
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!
This LoRA will give you an aesthetic based on the Tengami video game, which has a Japanese paper, watercolor, pop-up book kind of style.
Because this LoRA works pretty stably and has a very stylized aesthetic, as long as your initial gen is good, you probably won't need to do much post-processing besides maybe some minor inpainting or upscaling (depending on how much of a perfectionist you are, lol).
The LoRA will have some trouble generating characters at the default LoRA weight (1) with certain base models. If that happens to you, just lower the weight of the LoRA a bit and it should get better. I find that AniDosMix and Hassaku work pretty reliably as base models, but the LoRA will work to varying degrees with most base models, so you can get some really neat results by experimenting!
Here are some other standard usage tips:
1. Use a VAE, especially if your chosen base model doesn't have one baked in! It really seems to help with getting better colors and anatomy.
2. Upscale or use Hires. fix with a quality upscaler. I typically use SwinIR_4x because I've been too lazy to research and test others, lol. But mainly just don't use the Latent one.
If you make anything awesome, please consider posting them to the gallery! That goes for all of my LoRAs! 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 LoRAs, please don't hesitate to share them with me!
描述:
The OG version
训练词语:
名称: Tengami.safetensors
大小 (KB): 36978
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success