WaveSpeedAI Blog

Latest news on AI image and video generation models

Sora 2: See More. Do More. Have More Fun!

Sora 1 illuminated the possibilities beyond LLMs; Sora 2 responds with a real leap—more accurate motion, better light and texture, and synchronized audio, turning cinematic quality into a daily experience rather than a rare achievement.

2025-01-25 5 min read

OpenAI's Sora 2 Model Now Available on the WaveSpeedAI Platform

WaveSpeedAI, the global multimodal inference acceleration platform, today announced the availability of Sora 2 — OpenAI’s next-generation video-and-audio generation model — via the WaveSpeedAI API.

2025-01-24 5 min read

Step1X-Edit: Setting a New Standard for Open-Source Image Editing

In the field of image editing, users are increasingly demanding high-quality and user-friendly solutions. While closed-source multimodal models like GPT-4o and Gemini 2 Flash deliver strong image editing capabilities, open-source options have often lagged behind in performance.

2025-01-22 5 min read

Unlock the Future of AI Video: PixVerse v4.5 Series is Here

We’re excited to announce the PixVerse v4.5 series is now live on WaveSpeed AI. Whether you’re transforming text prompts or images into vivid motion or animating your favorite images, this new suite of models empowers you to produce stunning videos with speed, control, and unprecedented quality.

2025-01-21 5 min read

VEO 2 Now Live on WaveSpeedAl: Cinematic Video Generation

We are excited to introduce two of Google's highest quality models, veo2-i2v and veo2-t2v — now available on WaveSpeedAI!

2025-01-19 5 min read

Veo 3 Now Live on WaveSpeedAl: Audiovisual AI generation

2025-01-18 5 min read

Video Upscaler Now Live on WaveSpeedAl: The Best Model for Improving Video Resolution

We are excited to introduce the video-upscaler, a powerful tool designed to enhance the resolution and quality of videos, now live on WaveSpeedAI!

2025-01-16 5 min read

Vidu 2.0 Now Live on WaveSpeedAI: A New Generation of Controllable Video Generation Models

We’re excited to introduce the full suite of Vidu 2.0 models—now available on WaveSpeedAI. Designed by Shengshu Technology, these models bring a new level of controllability, visual fidelity, and temporal consistency to open-source video generation.

2025-01-15 5 min read

WAN-2.1 FLF2V Now Live on WaveSpeedAI: From Keyframes to Cinematic Motion

We’re excited to bring another powerful addition to the WAN-2.1 lineup: WAN-2.1 FLF2V (First-Last Frame-to-Video) is now live on WaveSpeedAI. This model introduces a novel approach to video generation by taking a starting frame and a target end frame, and then generating a smooth, dynamic video that transitions between the two. Instead of interpolating or morphing, WAN-FLF2V creates realistic motion informed by text prompts, style, and visual coherence.

2025-01-14 5 min read

Wan 2.1 text to image generation Is Here: Easily Create Stunning, Realistic Images from Text

We’re excited to announce that the Wan 2.1 text to image generation model is now available on WaveSpeed AI, a powerful tool that turns simple text prompts into high-quality, photo-realistic images.

2025-01-12 5 min read

Wan 2.1 V2V Now Live on WaveSpeedAI: A Powerful Visual Generation Model

We are excited to introduce the wan 2.1 V2V model — an enhanced version of wan 2.1, now available at WaveSpeedAI.

2025-01-11 5 min read

Wan2.1-VACE Now Live on WaveSpeedAl: All-in-One Video Creation and Editing Model

We are excited to introduce the wan-2.1-14b-vace, an all-in-one video creation and editing model developed by Alibaba, now live on WaveSpeedAI!

2025-01-09 5 min read