It takes substantial time and efforts to bake models. If you appreciate my models, I would be grateful if you could support me on Ko-fi ☕.
✔️ Good for inference: AnimeBoysXL v3.0 is a flexible model which is good at generating images of anime boys and males-only content in a wide range of styles.
✔️ Good for training: AnimeBoysXL v3.0 is suitable for further training, thanks to its neutral style and ability to recognize a great deal of concepts. Feel free to train your own anime boy model/LoRA from AnimeBoysXL.
Prompt: Use tag-based prompts to describe your subject.
Tag ordering matters. It is highly recommended to structure your prompt with the following templates:
1boy, male focus, character name, series name, anything else you'd like to describe, best quality, amazing quality, best aesthetic, absurdres
2boys, male focus, multiple boys, character name(s), series name, anything else you'd like to describe, best quality, amazing quality, best aesthetic, absurdres
For more detailed documentation, you can visit my article on Ko-fi (available to supporters only).
Negative prompt: Choose from one of the following two presets.
Heavy (recommended): lowres, bad, text, error, missing, extra, fewer, cropped, jpeg artifacts, worst quality, bad quality, watermark, bad aesthetic, unfinished, chromatic aberration, scan, scan artifacts
Light: lowres, jpeg artifacts, worst quality, watermark, blurry, bad aesthetic
VAE: Make sure you're using SDXL VAE.
Sampling method, sampling steps and CFG scale: I find (Euler a, 28, 8.5) good. You are encouraged to experiment with other settings.
Width and height: 832*1216 for portrait, 1024*1024 for square, and 1216*832 for landscape.
AnimeBoysXL v3.0 is trained from Pony Diffusion V6 XL, on ~516k images.
The following tags are attached to the training data to make it easier to steer toward either more aesthetic or more flexible results.
best quality
: score >= 150
amazing quality
: score in the range of [75, 150)
great quality
: score in the range of [25, 75)
normal quality
: score in the range of [0, 25)
bad quality
: score in the range of (-5, 0)
worst quality
: score <= -5
The aesthetic tags of AnimeBoysXL v3.0 reflect my aesthetic preference.
best aesthetic
amazing aesthetic
great aesthetic
normal aesthetic
bad aesthetic
sfw
: general
slightly nsfw
: sensitive
fairly nsfw
: questionable
very nsfw
: explicit
year YYYY
where YYYY
is in the range of [2005, 2023].
Hardware: 4 * Nvidia A100 80GB GPUs
Optimizer: AdaFactor
Gradient accumulation steps: 8
Batch size: 4 * 8 * 4 = 128
Learning rates:
8e-6 for U-Net
5.2e-6 for text encoder 1 (CLIP ViT-L)
4.8e-6 for text encoder 2 (OpenCLIP ViT-bigG)
Learning rate schedule: constant with 250 warmup steps
Mixed precision training type: FP16
Epochs: 40
Change the base model from Stable Diffusion XL Base 1.0 to Pony Diffusion V6 XL.
Revamp the dataset's aesthetic tags based on the developer's preference.
Update the criterion of quality tags.
Use FP16 mixed-precision training.
Train for more epochs.
chefFromSpace for his assistance with the showcase images.
Since AnimeBoysXL v3.0 is a derivative model of Pony Diffusion V6 XL by PurpleSmartAI, it has a different license from the previous versions. Please read their license before using the model.
Change the base model from Stable Diffusion XL Base 1.0 to Pony Diffusion V6 XL.
Revamp the dataset's aesthetic tags based on the developer's preference.
Update the criterion of quality tags.
Use FP16 mixed-precision training.
Train for more epochs.
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights.