I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: https://ko-fi.com/insult_to_ninjary

Your generosity helps me stay motivated to keep improving and to keep trying new things!

Trigger Words:

Main trigger: m0nv4l

Helper prompts: parody, style parody

Extra help: isometric

• The LoRA can potentially work with no triggers, but it may not be strong/consistent.

• For a stronger effect, use the main trigger: m0nv4l. You can also weight it numerically or with parentheses - I usually do (((m0nv4l))).

• If the (weighted) main trigger is still not enough by itself, next try one or both of the helper prompts along with the main trigger. They can be weighted as well - I usually do them all together, like (((m0nv4l, parody, style parody))).

• I didn't include it as an official trigger because it's usually not necessary and can sometimes overpower your prompt, but adding isometric to the other trigger words can sometimes help you get a stronger effect if you need it, and can really help with architecture-only (no character) images.

• Please note that the main trigger here is only for the Illustrious model - it won't work for the SD1.5 model. The helper prompts may or may not work for SD1.5 (I never tried them), but they are not necessary as the SD1.5 LoRA works just fine with no triggers!

At a Glance (Illustrious):

• Base model: Illustrated style (I use WAI-illustrious-SDXL)

• LoRA weight: 1 (but slowly go lower or higher if necessary)

• Suggested parameters: Euler a, Automatic, 30 steps, 832x1216/1216x832, CFG 5 (but feel free to experiment!)

• Hires. fix: 1.5x, use a quality upscaler (like 4x-UltraSharpV2), denoising strength 0.5 - 0.3

• Extra: use ADetailer to fix faces and/or hands if necessary

Illustrious Version Description:

This LoRA will give your images a Monument Valley vibe. Specifically, the general art style will become sort of soft and flat, and certain things like background elements and clothing/accessory details will take on a more geometric form. Sometimes this geometry is more subtle (like in the first showcase image), and sometimes it can be much stronger (like some of the other showcase images). It all depends on your prompt and seed. I ended up liking this LoRA way more than I thought I would, but it's still not without its faults, which I'll go over below.

First, it can struggle with the fine details of characters. For example, hands/fingers can sometimes be a mess, and smaller nuances of outfits, like earrings/necklaces/jewelry and designs/patterns can sometimes look a little muddy. Using ADetailer for faces and hands can be a big help.

Second, it also can have some problems with the fine details of backgrounds. It can sometimes make some really gorgeous geometric background elements, but when you zoom in, you'll notice the fine details are kind of muddy and not crisply defined. It's just kind of the nature of this model I guess. But luckily, I don't think most people will be zooming in super close to scrutinize, so images will still usually look ok when viewed normally.

Finally, you'll sometimes get a perspective that's too zoomed out, leaving you with either a really small character, or no character at all. If you don't want this, just try again on a different seed. This phenomenon is not too prevalent. However, if you like this isometric zoomed-out view, you can add "isometric" to your prompt, and this seems to give images much more of an architecture focus (vs. a character focus), and helps ensure the proper isometric viewing angle. I especially recommend using this extra trigger if you're not generating a character, and just want a higher chance of getting beautiful geometric scenery.

For more potentially relevant information, you can check out the original SD1.5 description immediately below. Below that, there's a troubleshooting section in case you're having any problems.

SD1.5 Version Description:

This LoRA will give your art geometric and angular backgrounds influenced from the Monument Valley games. Effects will be more subtle in character-focused images, but in images with no character, you'll really get a strong influence. The AI is not great at making precise straight lines and angles, especially when they're in the background and small, but you'll get the general aesthetic just fine, even if it looks a little sloppy.

Here are some tips if you're having trouble getting good images:

1. If you're frequently getting a small character, no character, and/or bad ???????, you can try gradually lowering the weight of the LoRA.

2. The LoRA seems to work with many base models, but it won't work with all of them. If you're not getting the style you want, try a different base model. It's a good chance to experiment with different combinations!

3. Use a VAE, especially if your chosen base model doesn't have one baked in!

4. Upscale or use Hires. fix with a quality upscaler.

Troubleshooting:

If you're having persistent problems with ???????, fine detail, and/or other jank, just try your best with all the usual fixes - different prompting (including negative prompt), try a different base model, use a different VAE, try different clip skip values, adjust the LoRA weight, use adetailer, inpaint, etc.

Outro:

If you make anything awesome, please consider posting them to the gallery! That goes for all of my models! I really like seeing what kind of stuff you all are able to make!

If you have any questions, feel free to ask! I will try my best to help! Also, if you have any ideas for future models, please don't hesitate to share them with me!