RDBT | MOSS
Finetuned LoRA from a personal all-in-one dataset, mainly for digital art and drawings, focusing on lighting, textures. Covered from wallpaper level digital art, to 5-min sketch
LoRA is trained against MOSS base (not sft). Cover images are also from MOSS base. It works on SFT, but you might need to lower the strength.
Dataset contains ~2k images, handpicked by professional amateur artists. The criteria for evaluation are not visual appeal, but the drawing technique and the level of completion.
There is no trigger words or style tags. All images are captioned by LLM. I'm too lazy to classify them. (Most of the style can't be classified in just few words tbh. It's hard to describe art.). So I used high caption drop rate hoping the model can guide itself from it's high noise steps.
Still testing. Styles seem to be messed up all together. E.g. "painting". I might need to change the way to caption, or just train dedicated LoRAs.
FAQs
Okay, but you still haven't mentioned what LoRA can actually do
AI only mimics the training dataset (unless RL, that's different topic). So there is no such thing called "LoRA functionality". If you really want a straight answer:
You can use it as a "regulator/stabilizer/detailer/whatever" LoRA with strength (0.2~0.5). It might alleviate the overfitting from other style LoRAs.
Or higher strength if you want some spicy visual effects. (I use it at full strength with my other style LoRAs)
Versions:
v0.1: This is a test run.
Sharing merges using this model is not allowed. This "restriction" won't affect anyone. It's only aimed at those who steal others' models to sell.
Description
FAQ
Comments (12)
style loras seem to perform better in combination with Lodestone's 8step dmd lora (just use a cfg of 2 or higher though and negative prompts)
This is promising, boss. Unlike the other general purpose, larger models, this is one seems to have actually been trained on the dark arts of the booru bible. Besides your usual magic on stabilizing, I'm hoping you can get it to match Anima or IL when it comes to style fidelity. It already seems to have some knowledge there, so maybe it just needs a little nudge.
the authors seem to be working on training a model specifically for anime
I'm more confident with Moss as alternative to Anima (replacing it or not would be differebt matter) because it has Booru tags training. Krea 2 while very good for realistic and general digital art, it is very sucks at interpreting otherwise very common booru tag. It can't even done panties/bikini aside properly!
I thought it could be an Anima replacement... but its not. It dont knows a lot of "not so popular" Anime Characters which Anima can handle without any problems. And its not like its only a few Characters...there are a lot missing.
@scarlizz Yes, and I don't think this specific model will replace Anima when it comes to character knowledge (maybe the anime-specific one the devs mentioned could). But it's still huge to have a general purpose model with all the knowledge this one does. It's unheard of, as far as I know, since even the "uncensored" ones are only trained on very restricted datasets and concepts.
moss for base style/background and qwen 2.1 for editing.
Model doesn't have to remember thousands of characters if it knows how to transfer the character from a reference sheet to the background. And that's what the editing model can do.
I'm really hoping they release an anime (editing) model good at anime style/character transfer. Then we'll never need style/character LoRA.
@scarlizz just temporarily, since it's not a model especially foe anime
Just heard about this Model and Search for RDBT Moss and to no surprise, the Goat delivered
你好，我很喜欢你的作品！想请问你，现在在Krea 2、Qwen Image 2.1 等模型各有优势的情况下，你为什么会选择继续深挖 MOSS呀？你觉得 MOSS 最值得继续挖掘的地方是什么呢？是因为它现在已经有一些独特优势（我觉得提示词遵循、构图控制和微调潜力上应该比Anima优秀，但画面审美与动漫风格可能还不如？），还是你觉得它还有很多潜力没发挥出来？挺好奇你对它未来发展的看法。
如果要追求极致质量，避免 slop，格外风格和角色 LoRA 是必须的，即使基座模型有相关知识。所以动漫模型不需要记住成千上万的风格和角色（当然如果可以那就更好了，微调能快一点）。
有基本的动漫知识就能微调 LoRA。Krea2 是第一个有基本的动漫知识大尺寸模型。之前的模型，比如 F2 Klein，最基本的脸都不会画，再怎么微调都没用。
训练数据集上 MOSS 比 Krea2 更进一步，还支持 bounding box 让构图更可控。
The black magic "stabilizer" still works. Got low quality output? Style LoRA overfitted and can't use strength>0.8? Add this LoRA. Boom, everything is fixed.
Works on every style LoRA I trained, downloaded, and even finetuned ckpt. E.g. https://civitai.red/models/3016505/mossad-demo-moss-image-danboorue621-57-artist-style-finetune