> For the complete documentation index, see [llms.txt](https://artroomai.gitbook.io/tutorials/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://artroomai.gitbook.io/tutorials/resources/settings-tutorials/image-scale.md).

# Image Scale

Most models are trained on images either 512x512 or 768x768 so they are often best at making images at that size. Smaller sizes often look very pixelated. 

<figure><img src="https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2FgaMsiLzCoxszEX2Nk0z8%2F00650_woman_wearing_a_sweater_seed_6.png?alt=media&amp;token=f612cbcb-f3aa-45ea-a958-0f196c172e4c" alt=""><figcaption><p>Woman wearing a sweater at 256x256</p></figcaption></figure>

While larger images can have "artifacts" appear. These artifacts are often doubling the amount of people, or alternatively, giving double heads/torsos.

<figure><img src="https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2Fzt9RsFkIR9BIapXTrmfq%2F00807_portrait_shot_smiling_man_dynamic_lighting_seed_1570381835.png?alt=media&amp;token=7e3fbe53-59f3-456d-aeb6-fbab835b7a98" alt=""><figcaption><p>large image Artifacts</p></figcaption></figure>

<figure><img src="https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2F8hHMlpcaZu3cHs36K8Zm%2Fscale2.png?alt=media&amp;token=8b47386b-9299-4313-887a-dcd7b0218993" alt=""><figcaption><p>Examples of high scale duplication</p></figcaption></figure>

Modern models seem to have a much lower chance of these artifacts appearing.&#x20;

If you intend to make images larger than 1024x1024 it is recommended to turn on "Highres Fix" in settings.&#x20;

![](https://1638460590-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsrvmkNlt2cT7tVvQkddJ%2Fuploads%2FwQOAeFWM4cxpZAtwcmZY%2Fimage.png?alt=media\&token=a01f31cd-04d1-4b2e-bf6f-46d16db27cf5)

Please note that for inpainting to work properly the "location" you work on is still under these constraints. So if you generated an image at 768x768 with a character in the distance, and it´s face just being 30x30 pixels, then inpainting is not going to work. Its best to upscale the image and then inpaint.&#x20;