WaveSpeedAI Blog

Latest news on AI image and video generation models

Introducing WaveSpeedAI LTX 2 19b Control on WaveSpeedAI

LTX-2 19B ControlNet generates synchronized audio-video (up to 20s) from video input with pose, depth, or canny edge guidance. Supports audio preservation, gene

2026-01-16 6 min read

Introducing WaveSpeedAI LTX 2 19b Ic LoRA Trainer on WaveSpeedAI

LTX-2 IC-LoRA Trainer lets you train custom In-Context LoRA models for video-to-video transformations, including depth/pose adapters, video restoration, and sty

2026-01-16 5 min read

Introducing WaveSpeedAI LTX 2 19b Video LoRA Trainer on WaveSpeedAI

LTX-2 Audio-Video LoRA Trainer lets you train custom LoRA models with synchronized audio-video generation support. Train action, motion, and video effect models

2026-01-16 5 min read

Introducing WaveSpeedAI LTX 2 19b Video Upscaler on WaveSpeedAI

LTX-2 19B Video Upscaler converts low-resolution videos into crisp 4K footage with seamless motion dynamics and frame consistency. Ready-to-use REST inference A

2026-01-16 5 min read

Introducing WaveSpeedAI Molmo2 Image Captioner on WaveSpeedAI

Molmo2-4B Image Captioner: Generate detailed, accurate captions for images with customizable detail levels (low, medium, high). Open-source vision-language mode

2026-01-16 5 min read

Introducing WaveSpeedAI Molmo2 Image Content Moderator on WaveSpeedAI

Molmo2-4B Image Content Moderator: Analyze image content for safety, appropriateness, and policy compliance. Detects violence, nudity, gore, and other harmful v

2026-01-16 6 min read

Introducing WaveSpeedAI Molmo2 Image Qa on WaveSpeedAI

Molmo2-4B Image QA: Answer questions about images with support for multi-image comparison (1-2 images). Open-source vision-language model. Ready-to-use REST API

2026-01-16 5 min read

Introducing WaveSpeedAI Molmo2 Prompt Optimizer on WaveSpeedAI

Molmo2-4B Prompt Optimizer: Enhance prompts for image and video generation with intelligent restructuring, style guidance, and context-aware improvements. Open-

2026-01-16 6 min read

Introducing WaveSpeedAI Molmo2 Video Captioner on WaveSpeedAI

Molmo2-4B Video Captioner: Generate detailed, accurate captions for videos with customizable detail levels (low, medium, high). Open-source vision-language mode

2026-01-16 6 min read

Introducing WaveSpeedAI Molmo2 Text Content Moderator on WaveSpeedAI

Molmo2-4B Text Content Moderator: Analyze text content for safety, appropriateness, and policy compliance. Detects hate speech, violence, sexual content, and ot

2026-01-16 6 min read

Introducing WaveSpeedAI Molmo2 Video Content Moderator on WaveSpeedAI

Molmo2-4B Video Content Moderator analyzes video content for safety, appropriateness, and policy compliance. Detects violence, nudity, gore, and other harmful v

2026-01-16 6 min read

Introducing WaveSpeedAI Molmo2 Video Qa on WaveSpeedAI

Molmo2-4B Video QA: Answer questions about video content with temporal understanding. Open-source vision-language model. Ready-to-use REST API, no cold starts,

2026-01-16 5 min read