08:52
ByteDance Just Rewrote AI Image Generation!|Is BitDance the Stable Diffusion Killer
BitDance, an open-source autoregressive image generation model jointly developed by ByteDance, the Chinese University of Hong Kong, a...
Sort by: Newest Items
There are 313 items in this page
33:45
New #1 open source AI model just dropped
GLM-5 from Zhipu AI, available for free at z.ai, is reviewed here as a top-performing open-source language model with a chat interfac...
29:36
NVIDIA Just KILLED all Voice AI — PersonaPlex is Wild!
This video provides a complete installation guide for NVIDIA PersonaPlex, an open-source duplex voice AI model that processes speech-...
07:33
SkyReels V3 is HERE! Perfect Lip Sync & Subject Consistency in ComfyUI
SkyReels V3 brings three new model variants — Video-to-Video, Reference Generation, and Audio-to-Video — and this Veteran AI video wa...
15:35
Ace-Step 1.5 – FREE & Open Source Suno / Udio Competitor – Runs Locally!
Ace-Step 1.5 is a free, open-source music generation model positioning itself as a local alternative to subscription services like Su...
27:22
New #1 open-source AI model is WILD
Kimmy K2.5 is a new open-source multimodal model from the team behind Kimmy AI, positioned as competitive with leading closed models...
13:28
Voice Cloning is Dead? Welcome to AI “Voice Design” (Qwen3 TTS)|Qwen3 TTS Full Tutorial
Qwen3 TTS goes beyond traditional voice cloning to offer a three-function voice synthesis platform: voice design (generating voices f...
26:18
Elevenlabs just got wrecked. This free AI text to speech is WILD!
Alibaba has released Qwen 3 Text-to-Speech, and this video makes the case that it's now the strongest open-source TTS option availabl...
20:38
Clone ANY Voice for Free — Qwen Just Changed Everything
Sam Witteveen digs into the newly open-sourced Qwen 3 TTS model family from Alibaba's Qwen team, covering what the release means for...
08:46
Better Than Suno? New Free Open-Source AI Makes 6-Min Songs| 12GB VRAM to Generate Full Songs
Heart Mula is a new open-source music foundation model family released in January 2026 that can generate high-fidelity songs up to si...