LoRA

The first eight articles come down, and you've changed style from a zero-packed ComfyUI, a map, a modulation, a self-rescue. By this, let's fill out the last piece of the puzzle -- Lora. Why the last piece? That's all you've got in front of you. To paint a watercolor, to fix the face of an animated character, to keep your hands off the "Six Fingers," it's hard to do it in a stable way with a background and a hint. Hanging a Lora, a few hundred gigabytes of paper, right now "a skill pack." My first..

Today's recommended lora for you is: Toowindy Flux-Anime National 1.0Turbo lora download address: https://www.liblib.art/modelinfo/384899bdd78a409ea0fc36fcbfd96f6a (comfyui workflow preview) 1) Painting style tips The lora is mostly anime style, a few cases will appear partial realism or realistic style, can be prompted by the word Anime style (anime style) or Realis...

Today I will introduce a domestic Flux LORA model: Everything Adjustment | Flux Realism Super Realistic Bunny Girl. This is a bunny girl realistic LORA. Lora has trained many Chinese portrait materials. The picture effect is closer to Chinese realistic portraits, and the European and American portraits of the FLUX base model have been removed. The LORA model allows the image characters to wear sexy and cute bunny girl cos costumes, and match a variety of colors and costumes. The portraits have more delicate skin, more details, and the scene generalization has also been greatly improved. Recommended weight ratio: 1-1.5 Basic trigger words:, in order to distinguish…

Today I will share an operation to change a photo into anime style. It is mainly for personal notes. You can take a look if you need it. The model and lora address used will be given at the end of the article. Without further ado, let's get to the practical stuff. Tools The AI tool used this time is Stable Diffusion. The plug-ins involve [WD 1.4 Labeler] and [controlnet]. The model mainly uses the two-dimensional model and anime-style lora. Effect display Original picture Anime style conversion picture This kind of picture itself has a redrawn component, so it is impossible to be exactly the same. There will be some differences, but the overall...

Recently, ByteDance released a model called AnimateDiff-Lightning, which has impressive performance in video generation. It only takes 4-8 steps of reasoning to generate very good quality videos, which is undoubtedly a major technological breakthrough for the video production industry. Paper address: https://arxiv.org/html/2403.12706v1 The AnimateDiff-Lightning model also works very well with Contorlnet, which means that video conversion...

Today I would like to introduce to you a large model NightVision XL that sounds very cool from the name of the official website. Let's take a look at the name of the model on the homepage of the C website. (1) NightVision XL is a lightly trained base SDXL model, which was then further improved by the community LORA to reach its current level. The improved and biased generated realistic portrait output of NightVision XL can be posted as a ready-made stylized picture to social media! (2) NightVision XL has...

When you first come into contact with stable diffusion, you will hear a lot of professional terms, among which the LoRA model will definitely be mentioned. So what is the LoRA model? What does it do? The full name of the LoRA model is: Low-Rank Adaptation of Large Language Models. It can be understood as a plug-in in Stable-Diffusion. It is a model that only requires a small amount of data to train. When generating images, the LoRA model will be used in combination with the large model, from...