SDXL VERSION HAS OUT!

Don't worry about the deleted post, I just merge the same version back here, my bad.

TL; DR:

Based on Animagine XL V3, use Blue Archive's official artwork as fine-tune dataset for its art style. You are prohibited to use this model for any kind of commercial use. Please read the disclaimer below before you use this model.

Disclaimer:

Animagine XL V3's license asked that merges of this model should be released as same permissions, which is allowed user to use generation service or sell generated images of the model.

But according to Blue Archive's Fanart Guidelines ( JP | CN ), this model (BArtstyle) shall not be used for any kind of commercial use, including but not limited to selling this model or merges of this model, selling image generated by this model or merges of this model, or 'paid member exclusive' for monetization platforms like Patreon/Fanbox/etc.

The license change of this model is permitted by Cagliostro Research Lab, the author of Animagine XL. Once again, I sincerely thank them for their understanding and dedication for open-source community. (Permission Source)

免责声明:

根据 Animagine XL V3 的许可证，基于该模型的衍生模型应以相同授权方式公开，即允许用户使用线上生成服务，或售卖该模型生成的图片。

但根据《<蔚蓝档案>同人创作指引》 ( 日文 | 中文 )，此模型（BArtstyle）不得用于任何形式的商业用途，包括但不限于售卖该模型及其衍生模型自身或其生成的图片，或Patreon/Fanbox等众筹平台的“订阅会员限定”服务。

该许可证授权范围变更得到 Animagine XL 作者 Cagliostro Research Lab 的许可。

在这里再次感谢他们的理解，以及他们对于开源社区的贡献。（授权来源）

How-to:

This model is in ALPHA phase, pretty much undertrained, only works perfect for Blue Archive's characters.

• You can treat this like Animagine XL V3, all tag still work at same methods.

• LoRA based on Animagine XL V3 will work fine on it.

• Suggest Upscaler: AnimeVideo v3

• Still trained with color tags like BArtstyleDBv1, but seems not very effective.

• Feel free to give feedback, I need your suggestion for further developments.

Training Details:

AdamW8bit

200 Images@1024x1024

200 epoch@batch size 1

UNET: 1E-5

TE1/TE2: 5E-6

Cosine with 15 Restarts

===========DBv1 INFO===========

I'm back!

Yeah, I did say I won't update BArtstyle LoRA, but hey it's Dreambooth! I will update a merge LoRA later tho

Ah yes, I've got a 4090 now. 3 Days before it's 'banned by US' in China. Very lucky maybe.

There're far less tutorials for Dreambooth than LoRA. It costs me about a month to get a reasonably good model. Maybe NAI3.0 could do sort of the job, but I couldn't make it a full replica for Blue Archive's art style on NAI3, so good old SD1.5-base is still worth it. Enjoy!

BTW, if anyone know how to fine-tune/LoRA SDXL model, please leave comment below, I'm going to research SDXL Art Style model after this one.

How-to:

• Positive Prompts:

  • Just like BArtstyle LoRA, color scheme still work, and I managed to make these typical color like blue theme or pink theme much closer to original data without overfitting.

  • Natural Language + Low CFG (4.5-6) + Roll dices + cherry-pick > "quality tags"

  • From my test, about 30% image should be good enough at first glance. If you can't get similar result, check if there are any duplicate/conflict tags in your prompt, shrink it and lower your CFG.

• Negative Prompts:

  • DO NOT USE FCKING LONG NEGATIVE PROMPTS UNLESS YOU KNOW WHAT ARE YOU DOING!!!

  • For randomly generate, simple EasyNegativeV2 is good enough.

  • You can try to add glowing, 3d, painting \(medium\), photorealistic, nsfw in negative prompts if you think this model is still have too much CounterFeit artstyle, but I can't guarantee the effect.

• VAE: WD1-4-kl-f8-anime2-bless09.ckpt

• Sampler: Euler A

  • step 50-100

  • Yeh, CHAD Euler A still better than Virgin DPM

• Upscaler: AnimeVideo v3

  • step 10-15

  • Denoising 0.45-0.55

Base Info:

Ver. 1.0 (Initial Release)

Base Model:

• Counterfeit V3-fp16-fix

  • After 6 MONTHS wait, author has released a vae fix version of CFv3. Original version had a serious VAE issue that make all the LoRA of CFv3 is bit broken, even if you replace the VAE won't help. Strongly recommend to update if you use it.

  • It seems like it is the ONLY TRAINING model that is capable with NAI 1.0 LoRA. That means only this model is good for fine-tuning

Dataset:

• 200 images from Blue Archive's Official Artwork + flip, 400 in total.

  • TOTALLY OVERHAULED DATASET COMPARE WITH BArtstyle LoRA.

  • Highest resolution I could found, cropped to improve dataset quality

  • Use XnConvert Downscale to 1280x1280

Training Setting:

• OPTIMIZER: AdamW8bit

• SCHEDULER: Constant with Warmup

  • Warmup to 10% of total steps.

• UNET LR: 1e-6

• TE LR: 1.25-7

  • 1/8 of UNET LR as suggestion

  • Stop TE Training at 50% of total steps.

• EPOCH: 100

• BATCH SIZE: 1

• STEP: 40000

• RES: 1280X1280

• TIME: 10H27M