xiaolxl

| 版本 | 效果图 | | --- | --- | | GuoFeng4.2 | | | GuoFeng4.12.5D | | | GuoFeng4.0RealBeta | | 【civitai站地址：https://civitai.com/models/118009?modelVersionId=199325】 欢迎使用GuoFeng4模型 - 这是一个微调后的全能的SDXL模型系列，也可以说是对国人喜欢的画风微调过的模型，具有2.5D，CG，游戏，建模质感。基于SDXL1.0训练。因为SDXL的升级，它的泛化性大大增强，如果你愿意尝试你可以用这个模型画出许多有意思的东西，以及不限于2.5D的画面。 Welcome to the GuoFeng4 model - this is a fine-tuned and versatile SDXL model, which can also be said to be a fine-tuned model for the art style that Chinese people like. It has a 2.5D, CG, gaming, and modeling texture. Based on SDXL1.0 training. Due to the upgrade of SDXL, its generalization has been greatly enhanced. If you are willing to try, you can use this model to draw many interesting things, as well as not limited to 2.5D graphics. (经过测试国风4.1几乎不存在这个问题 - After testing, Guofeng 4.1 has almost no such problem) 国外源地址：https://github.com/ototadana/sd-face-editor.git 国内加速地址：https://jihulab.com/xiaolxlpub/sd-face-editor.git If you experience facial collapse during the full body image, it is recommended to delete the full body keyword or use the facial automatic repair plugin: Foreign source address: https://github.com/ototadana/sd-face-editor.git Domestic acceleration address: https://jihulab.com/xiaolxlpub/sd-face-editor.git Face Editor (or other facial editing plugins): enable

基于SDXL的国风4已发布！- GuoFeng4 based on SDXL has been released! : https://huggingface.co/xiaolxl/GuoFeng4XL 本人郑重声明：本模型禁止用于训练基于明星、公众人物肖像的风格模型训练，因为这会带来争议，对AI社区的发展造成不良的负面影响。 欢迎使用Gfstyle2模型 - 这是一个中国华丽古风风格模型，也可以说是一个古风游戏角色模型，具有2.5D的质感。第二代相对与第一代减少了上手难度，不需要固定的配置也能生成好看的图片。同时也改进了上一代脸崩坏的问题。 Welcome to Gf Style2 model - This is a Chinese gorgeous antique style model, which can also be said to be an antique game role model with a 2.5D texture. Compared with the first generation, the second generation reduces the difficulty of getting started and can generate beautiful pictures without fixed configuration. At the same time, it also improved the problem of face collapse of the previous generation. This is a series of models that will be updated in the future. 1. 将XXX.ckpt模型放入SD目录 - Put XXX.ckpt model into SD directory 2. 模型自带VAE如果你的程序无法加载请记住选择任意一个VAE文件，否则图形将为灰色 - The model comes with VAE. If your program cannot be loaded, please remember to select any VAE file, otherwise the drawing will be gray 简单：第二代上手更加简单，你只需要下方3个设置即可 - simple：The second generation is easier to use. You only need the following three settings: - The size of the picture should be at least 768, otherwise it will collapse - 图片大小至少768，不然会崩图 高级：如果您还想使图片尽可能更好，请尝试以下配置 - senior：If you also want to make the picture as better as possible, please try the following configuration - The size of the picture should be at least 768, otherwise it will collapse - 图片大小至少768，不然会崩图 - 如果想元素更丰富，可以添加下方关键词 - If you want to enrich the elements, you can add the following keywords (可在文件列表中找到原图，并放入WebUi查看关键词等信息) - (You can find the original image in the file list, and put WebUi to view keywords and other information)

通用工作流：https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow 自动大小通用工作流：https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora 幻象绘影取衣去人-TakeclothesKontextLoRA。Used for removing people from various types of images while retaining clothing. Trigger word: Remove the characters, keep the clothing General workflow:https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow Auto-size Universal Workflow:https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora

幻象绘影 万物国画风格-GuoHuaKontextLoRA的第一代版本，经过调整后更适合国画风格的Kontext风格转换。 触发词：Transform into a traditional Chinese painting style 通用工作流：https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow 自动大小通用工作流：https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora 幻象绘影 万物国画风格-GuoHuaKontextLoRA - The first generation version of GuoHuaKontextLoRA, adjusted to be more suitable for Guohua-style Kontext style conversion. Trigger word: Transform into a traditional Chinese painting style General workflow:https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow Auto-size Universal Workflow:https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora

幻象绘影万物折纸画风-OrigamiKontextLoRA。用于各类图片转换成折纸形态，此模型具有一般的泛化能力，适用于人物/动物等。 通用工作流：https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow 自动大小通用工作流：https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora 幻象绘影万物折纸画风-OrigamiKontextLoRA. Used for converting various types of images into origami forms, this model has general generalization capabilities and is suitable for characters/animals, etc. Weight: Recommended value 1.0. General workflow: https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow Automatic size general workflow: https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora

“幻象绘影万物毛毡 - FeltKontextLoRA” 是基于 Kontext - 微调的 LoRA，聚焦 “万物毛毡” 风格，能将角色/场景/物品等转化为可爱毛毡质感画风，并保留原作服饰、发型、场景结构等特征，为画面增添柔软、手工感，轻松打造独特毛毡风格创作，为创作者开启趣味毛毡艺术绘画新体验 。 通用工作流：https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow 自动大小通用工作流：https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora "幻象绘影万物毛毡 - FeltKontextLoRA" is a LoRA based on Kontext - fine-tuning, focusing on the "FeltKontext" style, capable of transforming characters/scenes/objects into a cute felt texture style while retaining the original clothing, hairstyles, scene structures, and other features, adding a soft, handmade touch to the images, easily creating unique felt-style creations, and opening up a fun new experience in felt art painting for creators. General workflow:https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow Auto-size Universal Workflow:https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora

幻象绘影万物玩偶-DollKontextLoRA。用于各类图片转换成玩偶形态，此模型具有很强的泛化能力，适用于物品/人物/动物/建筑等。 通用工作流：https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow 自动大小通用工作流：https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora 幻象绘影万物玩偶-DollKontextLoRA. Used for converting various types of images into doll forms, this model has strong generalization capabilities and is suitable for objects/characters/animals/buildings, etc. General workflow: https://civitai.com/models/1733176/fluxkontextdev-lora-general-workflow Automatic size general workflow: https://civitai.com/models/1733187/fluxkontextdev-lora-general-workflow-auto-size-fluxkontextdev-lora