v1.0:

> Initial release

- - -

Anima Artificer Alter is a model based on Illumi Yume XL v3.5 (V-Pred). The strong point of this model is its ability to recognize any character and artist style only by name, based on Danbooru database up to May 9th, 2025.

My focus for Anima Artificer Alter is to create a base model that is capable of producing great images with simple input, without the need for a detailed prompt or a LoRA. I highly encourage you to use artist styles in your prompt, especially if you mix and match them. This approach will give very interesting and aesthetic images.

Check this web for list of artist style name: https://tagexplorer.github.io/#/artists

Recommended Settings

Positive prompt: masterpiece, best quality, very aesthetic, highres, absurdres
Negative prompt: worst quality, low quality, bad quality, watermark, worst aesthetic,
CFG: 3 ~ 5 (V-Pred doesn't need high CFG)
Step: 20 ~ 30
Sampler: Euler a / DPM++ 2M Karras

Use Upscale to get the best result.

Upscaler: R-ESRGAN 4x+ Anime6B / 4x-UltraSharp

Anima Artificer Alter | V-Pred Illustrious XL