Tech-Practice

@UCC8cMMvUfSYGndUfK7HgCsg - 6.7K subscribers

Tech tutorials, AI projects. Democratize AI! Contact: ttio2tech at gmail For Mac (apple silicon) tutorials, see agireact.com/mac-tutorials Accomplishments include: 1. AMD $95 APU turned into a 16 GB VRAM GPU. youtu.be/HPO7fu7Vyw4 20K views medium article: medium.com/p/51a8636a4719 featured on multiple tech news websites! www.techspot.com/news/99847-modder-converts-95-amd… 2. Contributed to multiple open source projects such as Fooocus (so AMD GPU users can use it) Get better prepared for AI age ! Empowering you with tech knowledge, one tutorial at a time! Master the art of technology, and become the architect of your own digital destiny. 👉ⓢⓤⓑⓢⓒⓡⓘⓑⓔ If you would like to support or buy me a cup of coffee, please use following link. Donations are welcome! For crypto donation, use Uniswap address: techpractice.uni.eth Thanks!

Home Videos Live Playlists

Kung fu bot - China's Robot 2025 vs 2026 Live performance - UniTree Robotics Wu Bot

Kung fu bot - China's Robot 2025 vs 2026 Live performance - UniTree Robotics Wu Bot Tech-Practice

2K views - 18 hours ago

How to access Seedance 2.0? Use Jimeng

How to access Seedance 2.0? Use Jimeng Tech-Practice

1.4K views - 3 days ago

OpenClaw safely Install and Setup - Mac, MacMini, or PC

OpenClaw safely Install and Setup - Mac, MacMini, or PC Tech-Practice

1.2K views - 4 days ago

Mac local vibe coding agentic coding: GLM-4.7-Flash + opencode - Step by step setup and demo

Mac local vibe coding agentic coding: GLM-4.7-Flash + opencode - Step by step setup and demo Tech-Practice

919 views - 1 week ago

Flova AI - How to Create a Sora 2 Anime in 10 Minutes! 🤯 Full Tutorial

Flova AI - How to Create a Sora 2 Anime in 10 Minutes! 🤯 Full Tutorial Tech-Practice

491 views - 2 weeks ago

GLM-4.7-Flash powered Local Claude level AI agent coding - Step by step setup

GLM-4.7-Flash powered Local Claude level AI agent coding - Step by step setup Tech-Practice

1.3K views - 3 weeks ago

Flux2 Klein 4B running locally on Mac

Flux2 Klein 4B running locally on Mac Tech-Practice

2.3K views - 1 month ago

Cephalon AI - the cloud ComfyUI works like a charm

Cephalon AI - the cloud ComfyUI works like a charm Tech-Practice

377 views - 1 month ago

Nemotron 3 Nano running very fast on Macbook/Mac Mini locally using LMStudio

Nemotron 3 Nano running very fast on Macbook/Mac Mini locally using LMStudio Tech-Practice

2K views - 2 months ago

Finetuning Z-Image LoRA locally using AI-Toolkit: Works on 12GB VRAM Nvidia GPU such as RTX 3060

Finetuning Z-Image LoRA locally using AI-Toolkit: Works on 12GB VRAM Nvidia GPU such as RTX 3060 Tech-Practice

1K views - 2 months ago

Z-Image LoRA + ComfyUI: Complete Setup and Usage Guide

Z-Image LoRA + ComfyUI: Complete Setup and Usage Guide Tech-Practice

5.7K views - 2 months ago

AMD GPU running Z-Image Turbo - the NEW amazing image gen model

AMD GPU running Z-Image Turbo - the NEW amazing image gen model Tech-Practice

1.8K views - 2 months ago

The speech that inspired ComfyUI, ChatGPT and all AI companies

The speech that inspired ComfyUI, ChatGPT and all AI companies Tech-Practice

304 views - 2 months ago

Macbook/Mac Mini running Z-Image Turbo - the new image gen model

Macbook/Mac Mini running Z-Image Turbo - the new image gen model Tech-Practice

6.1K views - 2 months ago

Flux2 is here! The 32B Flux.2 Dev model is released. But my 3090 got OOM.

Flux2 is here! The 32B Flux.2 Dev model is released. But my 3090 got OOM. Tech-Practice

1.4K views - 2 months ago

Mac install Claude Code - install and demo one of the best coding agent (Mac or Linux)

Mac install Claude Code - install and demo one of the best coding agent (Mac or Linux) Tech-Practice

1.3K views - 3 months ago

Mac or PC: Run Qwen-Image-Edit 2509 locally (GGUF to save VRAM)

Mac or PC: Run Qwen-Image-Edit 2509 locally (GGUF to save VRAM) Tech-Practice

1.9K views - 3 months ago

Nanochat: Single GPU to Build your own ChatGPT

Nanochat: Single GPU to Build your own ChatGPT Tech-Practice

1.6K views - 4 months ago

RTX 5090 vs RTX 4090: Wan 2.2 animate speed comparison side by side

RTX 5090 vs RTX 4090: Wan 2.2 animate speed comparison side by side Tech-Practice

6.4K views - 4 months ago

Running HunyuanImage-3.0 locally - how much VRAM needed?

