0xSoul 发表于 2023-6-7 20:49:36

[SD 1.5][Checkpoint]NeverEnding Dream (NED) baked vae

<h2>NeverEnding Dream (a.k.a. NED)</h2><h3>"This is a dream that you will never want to wake up from. A NeverEnding Dream."</h3><p><strong>Add a ❤️ to receive future updates. This took much time and effort, please be supportive </strong>?<br /><strong>Do you like what I do? Feel free to </strong><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/lykon"><strong>buy me a coffee</strong></a><strong> ☕</strong></p><p></p><p>It has been a while since I made a model. I've been making LoRA's non stop for the last month, but I felt like I needed something. A big problem with <a target="_blank" rel="ugc" href="https://civitai.com/models/4384">DreamShaper</a> is that it wasn't much compatibles with the LoRA's I was making. So I wanted to create a model that was "artistic" like DreamShaper but also able to use my LoRA's and booru tags for generating images. Plus I wanted this to be able to make <strong>good </strong>anime stuff out of the box, without needing an additional LoRA.</p><p>After a lot of tests and also fine tuning (plus LoRA merges) here is my newest model.</p><p>It came out a bit more realistic then I wanted, but I won't complain.</p><p><strong>What is this model great at?</strong></p><ul><li><p>Generating cosplay images</p></li><li><p>Generating anime pictures</p></li><li><p>Work accurately with character LoRA</p></li><li><p>Generating good looking people</p></li><li><p>Generating realistic animals</p></li><li><p>Generating images using booru-like tags</p></li></ul><p><strong>What is this model not too good at?</strong></p><ul><li><p>Generating pictures from complex sentences</p></li><li><p>Making fantasy/sci-fi paintings</p></li></ul><p>So this basically complements <a target="_blank" rel="ugc" href="https://civitai.com/models/4384">DreamShaper</a>, and it also doesn't include Dreamlike in the mix.</p><p></p><p>I hope you'll enjoy it!</p><p></p><p>Some tips:</p><ul><li><p>Select "auto" as vae if you're using the baked vae version.</p></li><li><p>Use highres fix or img2img to upscale the images after you get a preview. See the examples generation data for settings suggestions, I've tested various techniques.</p></li><li><p>If you're making images where the subject is far, remember you can inpaint eyes and faces selecting "only masked".</p></li><li><p>Stable Diffusion is great, have fun with it!</p></li></ul><p></p>
页: [1]
查看完整版本: [SD 1.5][Checkpoint]NeverEnding Dream (NED) baked vae