Sign In

Easy Results with Stable Diffusion/ Automatic1111

Easy Results with Stable Diffusion/ Automatic1111

In this article I will be giving you the tools I use to generate images. Below will include VAEs, Embeddings/ TIs, Extensions, and some other things I use to generate images. Feel free to use any of these and even recommend anything I may be missing in the comments. All example images were created using richyrichMix: https://civitai.com/models/105653/richyrichmix

VAE

A VAE will help dictate the colors that will be used when generating. If you are not using a VAE or a checkpoint without a VAE, the colors will look very bland/ less vibrant. See Examples:

SDXL

I currently recommend using this VAE: https://civitai.com/models/140686

This VAE doesn't change the look of generations but for lower end machines will help with generation times.

SD 1.5

I currently recommend using this VAE: https://civitai.com/models/276082

Here is an image without a VAE. See how boring it looks with it's washed out colors.

Here is the same generation but with the VAE. The image is much more vibrant and exciting to be looking at.

Upscaler

Upscalers help make the images a higher resolution when using Hires. fix, however they work good when upscaling images using the extras tab.

I currently use 4x-AnimeSharp: https://openmodeldb.info/models/4x-AnimeSharp

This upscaler works well with anime, although it also works with 2d/3d stuff too. If this one isn't what you are looking for there are a wide selection of upscalers here: https://openmodeldb.info/

Here is an image with the default upscaler enabled, latent. You will see that it is somewhat blurry almost like the image is a painting or there is too much exposure for a camera to handle.

Here is an image with 4x-AnimeSharp. You can see that it is much more crisp and sharp. It no longer looks "glossy".

Embeddings

I recommend Amazing Embeddings - fcNegative + fcPortrait suite: https://civitai.com/models/81575?modelVersionId=97691

There are other versions as well for specific things like portraits, however the one linked works for all stuff. This helps add more detail to your generations.

Here is an image without fcNegative. You can see there is a low amount of detail, especially in the background with certain things not connecting.

Here is the same seed but with fcNegative. You can tell that there is more detail in the image and no weird generations

Extensions

Adetailer

https://github.com/Bing-su/adetailer

This extension will auto in paint onto your generated image. This can fix things like faces, hands, eyes, even bodies if you have multiple. There are also other Adetailer models you can find that are trained specifically on other things. Try them out and see how you like them.

This is an image with no adetailer at a resolution of 512x768. I did this to help see the difference better.

Here is an image with adetailer with the same resolution. You will see the face looks better

Conclusion

Again these are what I am currently using to generate and if anyone has any recommendations, feel free to drop them down in the comments.

138

Comments