๐ Kivotos XL 2.0
Kivotos XL 2.0 is the latest iteration in the Yodayo Kivotos XL series. It's an open - source model based on Animagine XL V3, specialized for generating high - quality anime - style art, particularly tailored to the visual style of the Blue Archive franchise.
๐ Quick Start
- Use this model in our platform: [
](https://yodayo.com/models/ee3c3839 - e723 - 45f5 - 9151 - 18b592bc93b9/?modelversion=f3989e22 - 5afc - 40a1 - b435 - 38eae7760f37)
- Use it in
ComfyUI
or [Stable Diffusion Webui
](https://github.com/AUTOMATIC1111/stable - diffusion - webui)
- Use it with ๐งจ
diffusers
โจ Features
- Built upon Animagine XL V3, a specialized SDXL model for high - quality anime - style artwork generation.
- Focuses on accurately representing the visual style and aesthetics of the Blue Archive franchise.
- Inherits special tags from Animagine XL 3.1 to enhance image generation.
๐ฆ Installation
First install the required libraries:
pip install diffusers transformers accelerate safetensors --upgrade
๐ป Usage Examples
Basic Usage
import torch
from diffusers import StableDiffusionXLPipeline
pipe = StableDiffusionXLPipeline.from_pretrained(
"yodayo-ai/kivotos-xl-2.0",
torch_dtype=torch.float16,
use_safetensors=True,
custom_pipeline="lpw_stable_diffusion_xl",
add_watermarker=False,
variant="fp16"
)
pipe.to('cuda')
prompt = "1girl, kazusa \(blue archive\), blue archive, solo, upper body, v, smile, looking at viewer, outdoors, night, masterpiece, best quality, very aesthetic, absurdres"
negative_prompt = "nsfw, (low quality, worst quality:1.2), very displeasing, 3d, watermark, signature, ugly, poorly drawn"
image = pipe(
prompt,
negative_prompt=negative_prompt,
width=832,
height=1216,
guidance_scale=7,
num_inference_steps=28
).images[0]
image.save("./cat.png")
๐ Documentation
Tag Ordering
For optimal results, it's recommended to follow the structured prompt template because we train the model like this:
1girl/1boy, character name, from which series, by which artists, everything else in any order.
Special Tags
Kivotos XL 2.0 inherits special tags from Animagine XL 3.1 to enhance image generation by steering results toward quality, rating, creation date, and aesthetic. This inheritance ensures that Kivotos XL 2.0 can produce high - quality, relevant, and aesthetically pleasing images. While the model can generate images without these tags, using them helps achieve better results.
- Quality tags: masterpiece, best quality, great quality, good quality, normal quality, low quality, worst quality
- Rating tags: safe, sensitive, nsfw, explicit
- Year tags: newest, recent, mid, early, oldest
- Aesthetic tags: very aesthetic, aesthetic, displeasing, very displeasing
Recommended Settings
To guide the model towards generating high - aesthetic images, use the following recommended settings:
nsfw, (low quality, worst quality:1.2), very displeasing, 3d, watermark, signature, ugly, poorly drawn
masterpiece, best quality, very aesthetic, absurdres
- Classifier - Free Guidance (CFG) Scale: should be around 5 to 7; 10 is fried, >12 is deep - fried.
- Sampling steps: should be around 25 to 30; 28 is the sweet spot.
- Sampler: Euler Ancestral (Euler a) is highly recommended.
- Supported resolutions:
1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536
๐ง Technical Details
These are the key hyperparameters used during training:
Feature |
Pretraining |
Finetuning |
Hardware |
2x H100 80GB PCIe |
1x A100 80GB PCIe |
Batch Size |
32 |
48 |
Gradient Accumulation Steps |
2 |
1 |
Noise Offset |
None |
0.0357 |
Epochs |
10 |
10 |
UNet Learning Rate |
5e - 6 |
3.75e - 6 |
Text Encoder Learning Rate |
2.5e - 6 |
None |
Optimizer |
Adafactor |
Adafactor |
Optimizer Args |
Scale Parameter: False, Relative Step: False, Warmup Init: False (0.9, 0.99) |
Scale Parameter: False, Relative Step: False, Warmup Init: False |
Scheduler |
Constant with Warmups |
Constant with Warmups |
Warmup Steps |
0.05% |
0.05% |
๐ License
Kivotos XL 2.0 falls under [Fair AI Public License 1.0 - SD](https://freedevproject.org/faipl - 1.0 - sd/) license, which is compatible with Stable Diffusion modelsโ license. Key points:
- Modification Sharing: If you modify Kivotos XL 2.0, you must share both your changes and the original license.
- Source Code Accessibility: If your modified version is network - accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.
- Distribution Terms: Any distribution must be under this license or another with similar rules.
Model Details
Property |
Details |
Developed by |
Linaqruf |
Model Type |
Diffusion - based text - to - image generative model |
Model Description |
Kivotos XL V2.0, the latest in the Yodayo Kivotos XL series, is an open - source model built on Animagine XL V3. Fine - tuned for high - quality Blue Archive anime - style art generation. |
License |
[Fair AI Public License 1.0 - SD](https://freedevproject.org/faipl - 1.0 - sd/) |
Finetuned from model |
[Animagine XL 3.1](https://huggingface.co/cagliostrolab/animagine - xl - 3.1) |