#U-Net
55 related articles
·2 min
The Evolution of AI Video Generation: From the Will Smith Spaghetti Disaster to Cinematic Quality
From ModelScope's viral Will Smith spaghetti disaster to cinematic videos from Sora and Kling, tracing AI video generation's stunning leap in just 2-3 years through diffusion models and DiT architecture.
Read more →
·3 min
Building AI from Scratch: A Complete Learning Path with 503 Lessons in This Open-Source Course
AI Engineering from Scratch is an open-source course with 503 lessons across 20 phases, from linear algebra to autonomous agents, emphasizing hand-implementation before frameworks, supporting Python/TypeScript/Rust/Julia, with 46K+ GitHub stars.
Read more →
·3 min
Causes and Solutions for Periodic Severe Fluctuations in Dice Evaluation Metrics During Training
In-depth analysis of why Dice evaluation metrics fluctuate periodically during U-Net segmentation training, covering gradient instability, class imbalance amplification, and practical solutions.
Read more →
·5 min
Flux 3 Video Generation Experience: Home Movie Style and Prompt Optimization Capabilities
In-depth analysis of Flux 3 video generation model's home movie style capabilities, intelligent prompt optimization, Hermes Agent usage experience, and outlook for official release.
Read more →
·2 min
Wan2.2 LoRA Fine-Tuning in Practice: A Complete Guide from Principles to Effect Optimization
A detailed guide to Wan2.2 video model LoRA fine-tuning: working principles, common failure causes, and solutions covering weight settings, trigger words, version compatibility, and optimization tips.
Read more →
·2 min
LTX 2.3 + ComfyUI Local Video Generation Hands-On: A New Open-Source AI Video Option
A deep dive into the LTX 2.3 + ComfyUI combo for local AI video generation, covering deployment advantages, VRAM requirements, community ecosystem, and real-world output quality assessment.
Read more →
·3 min
No Python Required: A Unified Multimodal Local AI Generation CLI Tool
A CLI tool that enables local text, image, video, music, and 3D generation without Python. Explore its technical approach, advantages, limitations, and the growing trend of local AI tooling.
Read more →
·3 min
No Python Required: A Unified Multimodal Local AI Generation CLI Tool
A CLI tool requiring no Python that supports local text, image, video, music, and 3D generation. Explore its technical approach, advantages, limitations, and the growing trend of local AI toolification.
Read more →
·2 min
Krea 2 Turbo + Wan 2.2: A Detailed Workflow for Turning Static Images into Dynamic AI Videos
A detailed guide on using Krea 2 Turbo for high-quality static images and Wan 2.2 i2v to add dynamic motion—covering technical principles, key steps, and practical tips.
Read more →
·2 min
ComfyUI KREA 2 v1.2 Identity Edit Workflow: A Practical Guide to Low-VRAM Identity-Preserving Editing
A detailed guide to ComfyUI KREA 2 Identity Edit v1.2 workflow installation and usage, supporting low-VRAM GPUs for identity-preserving editing including pose changes, style transfer, face swap, and virtual try-on.
Read more →
·3 min
FeyNoBg: A Deep Dive into the Open-Source Background Removal Model and Training Library
Deep analysis of FeyNoBg, an open-source background removal project with pre-trained models and training library, compared to remove.bg and rembg solutions.
Read more →
·3 min
Midjourney's Multi-Industry Expansion: The Cross-Domain Logic Behind Its Move from AI Art to Healthcare and Astrology
Midjourney expands from AI image generation into medical scanning, spas, and astrology apps. Behind the seemingly chaotic diversification lies a clear strategic logic of generative AI's horizontal penetration.
Read more →
·6 min
Tongyi Qianwen Qwen-Image-3.0: The Leap of AI Image Generation from Toy to Productivity Tool
Tongyi Qianwen Qwen-Image-3.0 image generation model gets a comprehensive upgrade: supporting 4,500-token ultra-long instructions, pixel-level detail rendering, 12-language knowledge understanding, and ancient painting restoration. This article analyzes its three core capabilities.
Read more →
·3 min
InvokeAI In-Depth Review: Can It Replace SD WebUI and ComfyUI?
A hands-on InvokeAI review covering installation, VRAM optimization, infinite canvas, node workflows, and model management — with an objective comparison to SD WebUI and ComfyUI.
Read more →
·7 min
The Complete AI Character LoRA Training Workflow: Hands-On Multi-Character Consistency Generation with Local Deployment
A detailed guide to a complete local AI character generation workflow: from the five golden rules of LoRA training and automated ComfyUI dataset construction to hands-on comparisons of Crea2, Ideogram4, and Wan for multi-character same-frame interaction—all running free on personal hardware.
Read more →
·3 min
LoRA Training Showdown: We Tested 6 Base Models — Does Ideogram Beat Flux?
A developer ran a 4-day benchmark testing LoRA training across Ideogram, Flux 1 Dev, Flux 2 Dev & more — revealing overfitting traps and surprising rankings.
Read more →
·3 min
LTX2.3 Open-Source Model Tested: Full AI Comic Drama Pipeline on Just 6GB VRAM
LTX2.3 ComfyUI bundle tested: runs locally on 6GB VRAM, covering character generation, image-to-video, storyboarding, motion transfer, and frame interpolation for full AI comic drama workflows.
Read more →
·6 min
Multimodal and Embodied Intelligence: A Comprehensive Look at Progress, Pitfalls, and Opportunities
At the Microsoft Research India summit, top experts explore the real progress of multimodal AI and embodied intelligence: fusing classical robotics with large models, healthcare AI deployment challenges, perceptual bottlenecks in reasoning, and possibilities beyond scaling.
Read more →
·2 min
ComfyUI v0.28.0: Native Video Super-Resolution, 3D Support, and PixelDiT Architecture — A Complete Breakdown
ComfyUI v0.28.0 adds SeedVR2 native video super-resolution, PixelDiT architecture, 3D Gaussian Splatting export, int4 quantization, and lip-sync integration for a major multimodal AI workflow upgrade.
Read more →
·3 min
What to Do When Model Training Fails? A Systematic Debugging and Iteration Guide
Model training failure is the norm in research, not the end. Using a real DiT fine-tuning failure on weather radar as a case study, this guide offers a systematic three-layer debugging methodology — data, training convergence, and evaluation — to help deep learning practitioners diagnose issues and iterate efficiently.
Read more →