AingDiffusion XL

CHECKPOINT
Reprint


Updated:

459

Created by kayfahaarukku

AingDiffusion XL (read: Ah-eeng Diffusion XL) merges anime models based on SDXL with some extra self-trained datasets. This model is capable of generating high-quality anime images.

Guide to generating good images with this model

(This guide is relevant to the latest version of AingDiffusion XL)

  • This model uses Animagine's way of prompting:

    1girl/1boy, character name, from what series, what style, everything else in any order, masterpiece, best quality, very aesthetic, absurdres

    It is also recommended to include the style name of the images you want to generate in the prompt (eg. anime screencap, sketch, pixel art, famous artist name, etc.).

    The standard negative prompt recommended for this model:

    nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, watermark, artistic error, username, scan, [abstract],

  • Use SDXL-recommended resolutions. This is SDXL, SD 1.5 resolution always performs worse.

  • The recommended sampler is "Euler a" with ~7 CFG and ~25 steps.

  • Set ENSD (eta noise seed delta) to 31337 [to replicate image].

Character List

AingDiffusion XL is a derivative of Animagine XL v3. The latest version of AingDiffusion XL is a derivative of Animagine XL 3.1, which has over 4.9k characters trained on it. You can see the full list here:  https://huggingface.co/spaces/cagliostrolab/animagine-xl-3.1/blob/main/wildcard/characterfull.txt

FAQ

Q: There's nothing special about this model, it didn't have something unique.

A: The goal of AingDiffusion XL right now is to enhance the experience and the capabilities of Animagine. The goal is basically to make Animagine on steroids.

Q: The images I generate are bad and not as good as yours.

A: First, make sure you follow the standard prompting guide I provide. Also, sometimes I found people using SD 1.5 embeddings with this model. DO NOT USE THEM. THEY DON'T WORK WITH SDXL.

Legals

Due to the usage of Animagine XL with the merge, the model is now using Fair AI Public License 1.0-SD license.

Because of some reason, I decided to make the merging recipe clearer which I will put in the "About Version" section starting from version v0.6.

Version Detail

SDXL 1.0
The fine-tuned layer dataset count has been increased from 7.7k images to 19.8k images, which improves the quality of the model. Fine-tune Dataset Details - Raw dataset size: 33,704 images - Processed with aesthetic-shadow-v2 - Total lq dataset: 13.814 images - Total hq dataset: 19,890 images - Only the hq-rated dataset is used for training. First Layer finetuning Details - GPU: 1 x RTX 3090 - Dataset count: 19,890 images - Batch size: 8 - Gradient Accumulation: 3 - Equivalent batch size: 24 - Epoch: 8 - Used epoch: 5

Project Permissions

Model reprinted from : https://civitai.com/models/226403

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Comments

Related Posts

No posts yet
Describe the image you want to generate, then press Enter to send.