Mage-Flow
Efficient native-resolution image generation and editing
Efficient native-resolution image generation and editing
Low-resource speech synthesis with emotional control!
Codec-native video & image understanding with Mage-VL 4B
Text-to-motion with an interactive 3D skeleton playground
Run complete 3.96M and 9.36M text-to-waveform models live.
Play a Breakout game featuring 50 company logo bricks
BONSAI vs POCKET โ 26B Gemma4 MoE out-runs a 27B on CPU
Single-image Gaussian reconstruction
generate a video from an image with a text prompt
Animate an image into a video with custom prompts
Run a 1-bit 27B LLM locally in your browser on WebGPU
Demo of the Collection of Qwen Image Edit LoRAs
Efficient native-resolution image generation and editing
One-click model liberation + chat playground
Identity-preserving instruction image editing on Krea 2
Extract text from images and PDFs instantly
Run complete 3.96M and 9.36M text-to-waveform models live.
Image edit, text to image, image upscale, remove watermark
Reproduce every ICML 2026 paper with your agent
ltx 2.3 improved image-to-video with 10eros & native audio
Extend images into larger canvases with Krea 2 outpaint
Open agentic retriever for hard multi-step search
Use multiple FLUX.2-Klein LoRAs
High-fidelity 3D Generation from images
Voice chat over WebSocket against a HF speech-to-speech
Play a Breakout game featuring 50 company logo bricks
WAN2.2 based I2V
Resize images for visual token budgets while keeping aspect ratio
FireRed-Image-Edit ร Qwen-Image-Edit-Rapid (Transformers)
Generate vivid images from text prompts in seconds
High-resolution 2K image editing with FireRed
generate a video from an image with a text prompt