AI Painting Tutorial

The already powerful Flux has announced a batch of official tools covering commonly used drawing features, making it comparable to (or even surpassing) closed source tools. First you need to have the latest version of Flux installed in ComfyUI, see here: FLUX Testing and Installation Below is an itemized list of methods used in ComfyUI and the download paths for the models/workflows. First, Flux repainting (Fill Inpainting) Need to download the model flux1-fill-dev.safetensors: https://hug...

Flux has become very popular recently, and portraits of people are more realistic and delicate. Can you tell that these pictures are generated by AI? You can even precisely control the generated text, such as writing on your hands and paper: I am not real. Whether it is a single person or multiple people, it is difficult to see flaws in facial lighting, skin texture, and hair. And such realistic pictures can be easily generated using Flux: Today, I will teach you how to use Flux. First experience with Flux Former Stability AI core member Robin Rom…

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…

In recent articles, we have introduced a lot about Flux model, but this is a large model with 2B model parameters and a weight of about 23.8G. Not only is it large in size, but the biggest problem is that it requires a larger graphics card memory. The dev version is close to 24G, and it is also difficult (slow) to run multiple images on RTX4090. This has stumped most students for further experience. Today's topic is to introduce a ComfyUI plug-in: BizyAir. BizyAir is a collection of ComfyUI nodes that can help users overcome the limitations of local environment and hardware,...

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 (you can also get the network disk address at the end of the article) LiblibAI: https://www.libl…

Today I would like to share with you a large model based on SD1.5 with a camera theme: Dreams and bubbles. This version mainly includes the following improvements: (1) The character poses and picture composition are richer, more dynamic, and more visually attractive; (2) The character composition and natural language understanding are both ideal. Adding (8k, RAW photo, best quality, masterpiece:1.2,) to the prompt words will greatly improve the output effect (3) Recommended parameter settings sampler...

Today, I will introduce you to a SDXL-ControlNet, universal control model: Anytest. It is very simple to operate and does not require a preprocessor. You can use it directly. The basic functions include generating images based on line drawings and redrawing pictures in different styles. There is nothing much to say about this. Anytest has several interesting uses. It can also generate good quality pictures for compositions with unclear outlines. Not only that, Anytest can also help you improve incomplete sketches, including secondary creation on pictures. You may not feel much about this, so let's go straight to it...

Cue word 3 panel photography of the same [woman/man] character in different ages, from left to right in order representing the ages between [girl/boy], middle age and old [woman/man], each character age wea...