15:53
Open Responses – The NEW Standard API for Open Models
Sam Witteveen examines OpenAI's \"Open Responses\" initiative—a proposed open API standard aimed at giving open-source models a commo...
Sort by: Newest Items
There are 313 items in this page
33:49
Open-source SUNO is here! Free offline AI music generator
Heart Moola is the first open-source AI music generator to credibly challenge commercial platforms, and this video explains both why...
34:23
New open-source “Nano Banana” is here! INSANELY fast
Flux 2 Klein is the latest release from Black Forest Labs, and this video puts it through a direct head-to-head test against the curr...
07:20
Perfect Character Consistency in AI Video: The “Grid Method” with Qwen & LTX Two
This Veteran AI tutorial (presented in Mandarin) demonstrates a \"Grid Method\" for generating multiple storyboard shots of the same...
19:29
Qwen3 Multimodal Embeddings: Finally, RAG That Sees
Sam Witteveen covers the Qwen3-VL-Embedding models—Alibaba's new multimodal embedding series in 2B and 8B parameter sizes—which place...
09:18
Run LTX Video on Low VRAM! 🚀 Fast GGUF Workflow & Audio Noise Fix for ComfyUI
Veteran AI demonstrates a fully viable method for running LTX Video 2 on low-VRAM hardware, using GGUF quantization to dramatically r...
09:39
Master LTX Video Upscaling: 2 Workflows for High-Res AI Video Enhancement
Veteran AI presents two ComfyUI workflows for upscaling existing videos using LTX-2, demonstrating that the model's native upscaling...
09:10
NVIDIA’s 13 New Models
Sam Witteveen covers NVIDIA's CES 2026 keynote, where Jensen Huang announced 13 open-source models across autonomous vehicles, roboti...
11:51
Deploy personaLive Locally: Real-Time AI Avatar with TensorRT Acceleration (Full Linux Guide) 🛠️
This Veteran AI tutorial covers the full local deployment of personaLive, an open-source real-time AI avatar system that drives a vir...
21:26
Using Qwen Image 2512 in ComfyUI – The Photorealism King?
Nerdy Rodent puts Qwen 2512 — Alibaba's new text-to-image model released at the start of 2026 — through its paces inside ComfyUI, tes...