Stable Diffusion WebUI 是AUTOMATIC1111为 Stable Diffusion 开发的一套 UI 操作界面,大幅度降低了 Stable Diffusion 的使用门槛,让用户甚至可以不用写代码就能够实现模型的推理、训练等操作。 传送门:Git 启动器是什么? 启动器是秋葉 aaaki团推开发的用来启动 Stable Diffusion WebUI 的启动工具。不仅能够实现一键启...
https://github.com/CompVis/stable-diffusion/blob/main/Stable_Diffusion_v1_Model_Card.md The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, ...
Stable Diffusion belongs to a class of deep learning models calleddiffusion models. They are generative models, meaning they are designed to generate new data similar to what they have seen in training. In the case of Stable Diffusion, the data are images.稳定扩散属于一类称为扩散模型的深度学习...
与Textual Inversion 让梯度仅作用于词 embedding 相比,HyperNetworks 是让梯度作用于模型的 Diffusion 过程。他在 Diffusion 过程中的每一步都通过一个额外的小网络来调整去噪过程的结果。 准确的说,是作用在 Diffusion 的 Attention 部分,通过额外的小网络,把 key 和 query 进行变换,从而影响整个 diffusion 过程。
作者:corey 随着 stable-diffusion 的开源,让更多人有机会直接参与到 AI 绘画的创作中,相关的教程也如雨后春笋般的出现。可是目前我看到的教程同质性较高,通常只能称作为"使用流程讲解",但是通常没有对其原理和逻辑进行深入说明。所以本文的目的,是用尽可能少的废话
Left: Original images. Right: After face restoration. It’s well-known in the AI artist community that Stable Diffusion is not good at generating faces. Very often, the faces generated have artifacts. We often use image AI models that are trained for restoring faces, for example,CodeFormer,...
A method to fine tune weights for CLIP and Unet, the language model and the actual image de-noiser used by Stable Diffusion, generously donated to the world by our friends at Novel AI in autumn 2022. Works in the same way as Lora except for sharing weights for some layers. Multiplier ca...
一篇绝对值得躺在你收藏夹里的 Stable-Diffusion Tutorial 作者:coreyzhong,腾讯IEG应用研究员 随着stable-diffusion的开源,让更多人有机会直接参与到AI绘画的创作中,相关的教程也如雨后春笋般的出现。可是目前我看到的教程同质性较高,通常只能称作为"使用流程讲解",但是通常没有对其原理和逻辑进行深入说明。
, we showed how to use Dreambooth Stable Diffusion to create a replicable baseline concept model to better synthesize either an object or style corresponding to the subject of the inputted images, effectively fine-tuning the model. Other attempts to fine-tune Stable Diffusion involved porting the ...
Image count: You can generate anywhere between one and ten images for each prompt. Under Advanced, you get four other options: Prompt strength: This controls how strongly Stable Diffusion weights your prompt when it's generating images. It's a number between 1 and 30 (the default appears ...