Content before more comment is regarded as page excerpt.
January 1, 2020About 1 min
Illustrious XL 3.0–3.5-vpred represents a major advancement in Stable Diffusion XL (SD XL) modeling, notably supporting resolutions ranging seamlessly from 256 up to 2048. The v3.5-vpred variant particularly emphasizes robust natural language understanding capabilities, comparable in sophistication to miniaturized large language models (LLMs), achieved through extensive simultaneous training of both CLIP and UNet components.
March 22, 2025About 9 min
In the competitive world of game development, staying ahead of technological advancements is crucial. Generative AI has emerged as a game changer, offering unprecedented opportunities for game designers to push boundaries and create immersive virtual worlds. At the forefront of this revolution is Stability AI’s cutting-edge text-to-image AI model, Stable Diffusion 3.5 Large (SD3.5 Large), which is transforming the way we approach game environment creation.
March 19, 2025About 5 min
Overview
This article describes how to install the "Copilot MCP" extension in VS Code and use GitHub Copilot with MCP to fetch information from GitHub for testing purposes.
Note: Since the official GitHub Copilot implementation also seems to support MCP, this extension might become unnecessary once the feature is released.
March 18, 2025About 2 min
March 17, 2025About 5 min
Introduction
Illustrious XL 1.0-2.0 series aims to stabilize native generation at 1536 resolution while significantly improving natural language understanding capabilities.
While users sometimes observed successful 1024x1536 resolution generations, these were not stable. Similarly, 512x512 generations occasionally produced unwanted artifacts.
March 15, 2025About 4 min
Hi this is Crody from Team-C: creator of Nova Series
In this article, I'll write down what kind of merge I use with some knowledge about SDXL models For how I do, please read Merge Scripter Guide first
1. Weighted Sum / Sum Twice
Weighted Sum (WS) merges 2 models, Sum Twice (ST) merges first 2 and 1 model (which means doing WS twice) You can use Block Merge as well Using alpha (and beta) to determine how much similarity the result have Higher value means the results would be similar to latter model
March 14, 2025About 5 min
Model Context Protocol (MCP) has stirred up quite a storm on Twitter—but is it actually useful, or just noise? In this debate, Harrison Chase (LangChain CEO) and Nuno Campos (Head of LangGraph) discuss whether MCP lives up to the hype.
Harrison's Take: MCP Is Actually Useful
I started skeptical about MCP, but I've begun to see its value. Essentially: MCP is useful when you want to add tools to an agent you don't control.
May 1, 2024About 4 min
NOTE
This guide is still work in progress. Any and all feedback is highly appreciated, it doesn't have to be suggestions, even questions regarding things you didn't understand can help me figure out what to refine.
January 19, 2023About 13 min
- Introduction
- Experiment Overview
- Experiment 1
- Analysis 1
- Experiment 2
- Analysis 2
- Side Note 1
- Experiment 2 Setup
- Experiment 2: Results and Analysis
- Analysis Approach and Reminders (to me)
December 23, 2022About 7 min