#controlnet
11 articles
/filters:quality(82)/media/images/1773962750383987480_n3hqzHRZ.webp)
As Replicate is joining Cloudflare, Builders Need Stability More Than Ever — Why Thousands Are Moving Their Multimodal Workloads to WaveSpeedAI
When a major multimodal AI platform is acquired, ripple effects appear quickly. For teams running multimodal workloads, uncertainty isn’t just inconvenient. It’s expensive. A growing number are answering by moving to WaveSpeedAI.
Hailuo 2.3 — Where Motion Meets Emotion
For years, creators have imagined AI that can capture not only motion but also emotion — the subtle essence that makes human expression feel vibrant. That vision has long felt just out of reach. However, today, with the launch of the Hailuo 2.3 Model Series, we take a step closer to making it real! Now it officially lives on WaveSpeedAI! Built by MiniMax, each model—i2v-standard, t2v-standard, or i2v-Fast is designed to bring imagination to life with strong emotional depth. Let's enter the next era of cinematic AI generation, where technology feels human, and every frame tells a story.
Kling 2.6 Is Now Live on WaveSpeedAI: Experience “What You See Is What You Hear” Video Generation
WaveSpeedAI is excited to announce the official launch of Kling 2.6, a breakthrough upgrade that reshapes the way creators produce AI-powered videos. For the first time, video, speech, sound effects, and ambient audio can be generated simultaneously in a single pass.
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.
Veo 3.1 is now available on WaveSpeedAI
WaveSpeedAI, the global multimodal inference acceleration platform, today announced the availability of Veo 3.1 — Google’s latest video and audio generation model — now accessible via the WaveSpeedAI API.
Wan2.2-Fun-Control: Next-Gen AI Video Generation with Precision Control – Now on WaveSpeedAI
Wan2.2-Fun-Control is a next-generation video generation and control model designed to generate high-quality videos that adhere strictly to predefined control conditions.
/filters:quality(82)/media/images/1745293552924720544_c6Cyvrok.webp)
Framepack Now Live on WaveSpeedAI: High-Fidelity Image-to-Video via Autoregressive Generation
Framepack, a cutting-edge autoregressive image-to-video model from lllyasviel (the creator of ControlNet), is now available on WaveSpeedAI. Framepack redefines how static images become videos—by generating each frame based on the one before, it produces smoother motion, greater temporal consistency, and more coherent narratives than traditional methods.
/filters:quality(82)/media/images/1744206424148902819_efc8nkfb.webp)
Ghibli Now Live on WaveSpeedAI
Discover the groundbreaking Ghibli model on WaveSpeedAI, enabling high-quality video generation with unprecedented ease and efficiency. Explore its features, use cases, and why WaveSpeedAI is the ideal platform for your creative needs.
/filters:quality(82)/media/images/1745825166853375485_irvsolhe.webp)
InstantCharacter Model Launches on WaveSpeed: Ushering in a New Era of Personalized Character Generation
We’re excited to announce that Tencent AI Lab’s latest innovation — InstantCharacter, a state-of-the-art personalized character generation model — is now officially live on the WaveSpeed platform. Built upon a scalable Diffusion Transformer framework, InstantCharacter offers high fidelity, strong generalization, and fine-grained text controllability, setting a new benchmark in character generation technology.
The Next Step in AI Image Editing: Meet Qwen-Image-Edit-2509
The Next Step in AI Image Editing: Meet Qwen-Image-Edit-2509
WaveSpeedAI Video Outpainter: The Fastest Way to Expand Videos & Convert Aspect Ratios Without Cropping
If you need to repurpose videos for multiple platforms—TikTok, YouTube, Instagram, Reels, Shorts, ads—cropping isn’t an option.