Running HunyuanImage-3.0 locally - how much VRAM needed? Tech-Practice

1.3K views - 4 months ago

Run Wan Animate locally - on ComfyUI and a single GPU

Run Wan Animate locally - on ComfyUI and a single GPU Tech-Practice

3.2K views - 4 months ago

Wan2.2-Animate is here! It solves character consistency! And it's open source!

Wan2.2-Animate is here! It solves character consistency! And it's open source! Tech-Practice

1.5K views - 4 months ago

Olares OS: your personal AI cloud - install and demo (ComfyUI, Ollama)

Olares OS: your personal AI cloud - install and demo (ComfyUI, Ollama) Tech-Practice

2.1K views - 5 months ago

Wan 2.2 text to image ComfyUI Workflow - Generate Photorealistic Image (no LoRA finetuning needed)

Wan 2.2 text to image ComfyUI Workflow - Generate Photorealistic Image (no LoRA finetuning needed) Tech-Practice

1.3K views - 5 months ago

Mac or Nvidia GPU run Qwen-image-edit locally

Mac or Nvidia GPU run Qwen-image-edit locally Tech-Practice

4.5K views - 5 months ago

Qwen-image-edit: how to use it for FREE

Qwen-image-edit: how to use it for FREE Tech-Practice

3.7K views - 5 months ago

image to video - Macbook/Mac Mini run Wan 2.2 AI Video generation locally

image to video - Macbook/Mac Mini run Wan 2.2 AI Video generation locally Tech-Practice

12.8K views - 6 months ago

Mac run OpenAI gpt-oss locally using LMStudio - step by step guide

Mac run OpenAI gpt-oss locally using LMStudio - step by step guide Tech-Practice

2.1K views - 6 months ago

Qwen-Image running locally - FREE and BETTER than ChatGPT-4o or Flux.1!

Qwen-Image running locally - FREE and BETTER than ChatGPT-4o or Flux.1! Tech-Practice

1.2K views - 6 months ago

Mac run OpenAI gpt-oss locally - step by step how to run it using Ollama

Mac run OpenAI gpt-oss locally - step by step how to run it using Ollama Tech-Practice

10.9K views - 6 months ago

Macbook/Mac Mini run Wan 2.2 AI Video generation locally

Macbook/Mac Mini run Wan 2.2 AI Video generation locally Tech-Practice

21K views - 6 months ago

Wan 2.2 Is HERE! 720p AI Videos at your home - Cinematic MoE Model Demo

Wan 2.2 Is HERE! 720p AI Videos at your home - Cinematic MoE Model Demo Tech-Practice

6.1K views - 6 months ago

First-Last-Frame Magic: WAN-2.1 AI Video Generation (ComfyUI Guide)

First-Last-Frame Magic: WAN-2.1 AI Video Generation (ComfyUI Guide) Tech-Practice

3.1K views - 6 months ago

OmniGen 2 + ComfyUI: The ONLY Tutorial You’ll Ever Need (Install, Generate, Edit!)

OmniGen 2 + ComfyUI: The ONLY Tutorial You’ll Ever Need (Install, Generate, Edit!) Tech-Practice

1.6K views - 7 months ago

Macbook run FLUX.1-Kontext locally - the free and open source model that beats Chatgpt-4o. Mac mini

Macbook run FLUX.1-Kontext locally - the free and open source model that beats Chatgpt-4o. Mac mini Tech-Practice

6.3K views - 7 months ago

Rtx 5090 Local GPU run FLUX.1 Kontext [dev] via ComfyUI - installation and performance

Rtx 5090 Local GPU run FLUX.1 Kontext [dev] via ComfyUI - installation and performance Tech-Practice

6K views - 7 months ago

RTX 5090 vs RTX 4090 Running Wan 2.1 AI video generating model locally #5090

RTX 5090 vs RTX 4090 Running Wan 2.1 AI video generating model locally #5090 Tech-Practice

8.5K views - 8 months ago

Introducing FLUX Kontext - image editing made easy: The AI Photoshop Killer You Can Try FREE Today

Introducing FLUX Kontext - image editing made easy: The AI Photoshop Killer You Can Try FREE Today Tech-Practice

835 views - 8 months ago

The fastest Flux.1: FP4 Flux running live on a RTX 5090 #flux1

The fastest Flux.1: FP4 Flux running live on a RTX 5090 #flux1 Tech-Practice

2.7K views - 8 months ago

48GB RTX 4090! Risk, Reward & VRAM Inside the Underground Mod Scene #4090rtx

48GB RTX 4090! Risk, Reward & VRAM Inside the Underground Mod Scene #4090rtx Tech-Practice

