DeepSeek-R1 WebGPU
π§
554
Next-generation reasoning model that runs locally in-browser
Generate customized images from a prompt and reference photo
Generate images from text prompts
mcp_server & FLUX 4-bit Quantization + Enhanced
Optical illusions and style transfer with FLUX
A unified multimodal understanding and generation model.
High-quality virtual try-on ~ Your cyber fitting room
Convert images to anime-style bodies and sketches
Huggingface space for JanusFlow-1.3B
Co-Speech Gesture Video Generation
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
remove background from any image