Local deployment

Many readers mentioned that they hope the locally deployed DeepSeek-R1 has networking capabilities, so let's talk about how to realize it today. First, use Ollama to deploy the model locally (if you have already deployed it, you can ignore this section) Download Ollama through the URL: https://ollama.com. Multiple versions are available for Windows, Linux, and macOS: Take Windows as an example, install it directly after downloading, and the window will be closed automatically after completion, and then you can use the system tray icon to Determine whether Ollama is started or not: Click on the Ollama official...

Recently, I took over a project that needs to use Stable Diffusion, and I need to redeploy a set of SD environment. This is not quite the same as my previous SD deployment, and I encountered some problems during the deployment process, and summarized a more perfect installation plan, which I'd like to share with you here. Project address: https://github.com/AUTOMATIC1111/stable-diffusion-webui Environment Preparation Before starting the deployment, I use the following environment: Python 3.10.6 (...

Previously released Stable Diffusion 3 model, because of excessive auditing, resulting in the generation of human structure "regression", was sprayed a lot. Now an excellent flat replacement has appeared, that is, the Black Forest Labs FLUX model, the team consists of former core members of Stability AI. FLUX was released, the praise was overwhelming, was named "the strongest open source literate map model". Compared with the head of closed-source tools such as Midjourney, DALLE, FLUX's performance is still remarkable. At present, FLUX already supports ComfyUI graphic ...

Introduction to Joy Caption The current excellent image backpropagation cueing model, Joy Caption, has been introduced in a previous article.Joy Caption backpropagation cueing produces detailed and unambiguous information about the image description, and has attracted much attention by supporting both SFW and NSFW image descriptions. It is a combination of a Google siglip-so400m-patch14-384 model and a Meta-Llama-3.1-8B-bnb-4bit model composition geared towards fine-tuning image cues. Running Joy Cap locally ...

Previously, I shared with you some websites where you can experience the Flux model online. Flux [Basics]: Share some websites where you can experience the Flux.1 model online Today, let's share how to deploy the ComfyUI Flux.1 workflow locally. We will take the following typical ComfyUI Flux.1 workflow as an example to explain in detail (the network disk address at the end of the workflow article can be obtained). Related instructions: If ComfyUI is not the latest version, you need to update ComfyUI to the latest version first. 1. Download of the Flux.1 model...

Recently, I spent a week debugging and solving the problems encountered during the installation process, and finally completed the startup of stable-diffusion-webui and successfully generated pictures. I will make a note here and share it with you, hoping to help you avoid some pitfalls. Next, let's learn stable-difffusion-webui together. Preliminary preparation Hardware equipment Huawei Matebook 16s processor 13th Gen Intel(R) Core(TM) i9-13900H 2.6…