SoulTide 灵魂潮汐 Silenus 西勒诺斯
时装和纯样式提示词请参考标准提示样例图片与 [版本变更说明 (About this version)]。
这是传统 Diffusion 模型版本。 DiT 模型版本 (Anima) 请直接前往本页面的 [推荐资源 (Suggested Resources)] 栏目查看。
For fashion and pure style prompts, please refer to the standard prompt sample pictures and [About this version].
This is the DiT version. For traditional Diffusion models (SD1.5 / Pony / Illustrious), please check the [Suggested Resources] section on this page.
版本说明 Version Descriptions
Pony
基础模型: MugenMaluMix SDXL - v4.2
兼容性: 可在其他 Pony 系列模型上使用
训练方式: Lora
Base Model: MugenMaluMix SDXL - v4.2
Compatibility: Works with other Pony-series models
Training Method: Lora
IL
基础模型: Hassaku XL (Illustrious) - v2.1fix
兼容性: 可在其他 Illustrious 系列模型上使用
训练方式: Lora
备注: 若使用 Hassaku XL (Illustrious)，请避免使用 v2.1fix 以上版本
Base Model: Hassaku XL (Illustrious) - v2.1fix
Compatibility: Works with other Illustrious-series models
Training Method: Lora
Note: If you are using Hassaku XL (Illustrious), avoid versions above v2.1fix
ILLC
同 IL 版本，但使用 LyCORIS LoCon 方式训练
Same as the IL version, but trained using LyCORIS LoCon
ILWAILC
基础模型: WAI-illustrious-SDXL - v16.0
训练方式: 使用 LyCORIS LoCon
兼容性: 可在其他 Illustrious 系列模型上使用
Base Model: WAI-illustrious-SDXL - v16.0
Training Method: Trained with LyCORIS LoCon
Compatibility: Works with other Illustrious-series models
About the version number
Pony: 具体版本号数字为数据集与训练方式版本, 最高版本号为 Pony 下的最新的推荐版本, 但目前均落后于 IL
IL / ILLC / ILWAILC: 具体版本号数字为数据集版本, 最高版本号为 IL / ILLC / ILWAILC 三者下的最终版本, 同版本号如 ILV1.0 / ILLCV1.0 表示为使用相同数据集, 仅训练方式不同
Pony: The version number represents the dataset and training method version. The highest version number indicates the latest recommended version under Pony, though all Pony versions currently lag behind IL.
IL / ILLC / ILWAILC: The version number represents the dataset version. The highest version number is the final version across IL / ILLC / ILWAILC. Identical version numbers such as ILV1.0 / ILLCV1.0 indicate that they use the same dataset but differ only in training method.
Description
FAQ
Comments (5)
You seem to be releasing a lot of different loras, I've noticed, and I want you to continue to do so and be successful at doing so. So I would suggest a tip; You should try to train at conventional dim and conventional alpha at 8/4 respectfully so as you have a much smaller file size without losing any quality in your gens.
Smaller file size makes it more enticing for viewers to want to download more of your models. More people that download your models equals more popularity for you. Best of luck in your future ai endeavors!
Thank you for your suggestion!
I've actually been using 32/32 for quite some time now. I’m aware it results in a larger file size, but I haven't tested the quality of models trained with lower dim/alpha parameters yet. Before successfully releasing at least one stable version, I prefer to stick with this configuration as it’s something I know works well. For my own use, I find the current size (around 200MB) to be manageable.
If I decide to update the versions in the future, I might consider adjusting the parameters. However, for now, both ILV1.0 and PonyV3.0 will continue using the current configuration.
Looking ahead, do you think we might eventually transition away from LoRA to Dora/LyCORIS? Several studies suggest these newer methods outperform LoRA in many use cases, but I’m curious about your thoughts—have you explored them, or do you think they offer enough advantages to justify the switch?
I do, actually I believe many already use lycoris, it's just the civitai system still labels it as lora, unless you throw it in a metadata reader. There's a clear difference between the two in quality. Though for most characters it isn't needed too much, but lycoris will help with minute detail on clothing and such. Dora... I don't know TOO much on it, but it's more to learn and understand and most people don't like leaving their comfort zone of what works and what doesn't, so I see lycoris becoming more widely used, but not Dora.
I understand your reasoning for continuing to do it your way of 32/32, as back since 1.5 that's been the tried and true, but it's just only recently been discovered that it's unneeded. If you ever have the time you can always try and see for yourself with exact same parameters and only changing the dim and conv size. I've been a 'collector' of sorts of lora since the beginning of this bleeding edge technology and I too didn't care too much it was 217mb... but now as I keep collecting them, definitely starting to run out of space along with 7gb models and control-nets, video models, large language models and such. lol... it eats space very quickly. So it is definitely me trying to save space and get more models collected without having to sacrifice hard drive space, but also I know not everyone is aware of the fact it's even an option and I try to pick random people on here and explain such to them, then it's up to them.
@Light7799
I recently conducted a comparison under a 100-epoch training condition (with approximately 5000 global steps for 1 batch, selecting results with the lowest loss between steps 80-100). I tested both 16+16+4 (100MB) and 32+32+4 (200MB) Lycoris models.
Using the same seed, I generated images for an XYZ chart with 24+24 samples per group.
At a strength of 1.0, the 32+32+4 model showed significantly better adherence to the training set in terms of background details, though the difference in character clothing was minor.
At my usual strength of 0.7, the differences in clothing became more pronounced.
To rate them: the 16+16+4 set had 8 images where features were not well-represented, compared to just 1 such image in the 32+32+4 set.
I repeated the experiment with three different -1 seeds and reached the same conclusion.
It seems smaller-dimension models may not lose performance at lower steps, but larger models still exhibit greater potential for understanding the dataset at higher steps.
@zwa73 Interesting. Though I can see this being a case by case basis then if the larger mb lora gives better background, as some want just the character and I've even been told if the background starts to bleed into gens from the character dataset then it's slightly over-trained (I don't think this is particularly true, myself).
Though knowing this then I can see an argument for using a larger dim size when wanting to get the character pretty much spot on in the media that it exists in, say for like a genshin character, where you'd WANT the background to be cohesive with the character, but if you're just wanting the character per-say, and you don't need it in the exact media it's taken from, lower dim size works best... I see, I appreciate you informing me on your experiment and outcomes! I will keep this in mind, for sure.