AI Drawing

Today we introduce a Flux LORA model released by author @Slayer of Thousands: F.1-Rebel-Girl-Tattoo-Girl-Tattoo-Atmosphere-Beauty, which is a Flux LORA model featuring a rebel girl tattoo. It belongs to the character Lora, adding tattoos, and can be used as a full body tattoo or partial tattoo Flux Expenditure Figure. Model base trigger word: Tattoos; Recommended LORA weight: 0.8. As the LORA model straight out of the figure character is more monotonous, I used a mixture of the LORA model with the Ink Spectre net map, the specific weight to see the next section of the node legend. F.1-Rebel...

Previously, I shared with you a lot of loar models based on Flux. As the Flux ecosystem matures, large models based on Flux have gradually appeared. Today, I will share with you a large model trained on Flux: the real-life FluxAura large model. The official website does not provide any relevant introduction to this model, but the official website sample image effect removes the portrait look of the Flux base model, and the realistic portrait of the characters is very fresh, the overall picture quality is delicate, and it is full of artistic conception and beauty. Model download address (the network disk address at the end of the article can also be obtained) LiblibAI: https://www.…

Today I would like to share with you an ancient style loar model trained based on Flux: Ancient style girl Hanfu. The official website does not provide any relevant introduction to the model, only the usage instructions of the loar model. However, as the current Flux ecosystem becomes more complete, various domestic loar models based on Flux have also appeared on the stage. It must be said that the open source ecosystem is really beautiful. Model download address (the network disk address at the end of the article can also be obtained) LiblibAI: https://www.liblib.art/modelinfo /825ccb21c5ec4…

When many newbies first start learning AI drawing, they usually ask, "Is it free?" "Is the effect good?" "Everyone wants something that is both free and effective. It's human nature. But when it comes to AI drawing tools, you should look at what the big guys are using, not just listen to the advertisements. If a new product comes out that can compare to this or that, it's not that they are not good, but they are just out, and we need time to see them. Back to the field of AI drawing, let's not talk about who is good or bad, we should first look at adaptability. Adaptability means that we can customize many drawing styles, and we can adjust the size parameters. Whether it's a computer or a web page, you must also ensure the speed and quality...

When using the Stable Diffusion tool for drawing, we often encounter this kind of problems, mainly manifested in (1) after a lot of drawing, we finally draw a picture that we are satisfied with, but there are some flaws in some parts of the picture, and the overall satisfaction of the picture can only reach 95%. (2) after a lot of drawing, we finally draw a picture that we are very satisfied with, and we want to get multiple pictures with similar effects. If we regenerate them, since SD generates pictures randomly by default each time, the elements of the newly generated pictures may not be what we want. For the above two scenarios,…

I believe that when you use ComfyUI to write prompts, you often use translation software to translate our Chinese into English and then copy it to comfyui. This is very inconvenient. I recommend a Chinese prompt plug-in that does not use API and uses local deployment once and for all. The node used for node installation is also a very famous mixlab node. We install it in the manager or through the URL: https://github.com/shadowcz007/comfyui-mixlab-nodes Manual…

A friend asked me how to make a promotional cartoon character, with the following requirements: The cartoon character should be good-looking. Able to make a variety of expressions and movements. The company's abbreviation should be written on the helmet. It can be used for public account graphics, PPT, posters and other cartoon images for promotion. Solution Based on the friend's description of the needs, combined with my recent experience and learning results of AI graphics, the solution is as follows: Use AI Wenshengtu to generate a cartoon character. Based on the cartoon character, use AI to generate pictures with different expressions, movements, and postures. Based on the pictures of different movements and postures, add the company's abbreviation text to the helmet. Generate...

Today I will share with you a 2.5D model trained based on the Pony model: Speciosa 2.5D. Speciosa is a Latin word meaning "beautiful", so this model is good at generating semi-realistic cute Korean girls. The overall image quality of the pictures generated by this model is excellent, and the skin of the beauties is delicate. It can produce very high-quality pictures without the need for an amplification algorithm. On the official website, the author provides the training method of the model Steps #1: Js2Prony (v1.0) * 0.35 + DucHaiten-Pony-XL (pony-no-…

What are some useful AI tools for generating portraits in different styles? Upload a picture to generate your favorite style, preferably support custom styles. Solution Find the pictures you want to generate in different styles. Upload the original picture + reference style picture to generate new pictures. AI tool Jimeng, let's learn how to create portraits in different styles. Use Jimeng to generate portraits in different styles Enter the homepage of Jimeng's official website (jimeng.jianying.com) and click [Smart Canvas]. Enter the Smart Canvas page and name the project "Picture Style" here...

This tutorial is the latest SD ComfyUI Getting Started Guide in 2024, designed for beginners, and details how to build a controlNet workflow. Through step-by-step guidance, you can easily master the advanced features of SD ComfyUI and improve the accuracy and creativity of AI drawing. We use controlnet in WebUI through plug-ins, and plug-ins contain preprocessors and models. In comfyui, we build preprocessing and models separately. Next, let's see how to build it. First, we load our default...

