ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot Image-Text-to-Text β’ Updated 8 days ago β’ 483
Running on Zero MCP 14 WordVoice Word-Level Controllable TTS π£ 14 Zero-shot TTS with explicit word-level prosody control
Running Featured 332 Bonsai Image WebGPU π³ 332 State-of-the-art image generation, in your browser.
Running on Zero Agents 54 Vibe Voice Custom Voices π’ 54 Vibe Voice Large with Custom Voices (Voice Cloning)
Running Agents 161 Qwen3.5 Omni Offline Demo π 161 Chat with a multimodal AI using text, audio, images or video
Running Agents 73 Qwen3.5 Omni Online Demo π 73 Chat with a multimodal AI using text, image, audio, or video
Running Featured 145 Voxtral Realtime WebGPU π¬ 145 Real-time speech transcription, entirely in your browser.