI

Kling O3 Edit is an AI image editing model with 4K resolution and multi-image reference support, enabling high-quality transformations with multiple reference i

2026-02-20 7 min read