Inspired by this Don't starve lora for SD1.5 by @1to3fall5 and Don't starve style by @dimondexe. Special thanks to @xLordDonax for giving me detailed feedback about v1.2 and v1.3, @SulfurSniffer for feedback about v1.4. Also, a person who gave 1000 buzz (I don't see the name) some time ago. And everyone else who gave me a motivation.
The lore doesn't include names of original characters, so you won't get them in generations. (v1.5 has names of some characters, but using them on prompt didn't notice real effect.)
I recommend checking the LORA by @NeuralGL for Flux, instead of mine, which is based on game assets, but still looks pretty nice.
Description for V1.5 Pony : Put attention to the original characters have 4 fingers. To get 5, you may need to do inpainting. Strength 1.0-0.85 with additional character LORA, in some cases use '2D, CGI, photo, render in negative, 0.9-0.75 and lower for other cases if you want to keep the original style. Around 0.5 is fine for more detailed images but still maintain some influence of the style. 'chibi' I recommend using no stronger than 0.8. Comparing v1.5 and v1.4 for Pony, weight examples, 'chibi' all in one in the technical post. @SulfurSniffer is creator of Fate Spinner Lora.
Description for V1.4 Illustrious: 'dontstarvestyle' and 'blank eyes' are trigger words. The results I like the most with weights 0.7-0.9. Weights can be seen on the last picture. Lips might have incorrect shapes, especially at higher weights, so use addetailer or inpainting.
Description for V1.4 Pony: Strength '1.0' is usually fine for everything. Use 'dontstarvestyle', 'blank eyes', and 'muted colors' to make images closer to the original palette. The images in examples and in technical post used almost identical settings and prompts like in v1.3, so you could easily compare version v1.3 and v1.4. If you want the character more chibi, use 'solo' and 'chibi:0.7' and lower. Also, it works better with a strength of the Lora '1.0' and lower. Link on technical post. Usually, you don't need any specific negative, except when using LORAs with realistic characters and persons. Also, 'Liara t'soni' is trying to stay semi-realistic; my usual negative for it is '3d, photo, cgi, render'.
Description for V1.3 Pony: In general, everything similar like in v1.2. but you could use a bit lower wieghts. 'Muted colors' is not really a keyword, but use it if you want to get colors closer to original style, maybe even increase the weight of it. 'chibi' by part works like a keyword, but anyway just add similarity to style and proportion. By reason most of the dataset contain nature outside, it sometimes tries to put pot plants and stuff like that, so you could put it in negative if you want to avoid it. As usual, link on technical post to see examples of weights.
Description for V1.2 Pony: For usual usage, the weight ranges from 1.2-0.8. Without any description of the background, it will usually be simple or blank, so I recommend putting even a simple description like 'forest' or 'bedroom'. With the token 'chibi', it will look like a playable character. If you use it with other Lora of characters, I recommend increasing the weight between 1.2 to 1.6. Also, I recommend putting 'pupil' in negative if you want to get clear blank eyes. Some examples can be seen in my main post. The below is also an image with examples of weights. Link to post of weight examples.
Description for V1 Pony: ( I don't recommend using this version now; it's not stable enough.)
By default, with trigger words 'blank eyes, dontstarvestyle' generate 2.5D images. If you want to do it more flat and/or use it with another LoRA or character or person, add 'photo, render, 3d, cgi' in negative. Examples you could see in the technical post. The trigger 'blank eyes' works, but not like you expected; by fact, it works as a name for the style itself. It's possible to do another type of eyes, as the dataset has variants for it, but it's hard to get it, and actually, I like characters with blank eyes like Wendy. The LoRA isn't including names of game characters, so it won't generate specific ones from the Don't Starve series.
Description
Erased bad quality images from the dataset and added new, good ones. By default, it is now at the start more flat and closer to the original game (Don't Starve/Don't Starve Together) style. It's no longer necessary to use 'blank eyes' trigger words, but they are still recommended.
FAQ
Comments (9)
Well i still need to do some test and try different weights, buy I feel first one gives a little more cartoon look
Thank you for that information, it is because i used thist time more gameplay images and original art then from side artists. The main things is it better and gives more stable results or worse then first one.
@DemonAlone well using Gertrude lora the first one give better results more cartoony here you can notice a difference using exactly the same setting, i try different weight but still like the first pics i did more, on the second one the red hair girl since you can say is more original and not use any character lora results are ok and good actually i just feel looks a little bit more chibi on the first version
@xDoodlelandx You made some old and cool images, as well as some new ones. Do you have any opinion about the latest version or changes that are not very noticeable?
@DemonAlone the lates one works better, like a mix in between the previews ones, there are some characters that results looks so weird specially when you use the chibi prompt like for example Gertrude results , chibi version looks bad, but that also most be the character lora I asume, cause the red hair girl use chibi and works fine, but in general works good , i'll keep trying with other characters and see also haven experiment to much with weight
@xDoodlelandx I tried to get a kind of mix, not using the result (if used, degradation comes very easily) of them and made it more stable at the same time. The problem is the original artist changed style, and gameplay, art, and cinematic are too different to have one single point. Maybe if I did separate LORAs or made it activated by triggers, I could do better. I also saw a Lora for Flux, which looks really cool but only focuses on gameplay style. Well, maybe one day I'll know how to do a Lora better. Anyway, thank you again for your feedback.
@DemonAlone not gonna lie you never try the flux one , using flux takes a lot of buzz XD
but you did a good work on this one, wish i can more advice but since i never do a lora my self there is so much i still don't know
@xDoodlelandx , Thank you. I have tried Flux locally, in the FP8 and NF4 versions. I am too addicted to Pony, how it listens to prompts. Flux is now closer to the time of earlier SDXL. This is 'natural language' in my opinion makes prompts more difficult to use and less predictable, especially for me as a low-level English speaker. Using just tokens in Flux gets worse results. Censorship is less, of course, than SD3, but still much of it.
lovely!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.