Model Info
This model is intended to create antro/furry art, I primarily use it to create semirealistic art, but it can be used to create a wide variety of styles. This model uses both danbooru and e621 tags for prompting which can without lora generate characters, clothes, poses and more. This model uses tagging and is not proficient with natural language and has a baked in vae, so no seperate vae is needed.
Recommended Settings
Updated 2025-12-20
Resolution: Any SDXL resolutions, I use 1360 x 768
Steps: 25
CFG Guidance: 3
Sampler: Euler Ancestral
Scheduler: SGM_Uniform
It is also highly recommended to use Hires fix and optionally FaceDetailer (ComfyUI) or ADetailer (stable-diffusion-web-ui/A1111, stable-diffusion-web-ui-forge).
Recommended Prompts
Updated 2025-12-20
Positive
masterpiece, best quality, newest, absurd res, amazing quality, very aesthetic, very awa, anthro, furry, (no humans:0.1),Negative
worst quality, bad quality, human,
bad hands, deformed,
watermark,For further ideas and inspiration check out the prompts i used on the images associated with the model. They may not use the latest version of the prompts in their generation.
Changelog
V 7.0 Updated to Illustrious. Improved image fidelity, improved ability to make detailed poses.
V 6.0 Improved character anatomy, mitigated risk of human appearance, mitigated risk of names appearing.
V 5.0 Updated to latest version of source checkpoints as of 2025-06-11.
V 4.0 Updated to NoobAI. Improved character anatomy, color composition and prompt adherence.
V 3.0 This Illustrious based model has significantly improved versatility and offers the full spectrum of both danbooru tags and e621 tags.
V 2.0 A new hybrid merge between SDXL Lightning and Pony models. The model achieves significant improvements in anatomy, prompt adherence and overall quality while retaining the vast species library of the SDXL Lightning model.
V 1.1 Significant refinement of the 1.0 version including new recommendations in lora, generator settings and e621 artist prompt tags.
V 1.0 Initial upload.
Credits
Thanks to the SeaArtLab team, horizonteam, freek22, Urameshi, shadowrui, Jedas as well as Desync for creating and iterating the SDXL based models used in this merge.
Description
Updated to Illustrious. Improved image fidelity, improved ability to make detailed poses.
FAQ
Comments (6)
Great work. I never used to like the whole furry thing. I still don't understand the whole chicks with dicks thing, but each to their own. Great work regardless.
Thanks, I am glad you enjoy it 😊
Quite literally best model I've ever used.
Overall rating is probably 8/10, because I think that 10/10 model is years away.
This model surpasses NovaAnimal and Nova3DCG severely in the creativity department, but the anatomy isn't as accurate in comparison.
Nonetheless, it's an easy price to pay due to the anatomy being correct enough most of the time.
The faces for humans are very creative, diverse, and very sexy, which I can yet say for any other realism-esque Illustrious models.
8/10 is my rating for 2025 standards. 🦄
Wonderful to hear, I'm working to improve it further still but since this is a merge it is largely dependent on the work of other base models 😊
@Pentriac Despite it being a merge, from what I understand there's still different methods to bring forth certain attributes via U-Net block weights and self-attention layers.
As a consumer I'm only familiar with the U-Net block id thing with 'perturbed attention guidance' and U-Net Self Attention multiply node. I've never really got to merge any of these newer models before due to my GPU limits.
Either way, this version 7 is very useful. But just some food for thought on something to explore and study when/if you decide to make another version.
@Intosica Interesting 🤔