DEV Community

Garyvov profile picture

Garyvov

AI developer exploring the frontiers of open-source models (LLMs, VLMs, OCR). I build and share practical tools based on my experiments.

Joined Joined on  Personal website https://zimage.run
Mistral Small 4:开源 AI 的三合一革命

Mistral Small 4:开源 AI 的三合一革命

1
Comments 1
1 min read
Nemotron-3-Super-120B-A12B:英伟达 MoE 架构的暴力美学

Nemotron-3-Super-120B-A12B:英伟达 MoE 架构的暴力美学

Comments
1 min read
Fish Audio S2-Pro:用自然语言控制语音情感的 TTS 模型

Fish Audio S2-Pro:用自然语言控制语音情感的 TTS 模型

1
Comments
1 min read
Fish Audio S2-Pro: A TTS Model with Emotion in Speech Controlled with Natural Language

Fish Audio S2-Pro: A TTS Model with Emotion in Speech Controlled with Natural Language

Comments
3 min read
Use OpenClaw to Tweet from VPS Without Getting Banned: Headed Browser + Xvfb Solution

Use OpenClaw to Tweet from VPS Without Getting Banned: Headed Browser + Xvfb Solution

Comments
7 min read
使用Openclaw在服务器发推特不被封?用有头浏览器 + 虚拟显示完美绕过反爬检测

使用Openclaw在服务器发推特不被封?用有头浏览器 + 虚拟显示完美绕过反爬检测

Comments
2 min read
FireRed-Image-Edit 1.1 Tops Open-Source Rankings with 7.94 Score, Surpassing Alibaba's Qwen

FireRed-Image-Edit 1.1 Tops Open-Source Rankings with 7.94 Score, Surpassing Alibaba's Qwen

Comments
5 min read
小红书 FireRed-Image-Edit-1.1 刚开源就登顶!7.94 分干翻阿里 Qwen-Image-Edit-2511

小红书 FireRed-Image-Edit-1.1 刚开源就登顶!7.94 分干翻阿里 Qwen-Image-Edit-2511

Comments
2 min read
阿里开源 Qwen3.5-9B:9B 参数干翻 120B,小模型的 SOTA 时刻

阿里开源 Qwen3.5-9B:9B 参数干翻 120B,小模型的 SOTA 时刻

Comments
2 min read
Claude Code New Feature: /loop - Let AI Work for You 24/7

Claude Code New Feature: /loop - Let AI Work for You 24/7

1
Comments 1
2 min read
Claude Code 新功能:/loop 让 AI 自动帮你"值班"

Claude Code 新功能:/loop 让 AI 自动帮你"值班"

Comments
1 min read
Xiaohongshu's FireRed-Image-Edit-1.1 Tops Charts at Launch! 7.94 Score Beats Alibaba's Qwen-Image-Edit-2511

Xiaohongshu's FireRed-Image-Edit-1.1 Tops Charts at Launch! 7.94 Score Beats Alibaba's Qwen-Image-Edit-2511

Comments
5 min read
LTX-2.3 Open Source! Audio-Video Sync, 20s 4K Video on GPU

LTX-2.3 Open Source! Audio-Video Sync, 20s 4K Video on GPU

Comments
3 min read
AI Agents Can Finally Fetch Tweets Without Login! This OpenClaw Skill Makes It Zero-Config

AI Agents Can Finally Fetch Tweets Without Login! This OpenClaw Skill Makes It Zero-Config

Comments
3 min read
AI Agent 抓推特终于不用登录了!这个 OpenClaw 技能零配置搞定

AI Agent 抓推特终于不用登录了!这个 OpenClaw 技能零配置搞定

Comments
2 min read
Claude Code + SEOMachine: The Right Way to Write SEO Articles with AI

Claude Code + SEOMachine: The Right Way to Write SEO Articles with AI

Comments
7 min read
Claude Code + SEOMachine:AI 写 SEO 文章的正确姿势

Claude Code + SEOMachine:AI 写 SEO 文章的正确姿势

Comments 1
3 min read
Qwen3-TTS: Complete Guide to Open-Source Text-to-Speech Model

Qwen3-TTS: Complete Guide to Open-Source Text-to-Speech Model

2
Comments
7 min read
How to Use AI Face Swap Technology for Perfect Facial Replacement: Complete Guide 2026

How to Use AI Face Swap Technology for Perfect Facial Replacement: Complete Guide 2026

Comments
7 min read
How to Use AI Image Expander to Extend Image Boundaries: Complete Guide 2026

How to Use AI Image Expander to Extend Image Boundaries: Complete Guide 2026

Comments
7 min read
How to Use AI Image Upscaler to Enhance Image Quality: Complete Guide 2026

