Trackers
Track objects in your video and get an annotated result
Track objects in your video and get an annotated result
Open-source autoregressive model with binary visual tokens.
A JavaScript port of Andrej Karpathy's microgpt.py
text to video, image to video, video extend
Chat with Nanbeige AI locally in your browser
Generate natural‑sounding speech from your text
Counting manifolds in open LLMs from behavior to SAEs.
Metacognitive
Change the camera angle of a photo with AI
generate a video from an image with a text prompt
Generate vivid images from text prompts
text to video, image to video, video extend
Generate custom speech from text, voice descriptions, or samples
Image edit, text to image, image upscale, remove watermark
Wan2.2 Animate
High-fidelity 3D Generation from images
Demo of the Collection of Qwen Image Edit LoRAs
Generate or edit images from text prompts with optional input images
FireRed-Image-Edit-1.0
Track objects in your video and get an annotated result
Generate any application by Vibe Coding it
Generate singing voice from your lyrics
Build, train, and run LLMs in the browser
generate a video from an image with a text prompt
Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
Open-source autoregressive model with binary visual tokens.
Generate natural‑sounding speech from your text
Free platform to access multiple AI models
Based 'Z-IMAGE TURBO'
Remove Silence From Audio
Embedding Leaderboard
Fast 4 step inference with Qwen Image Edit 2509