Previously, we introduced the Large Language Models (LLMs) technology principles and applications. LLMs are a type of Foundation model, and besides LLMs, Foundation models also include Large Vision Models and Large Multimodal Models. Currently popular text-to-image models like Stable Diffusion, DALL-E, text-to-video model Sora, image-text retrieval, and visual content generation all fall under the category … Read more
© Author | Rui Zhang Company | Zcool Network Technology Co., Ltd. Research Direction | Recommendation, Search, NLP, etc. Introduction I really like the imagery often found in science fiction novels that “the universe is a computer.” After diffusion models represented by Disco Diffusion and Stable Diffusion became popular, I often face many questions from … Read more
” Click the above “GameLook” ↑↑↑, subscribe to WeChat “ Text-to-image is just the beginning of AI generation capabilities. Nowadays, with the increasing exploration by peers, many have started training stylized models through Stable Diffusion, turning AI into a specific artistic style creator. Recently, a developer shared their experiences and techniques for training stylized LoRA … Read more
Introduction Last night, the Runway Gen-2 model made a significant breakthrough in video generation, with improved stability and clarity reaching commercial levels. Therefore, I wrote a simple usage guide for everyone to play with! Usage Guide This guide will introduce the costs, usage methods, generation patterns, etc., of Runway’s Gen-2 model. Gen-2 is very easy … Read more
Project Introduction Project: There are various types of agents (projects), each with its own functionality. (rag, ragsql, inference, vision) User: Users represent the system’s users. It is used for authentication and authorization (basic authentication). Each user can access multiple projects. LLMs: Supports any public or local LLM supported by LlamaIndex or Ollama. VRAM: Automatic VRAM … Read more
Many friends in the background have been asking, what can Stable Diffusion (abbreviated as SD) be used for? In simple terms, Stable Diffusion is an AI software that automatically generates images. By inputting text, SD can generate a corresponding image, eliminating the need to ‘draw’ or ‘take’ pictures as before. When we scroll through short … Read more
If we talk about which AI software is the best for architectural design, it must be Stable Diffusion! Previously, we also introduced the basic usage of Midjourney in architectural workflows (click the blue text beside to jump if interested), but although the images generated by MJ are beautiful, the control is too poor, and the … Read more
↑ ClickBlue Text Follow the Jishi Platform Author丨Genius Programmer Zhou Yifan Source丨Genius Programmer Zhou Yifan Editor丨Jishi Platform Jishi Guide In this article, the author presents a relatively complex self-attention replacement example project developed based on Diffusers, aimed at enhancing the consistency of SD video generation. Throughout this process, the author discusses the usage of AttentionProcessor-related … Read more
How to achieve the best quality and performance of SDXL on your own graphics card, and how to choose the appropriate optimization methods and tools, has been a confusing question for GenAI users, as there has been no clear and detailed evaluation report available in the industry for reference.Until full-stack developer Félix San stepped in. … Read more
Stable Diffusion is an AI painting software based on neural networks that can automatically create a new artwork based on the reference image you provide. You only need to upload your reference image, set the parameters, and you can easily obtain high-quality, colorful paintings. Sora is an AI video generation model released by OpenAI. It … Read more