Notice:I published this model on LiblibAI on June 11, 2025.<a target="_blank" rel="ugc" href="https://www.liblib.art/modelinfo/53b863ceb57e492ea0aab84e5ffe62f2?from=personal_page&amp;versionUuid=a7d6c83690774eaeb5f7031388bd5e06">AWPainting CG.</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/1921087?modelVersionId=2195366">3D hyyer realisitc styels furry </a>They had the audacity to rename it and reupload it to plagiarize my work. Just look at the release dates.I demand that take this model down immediately. If refuse to do so, I will report this directly to the platform’s official team and have the model forcibly removed.AWPainting CGAWPainting CG is a version trained based on AWPainting IL. It is capable of generating highly realistic 3D-rendered effects and is well suited for anime characters, animals, still life, and architectural subjects.To achieve the best image generation quality, please follow the parameter settings below:<ul><li>Recommended sampler: Euler a</li><li>Steps: 30</li><li>CFG: Recommended 4.5</li><li>Recommended resolutions: 960×1440, 1024×1512</li><li>Upscaling algorithm: R-ESRGAN 4x+ Anime6B<ul><li>Denoising strength: 0.2–0.3</li></ul></li><li>Negative prompts: Refer to the example images</li><li>For medium to long shots: Enable Adetailer<ul><li>Redraw strength: 0.25–0.35</li></ul></li></ul>All content generated using this model is created and maintained by you. You must independently evaluate and use the generated content in compliance with applicable laws, regulations, and the terms of this service.Any intellectual property issues arising from the generated content are your sole responsibility. The author assumes no liability for any losses resulting therefrom.Unless otherwise required by law, without the author’s prior written consent, this model or its services may not be integrated into any third-party software or services, nor may you directly or indirectly, explicitly or implicitly, disclose to any third party the association between the generated content and this service.Without prior written authorization, non-individual users (including but not limited to enterprises and for-profit organizations) are prohibited from using this model for commercial purposes (including but not limited to text-to-image, image-to-image, or face swapping).If you violate this agreement and obtain commercial income as a result, or cause losses to the author, the author reserves the right to seek compensation.AWPainting 1.4This iteration focuses on enhancing scene diversity and visual impact, with improvements in picture details and color saturation compared to version 1.3. The variety of character faces has also increased. Using keywords such as "Top view" and "perspective composition" for controlling the camera can achieve better comprehension and visual effects compared to version 1.3.Recommended Resolutions: 512x768, 576x864, 640x960For low-resolution generation, you can use the "hire" HD repair feature to increase the resolution, with the recommended algorithm being ESRGAN_4x.AWPainting 1.4本次迭代主要在于提升场景多样性以及画面张力，画面细节以及色彩饱和度相较1.3均有一定提升，人物面部种类更加多样化。使用类似Top view, perspective composition的词汇控制镜头可以获得相较于1.3有更好的理解力和画面效果。推荐分辨率： 512*768, 576*864, 640*960在低分辨率生成下可使用hire高清修复增加分辨率，推荐算法ESRGAN_4x。————————————————————————————————————————AWPainting 1.3 What's New在1.2的基础上优化了角色面部的多样性，支持男、女及不同肤色，角色动作的类型以及协调性、优化了光照和整体的着色效果，对自然语言响应度良好（可使用GPT写自然语言的Prompts使用）。 翻译成英文AWPainting 1.3 has optimized the diversity of character faces based on version 1.2, supporting male, female, and different skin colors. It has improved the types of character actions and their coordination, optimized lighting and overall shading effects, and responds well to natural language (can use GPT to write natural language prompts for use).AWPainting 1.2 What's New在1.1的基础上提升了光照表现及画面表现的细腻程度，更有呼吸感的画面、更柔和的面部光照，对Prompts的响应略有提升，更多1.2与1.1测试结果可查看X:@dynamicwangsBuilding on 1.1, we offer more refined visuals, a more lifelike representation and gentler lighting. Also, enhanced response to PromptsAWPainting 1.1 What's New提高了画面光效和人物动作多样性，人物五官更加鲜明有辨识度，t2i直出精度有了一定程度的提升。搭配新出的LoRA DynamicKungfu可以很好的复现之前我一些作品的风格。The light effect of the picture and the diversity of character movements have been improved, the facial features of the characters are more distinct and recognizable, and the picture accuracy has been improved to a certain extent. With the new LoRA DynamicKungfu, it can reproduce the style of some of my previous works very well.—————————————————————————————————————————————AWPainting 1.0本模型适用性较广，插画、二次元及普遍的2D均可很好出图，比较有特色的是对niji风的复现，搭配LoRA nijiexpress以及不同LoRA的复用有很好的相性，直出图就会有很高的质量，如例图所示均为t2i直出+高清修复（无controlnet)。推荐搭配LoRA: Nijiexpress V1 V2，Xiaorenshu小人书，墨心moxin，沁彩This model has a wide range of applicability, illustrations, two-dimensional and general 2D can be well drawnWhat is more distinctive is the reappearance of the niji style. With LoRA nijiexpress and the multiplexing of different LoRAs, there is a good compatibility, and the direct image output will have high quality. As shown in the example images, they are all t2i direct output + HD Fix (no controlnet). Recommended collocation with LoRA: Nijiexpress V1 V2, Xiaorenshu villain book, Moxin moxin, Qincai Fisheyes, masterpiece, top quality, best quality, official art, beautiful and aesthetic, animation推荐Recommended Prompts：Fisheyes, masterpiece, top quality, best quality, official art, beautiful and aesthetic, animationNeg_Prompts: EasyNegativeV2, ng_deepnegative_v1_75t, (low_quality:1.4), (worst_quality:1.4), (badhandv4:1.1),collage, artist_name, signature, artist_logo, watermark免责声明 Disclaimer您基于本模型服务生成的文本内容由您自行维护并对其独立判断后使用，您需在遵守适用法律法规和本服务条款的条件下使用，基于本服务生成内容产生的任何知识产权问题由您自行处理，您需对生成内容负责，本人对由此造成的任何损失不负责任。除法律法规另有规定外，未经本人书面同意，不得将本模型服务集成在任何第三方软件或服务中，亦不得以任何直接间接、明示或暗示方式向其他任何第三方披露生成内容与本服务的关联性，您违反本条约给作者本人所造成的损失有权向您追偿。"You are responsible for maintaining and independently assessing the text content generated by this model service. You must use it in compliance with applicable laws and regulations and the terms of this service. Any intellectual property issues arising from content generated by this service are your responsibility. I am not responsible for any losses incurred as a result.Unless otherwise specified by laws and regulations, you may not integrate this model service into any third-party software or service without my written consent. You are also not allowed to disclose the association between the generated content and this service to any third party, directly or indirectly, in any manner, without my consent. If you violate this agreement, I have the right to seek compensation for any losses incurred."

