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: f1r3w4tch

Helper prompts: parody, style parody, realistic

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

• For a stronger effect, use the main trigger: f1r3w4tch. You can also weight it numerically or with parentheses - I usually do (((f1r3w4tch))).

• If the (weighted) main trigger is still not enough by itself, next try the helper prompts along with the main trigger. They can be weighted as well - I usually do them all together, like (((f1r3w4tch, parody, style parody, realistic))).

• The "realistic" trigger is not necessary to get the general style, but I feel it adds a slight boost of realism to get a little closer to the game's style, so I tend to use it more often than not. However, if you want a look that is a little more anime (or more like the general style of your chosen base model), then you can safely leave this trigger out!

• 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: Various styles should work (I usually use my own Illustrious merge or WAI)

• 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 vibe based on the video game Firewatch. Generally, you'll usually get warm, orange sunset lighting regardless of setting. If your setting is outdoors, stuff like the grass, trees, flowers, etc. will look kind of similar to how they are in the game. If your setting is indoors, it will usually have a rustic hardwood aesthetic. The LoRA mostly works OK, but there are a few issues I'll note below.

First, it can be a little fuzzy and lacking in fine details. Like, if you zoom in or check some fine details closely, they can appear kind of muddy or garbled. This is especially true with fingers. It's a manageable issue though, so I don't consider it a dealbreaker.

Second, I feel that outdoor shots look a lot better than indoor shots. I am pretty happy that the LoRA does have the ability to apply the style indoors as well, in the form of a rustic hardwood theme, but capturing the beauty of the outdoors is where this LoRA shines, just like the game it's based on.

Finally, it has trouble keeping track of objects that move behind other objects, if that makes any sense. Like if there is a bed behind the main character, the bed might not line up properly on each side of the character. This seems to be a general Illustrious issue in my experience, but this LoRA seems to make it even worse. So you may need to do some post-processing, or just hope for good seed RNG.

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 was intended to produce art in the style of the video game Firewatch. Like most of my style models, it won't give you exactly the art style from the source material, but it will provide a noticeable influence. In this case, the influence comes in the form of rustic nature/countryside vistas and warm orange sunset lighting, similar to the game.

Sadly, there are a few drawbacks to this LoRA:

1. It's not super stable when generating people, so be prepared to inpaint, especially hands. If you're just making landscapes with no people, then you generally shouldn't have any problems with stability.

2. The influence of the LoRA is significantly weaker if you generate something it wasn't trained on, namely indoor settings and non-nature outdoor settings. You may still get the sunset-style lighting though.

3. Sometimes your image will be in first-person view with a hand sticking out holding something (similar to what gameplay from Firewatch looks like when holding the walkie-talkie). If you don't want this, there are several fixes: try generating again with a new seed, inpaint, prompt it out, lower the weight of the LoRA, try a different base model, etc.

Here are some usage tips to help get the most out of the model:

1. A wide variety of base models will work - from anime to realistic - but the LoRA's performance will vary depending on the specific base model and your prompt. As always, experiment!

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

3. Upscale or use Hires. fix with a quality upscaler. If Hires. fix seems to be destroying your images, try lowering the denoising strength to 0.4 or 0.5.

Troubleshooting:

If you're having persistent problems with anatomy, 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!