This tutorial will show you how to use Midjourney's AI painting technology to create realistic macro photography effects. Through detailed steps and tips, learn how to capture the beauty of details and create amazing macro art. Spell: [SUBJECT], shot with a Nikon D850 DSLR and 105mm f/2.8G IF-ED VR Micro lens, photorealistic, ground-level shot, natura…

Do you have such old photos at home? They are full of childhood memories, but with the passage of time, they have become blurred. I want to restore old photos and restore their former glory. I went to Taobao and found that the price was 49 per photo. Wow, it's really expensive, but now it's the AI era, and it's a piece of cake for AI. Today, we will use AI to fix old photos in one click. 1. Use ComfyUI PC version to repair old photos ComfyUI is a graphics/…

Huiwa is an intelligent picture and copywriting platform that uses AI technology to provide users with commercial photo and grass-planting copywriting generation services. It is simple and easy to use, and can help users quickly create Xiaohongshu pictures, e-commerce product main pictures, cross-border e-commerce main pictures, etc. At the same time, it can also beautify pictures with one click, set the design with one click, change clothes with one click, remove watermarks with one click, and repair pictures in high definition. Huiwa function Commercial photo generation: Huiwa can generate pictures that meet commercial shooting standards based on the requirements and materials provided by users through AI technology, helping users to quickly create professional product main pictures. Grass-planting copywriting generation: Huiwa can generate pictures that meet commercial shooting standards based on the requirements and materials provided by users through AI technology, helping users to quickly create professional product main pictures. Grass-planting copywriting generation: Huiwa can generate pictures based on the requirements and materials provided by users...

Edraw is a one-stop office drawing tool and creative software. It is a product of Wondershare Technology, a listed company on the A-share market. Edraw AI is an intelligent drawing tool that integrates advanced artificial intelligence technology. It covers 210 types of drawings, including flowcharts, architecture diagrams, industrial design, and mixed text and graphics. It can do it all! It uses AI technology to provide users with an efficient and convenient drawing experience. Whether it is a flowchart, mind map, analysis chart or other graphics and charts, users can quickly generate the required graphics through simple commands or voice input. Edraw AI supports multi-platform use, including Windows, Mac…

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's practical scenario is to create exquisite mobile phone wallpapers, which may also be one of the fastest ways to realize AIGC. Although the theme of this article is mobile phone wallpapers, when adjusting the resolution aspect ratio of different ratios, it can be directly reused on mobile phones, computers, tablets, WeChat backgrounds and other screen device wallpapers. When expanding to other device wallpapers, please make sure to understand the corresponding wallpaper resolution requirements and other information, and at the same time, enlarge the higher resolution images in HD as required to obtain the maximum platform wallpaper experience. This article will use the latest Stable Diffusion model to create mobile phone wallpapers, resolution aspect ratio...

When I was a student, I read "Dream of Red Mansions". The characters in the novel have always existed in my mind, but they are rather vague. After studying AI for a while, I decided to visualize the characters in the classic novels to see what they look like in the eyes of AI? How about the finished film drawn by AI? The AI tool used this time: Alibaba's Tongyi Qianwen. https://www.1ai.net/6763.html Let's take a look at the effect first: Now, let's learn how to use Tongyi to generate photos of classic novel characters! How to use Tongyi to generate photos of classic novel characters? Before generating photos of novel characters, first confirm it...

Stable Diffusion, the flagship product of Stability AI, is a very powerful and open source AI text-to-image tool. Stable Diffusion is currently the most powerful open source AI painting model in the world. You only need to enter a prompt to create amazing paintings in seconds. A powerful open source AI drawing Stable Diffusion is a deep learning-based AI text-to-image generation model released in 2022. The model mainly…

Remini is a tool that uses AI technology to turn blurry photos into high-definition and repair old photos. This AI photo editing tool has been used by more than millions of people around the world. Remini uses advanced AI algorithms to analyze existing elements in photos and intelligently fill in missing image details, such as enhancing textures, correcting colors, and smoothing edges, so that the subjects and objects in the photos are clearer, thereby improving the image quality and clarity. This tool supports mobile APP and web version, and is suitable for repairing old family photos, improving the quality of images taken with low-resolution cameras, blurry pictures downloaded from the Internet, and repairing...

Recently, I have seen many reports on AI drawing-related scene applications, such as AI for children's picture books, AI for personal portraits, AI for posters, AI for PPT illustrations, AI for comics, etc. These scene productions all involve functions such as text-generated images, image-generated images, image expansion, and image modification. So, in addition to the foreign text-generated image AI applications such as Midjourney, Ideogram, and stable diffusion 3, what are the domestic text-generated image AI applications that may replace them? I have compiled a list of domestic AI drawing applications that may replace Midjourney for everyone to share...

Recently, a netizen asked me, although Stable Diffusion is open source, there are certain barriers to installation, and it requires a high computer configuration. Is there a free platform that does not require installation and can train its own model like Stable Diffusion? In the spirit of sharing everything, I finally found a platform that meets the requirements of netizens - Leonardo AI. This platform is based on Stable Diffusion and deeply integrates various aspects of Stable Diffusion...

The stable-diffusion-webui-forge tool is an AI mapping tool platform built on the Stable Diffusion WebUI (based on Gradio), with the goal of simplifying plugin development, optimizing resource management, and accelerating reasoning.The name Forge is inspired by "Minecraft Forge". The goal of this project is to become the Forge of SD WebUIs, and Forge promises to never make any changes to the Stable Diffusion WebU...

Deepai is an online AI image generation and editing website. Unlike other AI drawing tools, Deepai's page is very simple, with only a text description box and corresponding style selection. So if you want to generate beautiful AI images, you need to work hard on keywords. Deepai is an AI painting system based on artistic stylization technology. It is similar to Touch Station AI and can convert the pictures you provide into paintings that conform to a specific artistic style. In addition, Deepai has another feature. It provides users with an online art gallery where users can choose their favorite...

Visual Electric is an image generator built for the creative process with a library of stunning images and corresponding prompts to inspire. It can be used to develop ideas by iterating and experimenting with different styles and colors. This image generator opens up a whole new range of possibilities for the creative process, allowing users to visualize how their ideas will look in different styles. Its image generation interface is a whiteboard-like UI, where image generation and subsequent operations on the image are performed on a whiteboard, and you can clearly see all the images of your generation process, back at any time...