How to Use AI Image Upscaler to Enhance Image Quality: Complete Guide 2026

Comments
6 min read
Qwen3-TTS: The Open-Source Text-to-Speech Revolution in 2026

Qwen3-TTS: The Open-Source Text-to-Speech Revolution in 2026

2
Comments 1
8 min read
Microsoft VibeVoice-ASR: Revolutionary Speech Recognition Model for Long-Form Audio

Microsoft VibeVoice-ASR: Revolutionary Speech Recognition Model for Long-Form Audio

1
Comments
8 min read
AgentCPM-Explore: The First Open-Source 4B Agent Model Revolutionizing On-Device AI

AgentCPM-Explore: The First Open-Source 4B Agent Model Revolutionizing On-Device AI

1
Comments 1
7 min read
FLUX 2 Klein: The Fastest AI Image Generation Model with 9B and 4B Parameters

FLUX 2 Klein: The Fastest AI Image Generation Model with 9B and 4B Parameters

Comments
8 min read
GLM-Image: The First Open-Source Industrial-Grade Autoregressive Image Generation Model

GLM-Image: The First Open-Source Industrial-Grade Autoregressive Image Generation Model

Comments
8 min read
How to Use Qwen-Image-Layered GGUF in ComfyUI: Complete Installation and Usage Guide

How to Use Qwen-Image-Layered GGUF in ComfyUI: Complete Installation and Usage Guide

Comments
8 min read
Qwen Image Layered: Revolutionary AI Image Generation with Layer Decomposition Technology

Qwen Image Layered: Revolutionary AI Image Generation with Layer Decomposition Technology

Comments
8 min read
Qwen-Image-Edit-2511-Multiple-Angles LoRA: Complete Guide to Multi-Angle AI Image Generation

Qwen-Image-Edit-2511-Multiple-Angles LoRA: Complete Guide to Multi-Angle AI Image Generation

7
Comments
14 min read
How to Install and Configure LTX-2 GGUF Models in ComfyUI: Complete 2026 Guide

How to Install and Configure LTX-2 GGUF Models in ComfyUI: Complete 2026 Guide

3
Comments
14 min read
LTX-2 Advanced Prompt Techniques: From Basics to Professional Video Creation

LTX-2 Advanced Prompt Techniques: From Basics to Professional Video Creation

1
Comments
13 min read
How to Configure LTX-2 in ComfyUI: Complete 2026 Guide for AI Video Generation

How to Configure LTX-2 in ComfyUI: Complete 2026 Guide for AI Video Generation

Comments
15 min read
LTX-2 Prompting Guide: Master AI Video Generation with Expert Techniques

LTX-2 Prompting Guide: Master AI Video Generation with Expert Techniques

2
Comments
12 min read
Best Practices for Training LoRA Models with Z-Image: Complete 2026 Guide

Best Practices for Training LoRA Models with Z-Image: Complete 2026 Guide

1
Comments
6 min read
Amazing Z-Image Workflow v3.0: Complete Guide to Enhanced ComfyUI Image Generation

Amazing Z-Image Workflow v3.0: Complete Guide to Enhanced ComfyUI Image Generation

5
Comments
9 min read
How to Add Randomness to Z-Image Turbo Using Transformers: Complete Seed Control Guide

How to Add Randomness to Z-Image Turbo Using Transformers: Complete Seed Control Guide

Comments
8 min read
Qwen-Image-2512-Turbo-LoRA: The Ultimate Guide to 20x Faster AI Image Generation

Qwen-Image-2512-Turbo-LoRA: The Ultimate Guide to 20x Faster AI Image Generation

Comments
9 min read
Qwen Image 2512 Workflow: Complete Guide to AI Image Generation in 2026

Qwen Image 2512 Workflow: Complete Guide to AI Image Generation in 2026

Comments
11 min read
Qwen-Image-2512 vs. Z-Image Turbo: 5-Prompt Benchmark - Which Model is Better?

Qwen-Image-2512 vs. Z-Image Turbo: 5-Prompt Benchmark - Which Model is Better?

1
Comments
5 min read
Qwen Image 2512 GGUF: Complete Guide to Running AI Image Generation on Consumer Hardware

Qwen Image 2512 GGUF: Complete Guide to Running AI Image Generation on Consumer Hardware

2
Comments
10 min read
Z-Image-Turbo-Anime: Complete Guide to Lightning-Fast Anime AI Image Generation

Z-Image-Turbo-Anime: Complete Guide to Lightning-Fast Anime AI Image Generation

Comments
11 min read
Z-Image Turbo Quantized: Complete Guide to Running Professional AI Image Generation on Low VRAM GPUs

Z-Image Turbo Quantized: Complete Guide to Running Professional AI Image Generation on Low VRAM GPUs

Comments
10 min read
loading...