Ministral WebGPU
Frontier multimodal AI, running entirely in your browser.
Frontier multimodal AI, running entirely in your browser.
Generate edited images with masks and prompts
Generate or edit images using text prompts
Generate speech from text
Turn boring math into engaging animation videos
Official demo for Ovis-Image
Let your character interact naturally
Edit and guide image generation
Generate images from text prompts
Generate stunning images from text prompts
Display evaluation metrics for LLM benchmarks
Generate detailed images from text or edit existing images
Generate videos from images using prompts
Fast 4 step inference with Qwen Image Edit 2509
Demo of the Collection of Qwen Image Edit LoRAs.
Generate any application by Vibe Coding
Ask a question to a council of AI models for a detailed answer
Wan2.2 Animate
Generate images from text prompts
generate a video from an image with a text prompt
Frontier multimodal AI, running entirely in your browser.
The secrets to building world-class LLMs
Generate speech from text
Blazingly fast text-to-speech 100% locally in your browser
Generate speech from text with voice options
Generate or edit images using text prompts
Image-to-3D Generation
image generation
AI-powered image editing tool
All-in-one face swapping: single photo, video, multi-source,
Official demo for Ovis-Image