Prompt

Introduction to AWPortraitCN Today we introduce a Flux LORA model focusing on the appearance and features of Chinese people: AWPortraitCN. The model is specifically optimized for the appearance and aesthetic features of Chinese people. The model is trained using several types of portrait images, including indoor and outdoor portraits, fashion and studio photos, etc. AWPortraitCN has strong generalization ability. Compared to the original version, AWPortraitCN is more detailed and realistic in skin texture. Suggested Trigger word: None, Suggested LoRA weight: 0.9-1. LIB...

White people do not write a line of code, you can also use the AI programming tools Cursor installation and use tutorials After installing the software, we open, the interface is as follows, do not do to understand, directly on the hands of the beginning of the actual operation. Then we enter the shortcut key ctrl + i, pop-up dialog box, here you can choose the model, we certainly choose Cluade model. Next, then enter the big brother's god Prompt, called Thinking Claude, very long, github Original article address: https://github.com/richards199999/...

In today's AI prevailing development trend, there may be many creators will be attracted by these AI tools with magical ability, and then try to learn and utilize them, these AI tools with different abilities can really bring unprecedented energy and efficiency to our work and creation. However, if a white person who has no contact with AI directly starts, there is a great probability that he will be overwhelmed by the step of writing prompts, and find that no matter how he tries to debug it, he just can't produce the same high-quality works as those of the network gods. In fact, the distance between you and the gods is only a good cue word. Of course, writing...

Prompt Genie is an easy-to-use prompt generator. By providing basic requirements, you can automatically generate detailed and professional prompts for all kinds of generative AI tools such as ChatGPT, thus helping users to get better results.Prompt Genie is supported as a Chrome plugin, which generates prompts directly in ChatGPT's input box, which is very convenient and fast. Prompt Genie Features Super Prompt Generation: Convert basic prompts into more effective and powerful Ch...

Public Prompts is a free prompts repository created by individuals to provide pre-trained AI mapping models and prompts for prompt generation on a website, the prompts provided on the page are completely free and can be copied by clicking on the page.The prompts provided by Public Prompts include not only the prompts for a specific kind of image, but also the prompts for different model styles. Public Prompts provides prompts not only for a specific type of image, but also for different model styles. Public Prompts provides prompts not only for a specific type of image, but also for different model styles, making it ideal for beginners. Public Prompts features Rich model library: Fine-Tuned Model, Flexible D...

Snack Prompt is a library of AI prompts covering both text and drawing categories, Snack Prompt's prompts are uploaded and rated by users, the writing prompt templates are suitable for ChatGPT, Gemini and various AI writing tools, and the drawing prompt templates are suitable for Dall-E, Midjourney and various AI drawing tools, users can switch search categories and filter by specific work categories using time or heat sorting, or directly type keywords to search precisely. Painting tools, users can switch search categories and filter according to specific categories of works using time or heat sorting, you can also directly type in keywords to conduct an accurate search, not...

Do you have such a feeling, sometimes see an article, although the words look quite like that. But you always feel that there is something strange about it, and it feels mechanical, stiff and lacks human touch when you read it? Yes, this is the legendary "AI flavor"! AI writing can greatly enhance the efficiency of creation, but AI writing always has a AI flavor, so how to remove the AI flavor? On November 8 last year, the Government of Singapore Technology Agency (GovTech) organized the first GPT-4 Prompt Engineering (Prompt Engineering) Competition...

Today, we recommend a Flux-based training lora model of Chinese style illustration:F.1 Chinese Style Illustration-Four Seasons Palace Shadow. This lora model of Chinese style illustration has a delicate drawing style, good recognition of ancient Chinese architectural (palace, etc.) elements, and can be drawn in all seasons. It is very easy to create a beautiful atmosphere of the national style illustration pictures. Model download address (the end of the article net disk address can also be obtained) LiblibAI: https://www.liblib.art/modelinfo/d0314e9e5cd04d8aa0805cdf2a9d9...

Flux is a quality base model, but Flux still owns the common problems of other open source models in Chinese female portraits. Today we share with you a female Lora model trained on Flux base model - Chumhum FLUX | INS Filter. The Lora model for the portrait to add Ins style filters at the same time the ultimate optimization of the performance of Chinese women out of the picture, very oriental beauty, out of the picture of the beauty of the portrait of pure sweet. The model is trained with the help of WellCap using completely artificial natural language manual marking, cue word comprehension is very strong, based on Flux.Dev training...

Today I would like to share with you a SDXL-based Lora model for clothing accessories classification background: classification background XUER. This Lora model was launched by the model training master Xuer in August. Currently, the V1 version is launched. The author claims that the image accuracy has not reached expectations, and the splitting is still a little different. It is being improved and optimized. I believe that a better version will be launched soon. However, even if the current version is not perfect, the effect is still very amazing, except for the inaccurate processing of clothing combination elements. Model download address (the network disk address at the end of the article can also be obtained) LiblibAI: https://ww…

Do you feel that your answers are not accurate enough when using ChatGPT? In fact, the problem is probably in the writing of prompts! How to provide ChatGPT with clear and effective prompts is the key to making it your right-hand man. In this article, I will share some practical tips to teach you how to write efficient ChatGPT prompts so that its answers are more in line with your needs and help you get more results with less effort at work. What is a ChatGPT prompt? ChatGPT prompts are the main way for users to interact with ChatGPT…

