Stable Diffusion

Today and share with you 9 kinds of characters commonly used lens keywords, I hope to help you in the creation of more perspective choices, these tips apply to Midjourney, Flux, SDXL and so on a variety of models The following I'll take Flux as an example to show the effect of various perspectives 1, full body shot Full body shot to show the whole body of the character's modeling. Such as clothing, posture or the relationship between the character and the environment. Like you stand in the city street, a friend to help you take a picture from head to toe. For example, a full body shot of a young college girl standing on the street waving her hand. ......

Today, I will introduce a domestic Flux LORA model: New World E-commerce Supermodel FLUX.1-SuperModel Oriental Aesthetics. This is a LORA model focusing on the Oriental aesthetics of e-commerce supermodels. It is a Flux LORA model completed through the Liblib.Art FLUX online trainer. Using the LORA model can add more Chinese elements and character faces, as well as clothing, and no longer a small number of monotonous faces at the bottom of Flux. The author noted that this model is the first free model, online drawing is free, and commercial authorization is automatically obtained. The author pointed out that with the A…...

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…...

How to use the Stable Diffusion tool has always been one of the questions that many friends often ask. Today, let's talk about how to experience the AI painting tool Stable Diffusion. In general, there are three main ways to experience the Stable Diffusion tool. Method 1: Local computer installation and deployment (computer configuration requirements) Method 2: Paid cloud platform (charged by traffic or time) Method 3: Free cloud platform (free, but limited functions) Related instructions, this article is mainly for SD …...

Previously, I shared with you the relevant production methods of line drawing transfer. I will continue to share new practices about line drawing transfer in the future. Today, we will start to share another kind of picture transfer: illustration transfer. 1. Production method of picture to illustration [Step 1]: Selection of large model Here we recommend: Vientiane Melting Furnace | Anything V5/V3. Model download address (you can also get the network disk address at the end of the article) LiblibAI: https://www.liblib.art/modelinfo/1f26c86ea6a8442c856…...

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 the help of 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 implementation ideas, you can leave a message or add WeChat to communicate privately…...

In the previous article, I shared with you how to achieve the Wenshengtu conversion of image line drawings. Stable Diffusion [Application] [Line Drawing Conversion]: One minute to achieve image conversion to line drawings Image line drawing conversion can also be achieved using the method of picture generation. Let's first look at the effect of using the picture generation method to achieve the image conversion to line drawings. 1. How to make a picture to line drawing [Step 1] Upload a white background image of the picture generation image Here we use Meitu Xiuxiu to make a pure white background image. Upload this white background image in the picture generation function menu. [Step 2]: The choice of large model is recommended here...

Today we start sharing the series of image-to-drawing in the application chapter. Image-to-drawing has many different application scenarios, such as image-to-line drawing, image-to-illustration, image-to-comic, etc. This is also one of the more common application directions of AI painting in actual scenes. Here we start with the production method of image-to-line drawing. 1. Production method of image-to-line drawing [Step 1]: Selection of large model Here we recommend: ReVAnimated, version v122. Model download address (the network disk address at the end of the article can also be obtained) LiblibAI: https://www.libl…...

When using the Stable Diffusion tool for drawing, we often encounter this kind of problem, which mainly manifests 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. 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,…...

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-…...

Today I would like to recommend a very good general-purpose large model based on SDXL: SDVN7-NijiStyleXL. The drawing style of this model is very similar to the Midjourney style. The author combines animation, sketching, realism and other styles to create many great styles. We can use various artist style combinations supported by SDXL. The artist styles supported by SDXL can be found on the website: https://rikkar69.github.io/SDXL-artist-study/. This large model is similar to the realistic style…...

In the hot summer, cool fruits are the most comfortable and cozy choice. Today I recommend a LORA model based on SD1.5: KK-Watery Fruit Photography. This model is a fruit photography model, which brings a watery special effect when the fruit falls, bringing a cool visual experience to the hot summer. The latest version of the model is V2.0. Some training materials have been added to the V1.0 version, and the number of learning times and optimizers have been adjusted. However, after actual testing, I personally feel that the effect of V1.0 is better. The author gives the recommended parameter settings on the official website: • …...