IllumiYume (Anime Style) NoobAI-XL (NAI-XL)

Overview

• This model is built based on the architecture of the NOOBAI XL-VPred 1.0, with some structural modifications. It is trained on the Danbooru2024 dataset along with a custom dataset captioned by ChatGPT-4o, and it uses the NOOBAI XL-VPred 1.0 model as a teacher during training.

Important Note

• Since this is a model which I reconstructed myself, I would really appreciate any feedback. It will not only motivate me but also help me understand its strengths and weaknesses so I can improve it in the future.

• This is a V-prediction model (different from epsilon-prediction), it requires specific parameter configurations. Please refer to the user guide here.

• This model focuses on anime style so it may decrease the performance of artist tag style

Currently, the model is not available for use via Civitai Generation. You can visit the following website to use it:

• tensor.art

Recommended Settings

• Positive prompt: masterpiece,best quality,amazing quality

• Negative prompt: bad quality,worst quality,worst detail,sketch,censor, simple background,transparent background

• CFG: 4-6

• Clip skip: 2

• Step: 20-30

• Sampler: Euler a

Note:

• I don't use any post-processing and Lora to enhance the example images. I only use these settings and a custom prompt with my base model to generate.

• I used prompts from various sources and authors to generate these example images for comparison and to evaluate my model independently.

Acknowledgments

• Thanks to narugo1992 and Nyanko for sharing such valuable data and Laxhar Lab for providing an amazing model!

If you'd like to support my work, you can do so through Ko-fi!