WaveSpeedAI Blog

Latest news on AI image and video generation models

Kling O1 Series Officially Launches on WaveSpeedAI — A New Standard for Unified Image & Video Creation

The Kling O1 Series officially launches on WaveSpeedAI, introducing next-generation multimodal image and video creation with Kling Image O1 and Kling Video O1. Create, edit, and transform visuals with unmatched consistency, control, and creative power—directly in your browser.

2025-05-13 5 min read

Kling O1 Video Model Is Coming — A Unified Leap in Visual Creation

Built for creators, filmmakers, and designers, Kling O1 represents a major leap forward in intelligence, consistency, and editability across video workflows. This next-generation multimodal video engine brings a smoother, more intuitive, and highly controllable workflow to anyone working with video.

2025-05-11 3 min read

Kling Omni Video O1 Video Edit — Natural-Language Video Editing Arrives on WaveSpeedAI

WaveSpeedAI is excited to announce the release of Kling Video Edit, powered by Kuaishou’s groundbreaking multimodal video model Kling Omni Video O1. With Video Edit, you can modify videos using simple natural language instructions.

2025-05-10 3 min read

Kling Reference-to-Video: Generate New Videos from Your Subjects — Now on WaveSpeedAI

Kling Reference-to-Video allows you to generate entirely new video content based on subject reference images or videos, while maintaining consistent appearance, identity, and scene logic across all frames.

2025-05-08 3 min read

LTX-2 Surpasses Sora 2, Defining the 20-Second AI Video Era

While we were still in awe of Sora 2 extending AI video to 12 seconds, LTX-2 has once again shattered this boundary — directly pushing video generation to 20 seconds.

2025-05-07 4 min read

LongCat Avatar Is Live on WaveSpeedAI: Ultra-Realistic Lip-Synced Avatar Videos Up to 2 Minutes

LongCat Avatar transforms a single photo and an audio track into super-realistic, lip-synchronized talking or singing avatar videos, with natural dynamics and consistent identity—for up to 2 minutes per generation.

2025-05-06 4 min read

Nano Banana 2 Leak: A Glimpse Into Google's Next-Gen AI Image Model

A few months ago, Nano Banana became known for creating hyper-realistic AI figures with collectible-style aesthetics.

2025-05-04 6 min read

Nano Banana Pro vs Seedream 4: Which Delivers Better Realism and Visual Consistency?

Compare Google’s Nano Banana Pro (Gemini 3.0 Pro Image) and Seedream 4 in realism, speed, resolution, and consistency to find the best AI image generator.

2025-05-03 5 min read

Nano Banana Pro vs Wan 2.5 Image Edit: Editing Refinement Meets Full Generation Power

Discover how Google's Nano Banana Pro (Gemini 3.0 Pro Image) and Wan 2.5 Image Edit unite generation and precision editing to streamline creative workflows.

2025-05-01 5 min read

OmniHuman-1.5:Toward Virtual Humans with “Soul”

Have you ever watched videos featuring smoothly animated digital humans, but felt they lacked genuine emotion? To overcome this limitation, we introduce OmniHuman-1.5, developed by ByteDance—a groundbreaking framework designed to generate character animations that transcend superficial mimicry. It not only brings virtual avatars to life but also endows them with the ability to express emotions.

2025-04-30 3 min read

Quick Start of Seedream V4

Seedream 4.0 supports three types of input: text, a single image, and multiple images.

2025-04-28 6 min read

Qwen-Image-Edit on WaveSpeedAI: Clean Up Photos & Perfect Visuals in Seconds

Are you tired of struggling with complex image editing software, spending hours and energy just to make a simple modification? Do you wish for an image editing tool that can solve your image editing challenges? We’re excited to announce that Qwen-Image-Edit is now available on WaveSpeed AI. Built on the flagship 20B-parameter Qwen-Image model, this tool merges cutting-edge semantic understanding with pixel-perfect appearance control, empowering users to create, modify, and refine images with unprecedented precision.

2025-04-27 5 min read