AWPainting

awpainting_v14.safetensors

v1.4

CG_illustrious

v1.3

v1.2

v1.1

v1.0

AWpainting

AWPainting 1.4This iteration mainly focuses on enhancing scene diversity and picture tension. There has been a certain improvement in picture details and color saturation compared to 1.3, with a more diverse range of character facial types. Controlling the lens with vocabulary similar to Top view, perspective composition can lead to a better understanding and visual effect compared to 1.3.Recommended resolutions: 512*768, 576*864, 640*960For generating low-resolution images, you can use hire high-definition restoration to increase resolution, and the recommended algorithm is ESRGAN_4x. AWPainting 1.3Building on 1.2, this version improves the diversity of character facial features, supporting male, female, and various skin tones. It enhances the variety of character movements and coordination, optimizes lighting and overall shading effects, and has good natural language responsiveness (you can use GPT to write prompts for natural language). AWPainting 1.2Building on 1.1, this version enhances lighting and picture expression finesse, creating a more lifelike image and softer facial lighting. It has slightly improved responsiveness to prompts. For more test results comparing 1.2 and 1.1, please refer to X:@dynamicwangs. AWPainting 1.1It enhances image lighting effects and the variety of character movements, making facial features more distinct and recognizable. The t2i direct output accuracy has seen some improvement.Paired with the newly released LoRA DynamicKungfu, it can effectively reproduce the style of some of my previous works.————————————————————————————————————————————————————————AWPainting 1.0This model has a wide applicability, suitable for illustrations, 2D, and generally 2.5D images.Notably, it excels in reproducing the niji style, with excellent compatibility with LoRA nijiexpress and different LoRA combinations, resulting in high-quality direct output images, as shown in the example images, all t2i direct output + high-definition restoration (no controlnet).Recommended with LoRA: Nijiexpress V1 V2, Xiaorenshu, Moxin, QincaiRecommended Prompts: Fisheyes, masterpiece, top quality, best quality, official art, beautiful and aesthetic, animationNeg_Prompts: EasyNegativeV2, ng_deepnegative_v1_75t, (low_quality:1.4), (worst_quality:1.4), (badhandv4:1.1), collage, artist_name, signature, artist_logo, watermark Disclaimer:The text content generated by this model service is maintained and used by you based on your independent judgment. You must use it in compliance with applicable laws and regulations and the terms of this service. You are solely responsible for any intellectual property issues arising from the content generated by this service. You are responsible for the generated content, and I am not liable for any losses incurred. Except as otherwise provided by laws and regulations, without my written authorization, you may not integrate this model service into any third-party software or services, nor may you disclose the association between the generated content and this service to any third party in any direct or indirect, explicit, or implicit manner. Without my written consent, non-individual users (including but not limited to enterprises, profit-making organizations) may not use the model for commercial purposes (including but not limited to text-to-image, image-to-image, face swapping, etc.). Should you violate this provision, I reserve the right to seek compensation for any losses incurred.

AWPainting_1.4.safetensors

v1.5

Files with SHA256: cdf971b4a0d4b8b5c5d82f86d1ddfdaa7c0ba328dfb02dd63b4d55c1507844e9