WaveSpeedAI Blog

Latest news on AI image and video generation models

Introducing WaveSpeedAI Hunyuan Video T2V on WaveSpeedAI

Hunyuan Video (t2v) is an advanced text-to-video model that generates high-quality videos from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-28 5 min read

Introducing WaveSpeedAI WAN 2.1 V2V 480p Ultra Fast on WaveSpeedAI

Ultra-fast Wan 2.1 Video-to-Video (v2v) model for generating unlimited AI videos at 480p from existing video inputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-28 5 min read

Introducing WaveSpeedAI FLUX Redux Dev on WaveSpeedAI

FLUX.1 Redux [dev] adapts FLUX.1 base models to generate subtle image variations and easy image-to-image restyling for refinement. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-27 5 min read

Introducing WaveSpeedAI Hunyuan Video 1.5 Image-to-Video on WaveSpeedAI

HunyuanVideo-1.5 (i2v) is a lightweight 8.3B parameter image-to-video model that generates high-quality videos from images with top-tier visual quality and motion coherence. Optimized for fast inference on consumer-grade GPUs. Ready-to-use REST inference API, best performance, no coldstarts, afforda

2025-09-27 5 min read

Introducing WaveSpeedAI Hunyuan Video 1.5 Text-to-Video on WaveSpeedAI

HunyuanVideo-1.5 (t2v) is a lightweight 8.3B parameter text-to-video model that generates high-quality videos with top-tier visual quality and motion coherence. Optimized for fast inference on consumer-grade GPUs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-27 5 min read

Introducing WaveSpeedAI Step1x Edit on WaveSpeedAI

Step1X-Edit converts photos into professional-quality edits using simple instructions, rivaling top proprietary tools. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-27 5 min read

Introducing Kuaishou Kling V2.1 T2V Master on WaveSpeedAI

Kling v2.1 creates cinematic 5-10s videos at 720p or 1080p from a single image or text prompt with improved motion fidelity and coherence. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-26 5 min read

Introducing MiniMax Voice Clone on WaveSpeedAI

Minimax Voice Clone creates high-quality voice clones from short reference clips, closely matching tone, accent, and speaking style. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-26 5 min read

Introducing WaveSpeedAI WAN 2.1 T2V 480p on WaveSpeedAI

Wan 2.1 creates unlimited text-to-video content at 480P from simple text prompts, ideal for prototyping and content generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-26 5 min read

Introducing Recraft AI Recraft Crisp Upscale on WaveSpeedAI

Recraft Crisp Upscale enhances textures, fine details, and facial features to add depth beyond simple resolution boosts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-25 5 min read

Introducing Video Effects Kissing Pro on WaveSpeedAI

Convert two-person photos into natural, synchronized kissing videos with lifelike motion using Photo-To-Video AI. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-25 5 min read

Introducing WaveSpeedAI Framepack on WaveSpeedAI

Framepack is an efficient autoregressive Image-to-Video model that generates smooth, temporally consistent videos from a single image. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

2025-09-25 5 min read