Supertonic (TTS)
Lightning-Fast, On-Device TTS
Lightning-Fast, On-Device TTS
Generate videos from images and text prompts
Streaming conversational audio in realtime
Generate custom images from text descriptions
Track objects in a video using points, boxes, or text prompts
Qwen Image Editing Fusion Collection LoRA Demo
Fast, multi-speaker TTS (44.1kHz) with voice cloning
Complex text label dection using SAM3 with VLM-FO1
Fast 4 step inference with Qwen Image Edit 2509
Generate dynamic video from an image
The secrets to building world-class LLMs
Demo of the Collection of Qwen Image Editing LoRAs.
Generate images from text prompts with optional editing
Generate depth maps from images using GPU acceleration
Wan2.2 Animate
Lightning-Fast, On-Device TTS
Generate any application by Vibe Coding
Generate custom images from text descriptions
Convert photos to anime-style images
Track objects in a video using points, boxes, or text prompts
generate a video from an image with a text prompt
Qwen-Image-2509-MultipleAngles
AI-powered image editing tool
Fast, multi-speaker TTS (44.1kHz) with voice cloning
Swap faces in images
Streaming conversational audio in realtime
Ask a question to get a consensus answer
Generate images from text prompts
Image-to-3D Generation
Qwen-Image-2509-CharacterSheet
Embedding Leaderboard
Free Text-To-Speech generator with Emotion control (OpenAI)