DINOv3 Video Tracking
In-browser video tracking, powered by Transformers.js
In-browser video tracking, powered by Transformers.js
Modify images based on text prompts
Edit and enhance images based on descriptive instructions
Generate talking heads from audio
generate a video from an image with a text prompt
Generate personalized character images with prompts
Clarity AI Upscaler Reproduction
Multilingual translation | Transformers.js
nanonets ocr2 / olmocr / qwen2vl ocr / aya vision / rolmocr
Generate realistic audio from video and text
Qwen Image with ControlNet Union
Generate videos from start and end images with prompts
Privacy-safe synthetic data for ML and data augmentation
Chatterbox TTS supporting 23 languages
Generate high-quality images from text prompts
Generate music from text descriptions and melodies
Generate MIDI music from text input
Generate music from text descriptions
In-browser text-to-music w/ Transformers.js!
AI Music Arena & Leaderboard (Suno, Udio, Google, Meta, +)
Create a video from three images and a prompt
use app_fast.py for fast api works wel and app_t2v is 14B
generate a video from an image with a text prompt
Transcribe and Translate in 25 European Languages
Generate edited images based on prompts
Image manipulation with Kontext adapters.[demo]
Image-to-3D Generation
Recommend products to users based on purchase history
Analyze images and detect objects with prompts
Powerful Watermark Removal API
Run Granite-4.0-Micro 100% locally in your browser on WebGPU
Generate Hollywood Style Actors on your Local Machine
270+ Impressive LoRAs for Flux.1
nanonets ocr / smoldocling / monkey ocr / typhoon ocr
Embedding Leaderboard
Generate step-by-step solutions to complex queries
Multimodal Instruction-based Editing and Generation
ChatGPT with real-time web search & URL reading capability
Chat with an AI assistant using text and images
Generate subtitles and translate audio files
Transcribe audio files into text
Run GGUF directly on your browser!
Generate text based on prompts
Video Dubbing with Open Source Projects
Generate images from text prompts
Generate music powered by AI
DiT360: A High-Fidelity Panoramic Image Generation Framework
In-browser background removal
Relight images using foreground and background conditions
AI Remove Watermark
An interactive demo for the DeepSeek-OCR model.
Generate detailed captions for images
Generate captions for images in various styles and lengths
Generate tags for images using Waifu Diffusion models
Text-to-Video
Demo working simulation of Arch Router
The secrets to building world-class LLMs
Generate images from text or images
Generate videos from text or images
Generate AI images from text prompts
Streaming conversational audio in realtime
Playground for music generation using Elastic-musicgen-large
An interactive demo for the Qwen3-VL family models.
Generate images from text prompts
🚀 Support the blending of 2-6 Images!
Molmo2 - Image, Video (QA, Pointing & Tracking)
Image edit, text to image, face swap, image upscale