Sign In


Checkpoint Trained
Jan 19, 2024
Base Model
SD 1.5


1.3继续优化棚拍的质感及皮肤肌理,且增加了户外场景的优化,使得户外场景的直出兼具了1.2的写真感,以及更加有“网感”的拍摄构图及模特造型,1.3整体照片的色彩呈现一种兼具宽容度的灰度和柔和色彩感受的直出效果。 增加了更多的对于表情理解,可以做出微笑、大笑、痛苦、哭泣等面部表情,最好结合Adetailer,将权重设置到0.35-0.4为宜。 本模型非常适合制作摄影风格化的LoRA,可以达到非常真实的照片效果。 更多Prompts参考,可看直出例图。 采样推荐Restart, DPM++ 2M Karras

Version 1.3 continues to optimize the texture and skin details in studio photography, and has added enhancements for outdoor scenes. As a result, direct output from outdoor settings now combines the photogenic quality of version 1.2 with a more 'internet-trendy' composition and model styling. Overall, the photos in version 1.3 display colors that strike a balance between a tolerant grayscale and a gentle color feel.

The update includes improved understanding of facial expressions, allowing for more accurate depictions of smiles, laughter, pain, and crying. It is recommended to combine this with Adetailer, setting the weight between 0.35 to 0.4 for optimal results.

This model is particularly suitable for creating stylized photography LoRAs, achieving very realistic photo effects.

For more prompt references, see the direct output example images.

Sampling recommendation: Restart, DPM++ 2M Karras.


AWPortrait 1.2


AWPortait 1.2 has enhanced the simulation of lighting sources for both in-studio and outdoor photography. Additionally, it has refined the depiction of facial features, especially addressing abnormalities apparent in close-up shots. Utilizing the direct output from t2i in conjunction with ADetailer, users can achieve results remarkably akin to authentic photographs.This model is ideal for crafting a photographic style of LoRA. When using photos as the training dataset, the LoRA model can produce impressively lifelike results.


AWPortrait 1.1.1

1.1.1提升了对LoRA及面部的兼容性和泛用性,可兼容更多对脸部影响较大的LoRA,nwsj,Negfilm, instanfilm等都可以比较好兼容;使用ADetailer对面部单独叠加LoRA亦可提升直出效果。

AWPortrait 1.1.1 enhances the compatibility and versatility of LoRA and facial features. It is compatible with more LoRAs that have a significant impact on the face, such as nwsj, Negfilm, instanfilm, etc., and can achieve better compatibility. Additionally, using ADetailer to apply LoRA separately to the face can also improve the image output effect of t2i.


AWPortrait 1.1

AWPortrait1.1的创作过程其实是思考真实人像和AI生成影像视觉上的区别是什么的过程,希望AWPortrait能够在AI模拟人像摄影的真实度探索上再进一步;AI只是创作工具,只有每个人无可取代的想象力,才能开启属于我们独特的虚拟摄影之旅。 使用说明: 在t2i直出时,模拟影棚人像摄影的效果是最好的,如:Pure white background, Studio light, Studio 人像景别可选,如:Close-up , Upper body 全身full body 直出需要配合ADetailer插件控制脸部 可使用Prompts控制模特彩妆,如:Make up Portrait, pink eyeshadows, red lips等 表情可选,如: emotional face, smile, happy等 更多Prompts参考,可看直出例图。 采样推荐DPM++ 2M Karras 感谢第一批加入AWPlanet AWPioneer的会员: Amier, misotofu, yuruying的支持,1.1离不开你们的支持与帮助!

AWPortrait 1.1 The creation process of AWPortrait1.1 is actually a process of thinking about the visual difference between real portraits and synthography. I hope that AWPortrait can further explore the authenticity of AI-simulated portrait synthography; Now, you can embark a unique synthography journey. Instructions for use: t2i | the effect of simulating studio portrait photography is the best, such as: pure white background, studio lighting, studio Portrait scenes are optional, for example: close-up, upper body, whole body straight out needs to ADetailer plug-in. control model makeup, such as: make-up portrait, pink eyeshadow, red lips, etc. Face expression, such as: emotional face, smile, happy, etc. For more tips and references, see the example covers. Sampling Recommended DPM++ 2M Karras Thanks to the first batch of members who joined AWPlanet AWPioneer: Amier, misotofu, yuruying for their support, 1.1 radish for your support and help!

免责声明 Disclaimer


"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."