12.5K views - 9 months ago

BITNET - 1 Bit LLM inferencing on Mac - step by step installing Bitnet on Apple silicon #macbook

BITNET - 1 Bit LLM inferencing on Mac - step by step installing Bitnet on Apple silicon #macbook Tech-Practice

1K views - 9 months ago

RTX 5090 run HiDream-I1: the Best Open Source AI Art Model Yet? ComfyUI install & Demo

RTX 5090 run HiDream-I1: the Best Open Source AI Art Model Yet? ComfyUI install & Demo Tech-Practice

1.7K views - 9 months ago

Only needs 6GB VRAM - FramePack for local AI Video generating: installation and test running

Only needs 6GB VRAM - FramePack for local AI Video generating: installation and test running Tech-Practice

2.4K views - 9 months ago

RTX 5090 vs RTX 4090 - Test AI performance in Flux1.dev text to image SOTA model

RTX 5090 vs RTX 4090 - Test AI performance in Flux1.dev text to image SOTA model Tech-Practice

8.6K views - 10 months ago

Hunyuan3D-2: text or image to 3D model running locally (step by step guide)

Hunyuan3D-2: text or image to 3D model running locally (step by step guide) Tech-Practice

3.2K views - 10 months ago

Macbook run Wan 2.1 AI Video generation locally

Macbook run Wan 2.1 AI Video generation locally Tech-Practice

19.2K views - 10 months ago

RTX 50 series GPU install Nvidia Driver, Pytorch on Linux (for GPU: 5060ti,5070, 5070Ti, 5080, 5090)

RTX 50 series GPU install Nvidia Driver, Pytorch on Linux (for GPU: 5060ti,5070, 5070Ti, 5080, 5090) Tech-Practice

18.3K views - 10 months ago

ComfyUI Tip: 1.5 times faster Flux1.dev or HunyuanVideo generating using TeaCache

ComfyUI Tip: 1.5 times faster Flux1.dev or HunyuanVideo generating using TeaCache Tech-Practice

2.5K views - 11 months ago

Hunyuan Image to Video (I2V) - 2K video, lip syncing, motion driven interactions

Hunyuan Image to Video (I2V) - 2K video, lip syncing, motion driven interactions Tech-Practice

3.3K views - 11 months ago

Wan 2.1 - the new Video AI model: running it on ComfyUI

Wan 2.1 - the new Video AI model: running it on ComfyUI Tech-Practice

5.6K views - 11 months ago

RTX 5090 vs 3090 - EP2: Flux.1-dev, HunyuanVideo, Stable diffusion 3.5 Large running on GPU

RTX 5090 vs 3090 - EP2: Flux.1-dev, HunyuanVideo, Stable diffusion 3.5 Large running on GPU Tech-Practice

23.3K views - 11 months ago

RTX 5090 vs 3090 EP1 - LLM Deepseek-r1 Ollama running on GPU locally

RTX 5090 vs 3090 EP1 - LLM Deepseek-r1 Ollama running on GPU locally Tech-Practice

28.1K views - 11 months ago

RTX 5090 unboxing! ROG Astral GeForce RTX 5090 32GB GDDR7 OC Edition

RTX 5090 unboxing! ROG Astral GeForce RTX 5090 32GB GDDR7 OC Edition Tech-Practice

2.3K views - 1 year ago

RTX 5090 GPU run ComfyUI - Experience the Power of RTX 5090 with ComfyUI (Flux.dev model)

RTX 5090 GPU run ComfyUI - Experience the Power of RTX 5090 with ComfyUI (Flux.dev model) Tech-Practice

22.1K views - 1 year ago

AMD GPU run DeepSeek-R1 reasoning model (AMD native support)

AMD GPU run DeepSeek-R1 reasoning model (AMD native support) Tech-Practice

7.8K views - 1 year ago

Macbook user - Run Deepseek-R1 using Ollama

Macbook user - Run Deepseek-R1 using Ollama Tech-Practice

1.5K views - 1 year ago

Ollama run Phi4 model on Macbook - the small 14B model from Microsoft that's better than 70B model

Ollama run Phi4 model on Macbook - the small 14B model from Microsoft that's better than 70B model Tech-Practice

1.1K views - 1 year ago

Ultimate guide on training and using LoRA for HunyuanVideo - the best open source local video AI

Ultimate guide on training and using LoRA for HunyuanVideo - the best open source local video AI Tech-Practice

3.2K views - 1 year ago

Run HunyuanVideo on Mac/Macbook ! (Workflow included)

Run HunyuanVideo on Mac/Macbook ! (Workflow included) Tech-Practice

7.4K views - 1 year ago

AMD GPU run Hunyuan Video - tutorial and demo

AMD GPU run Hunyuan Video - tutorial and demo Tech-Practice

8.1K views - 1 year ago