Regarding line drawing transfer, I have shared with you two ways to achieve text-generated images and image-generated images. Stable Diffusion [Application] [Line Drawing Transfer]: One minute to achieve image transfer and line drawing Stable Diffusion [Application] [Line Drawing Transfer]: One minute to achieve image transfer and line drawing without loar The previous two methods did not perform well in achieving line drawing transfer of architectural images. Today, I will share my personal practice specifically for line drawing transfer of architectural images. If you have good ideas for implementation, you can leave a message or add WeChat to communicate privately…

The most common questions I’ve been asked by readers are: “Do you have any prompts to remove the AI flavor?” “How to make AI-generated content more human?” Today I’m going to share a super practical universal prompt to remove the AI flavor! First of all, we need to figure out why AI-generated content always has a “machine flavor”? There are actually several main reasons: 1. Too perfect grammar and structure 2. Lack of personalized expression 3. Emotional expression…

Today I will share with you a two-dimensional model trained based on the Pony model: two-dimensional illustration. There are 4 different branch versions of this model. 1.5 version: loar model, recommended base model niji-anime two-dimensional 4.5. xl version: SDXL model version mix version: light and shadow weakened, reduce the SDXL version of the warm tone and a sense of overexposure. Pony version: based on the version trained by Pony Diffusion v6. The author's introduction to this model on the Liblib official website is relatively short, mainly related parameter recommended settings. Personal experience...

Prompt word [SUBJECT], crisp neo-pop illustration, pencil sketch on old paper [Subject], fresh neo-pop illustration, pencil sketch on old paper Parameter settings Large model: RealVisXL V4.0 Lightning Sampler: DPM++ SDE Karras Sampling iterations: 5 CFG: 2 Reverse prompt word: (octane render, render, …

Today I would like to share with you a large model that can draw the second dimension style of the Midjourney tool: niji-Anime Second Dimension Enhanced Edition. This model is a large model trained based on SD1.5. It is called the enhanced version because the author has launched a similar large model: niji-Anime Second Dimension. Niji-Anime Second Dimension access address: https://www.liblib.art/modelinfo/a9a92acbcd2f4033856db53ede728f51 to ensure the uniformity of the output style. In addition…

Today, I will introduce a high-quality real-life portrait model: Zeekr Photography PRO-V8 Pure Texture. This is a high-quality portrait photography model with extremely strong pure texture, realistic and delicate skin texture, soft skin color and clear three-dimensional texture. This model is an SD1.5 model with excellent LORA model compatibility. Zeekr Photography PRO-V8 Pure Texture Model includes a pairing of exclusive camera lens prompts TAG recommendation: • Night and low-light photography (Nikon AF-S NIKKOR 35mm f/1.4G): This 35mm lens…

Introduction to the Ultimate Texture DgirlV5 Model Today, we introduce a super textured real person model: D series - ultimate texture - DgirlV5. This is an optimized realistic model that the author has continuously optimized in pursuit of character texture, even down to the hair details. This model is a drawing model trained based on the SD1.5 model. The current open version is the latest version V5.1, which focuses on enhancing the details and correcting the overall reddish color problem of the drawing before the V5 version. This is a large model that can directly produce high-quality and beautiful pictures according to a simple prompt word Prompt…

This time, I will introduce how to produce images of fashion shows by setting camera and lens parameters and determining the aperture value. First, start by deciding the basic settings. Basic settings 1. Subject: Fashion show 2. Camera: Canon EOS R5 (high image quality, high performance, suitable for shooting fashion shows, with high-speed continuous shooting performance to capture dynamic models) 3. Lens and aperture value: • 24-70mm f/2.8 (suitable for shooting the entire fashion show) • 70-200mm f/2.8 (telephoto zoom lens, suitable for shooting close-ups of models) • 85mm f/1.4 (fixed focus…

Since ChatGPT launched in November 2022, tens of billions of questions have been asked of ChatGPT. Many of those people are using it at work, alongside many other AI tools. Chatbots become more valuable if you use ChatGPT prompts to inspire their responses. ChatGPT prompts are designed to generate specific, helpful responses from AI tools. Prompts are particularly good at helping you complete tasks, and therefore are closely related to work scenarios. This article will walk you through the different use cases of ChatGPT in a variety of…

Is it true that longer prompts are better? According to Midjourney's official documentation, not necessarily: Prompts can be very simple. Single words (or even an emoji!) will produce an image. Very short prompts will rely heavily on Midjourney's default style, so…

In the chapter Stock Photo, we introduced the img2img method. In addition to solving the problems of Stock Photo, this method is also suitable for many scenarios. This chapter will focus on the prompt of the avatar generated by this method. And starting from this chapter, we will gradually enrich our prompt structure to make it more complete. Notes Before introducing the application of img2img, I would like to emphasize: Do not upload your own photos in the Discord Midjourney public group! This way you...

Summary Midjourney Application Scenario 1: Stock Photo Midjourney Application Scenario 2: How to use AI to generate brand logos? Midjourney Application Scenario 3: App and Badge Logos How to write prompts? Through the previous learning, you should have copied a few pictures more or less. If not, I suggest you practice more, because learning from books is always shallow. Let's summarize what we have learned: The core of writing prompts is to "describe the picture you want clearly". The more detailed the generated picture is, the better it is.

The Logo chapter is quite long, so it is divided into two chapters. App Logo Actually, the App Logo can use the brand logo mentioned in the previous chapter, and add a rectangular border. It can be completed in a few steps with Figma 😂, but if you really don’t want to use Figma, you can also use Midjourney to generate it. Why not take a look at the apps on your phone and think about how to write the App Logo Prompt? I used the case in the previous chapter and wrote two prompts. The output is as follows: Close…