animagine-xl

For best outputs:


 Sampler: Euler Ancestral.


 Steps: 28, cfg 7, CLIP skip 2.


 VAE: none required.


 Pos prompt: add "masterpiece, best quality, very aesthetic, absurdres" at the end.


 Neg prompt: "wings, low quality, worst quality, normal quality,
 
 nsfw"
 
 optional.


 This model is SFW / NSFW. It's able to recognize the most common sex positions and it's not POV only, it's able to draw the male partner's body. Remember to mark your NSFW run as NSFW if you plan to post them in the model's gallery.


 Animagine XL 3.1 is an update in the Animagine XL V3 series, enhancing the previous version, Animagine XL 3.0. This open-source, anime-themed text-to-image model has been improved for generating anime-style images with higher quality. It includes a broader range of characters from well-known anime series, an optimized dataset, and new aesthetic tags for better image creation. Built on Stable Diffusion XL, Animagine XL 3.1 aims to be a valuable resource for anime fans, artists, and content creators by producing accurate and detailed representations of anime characters.

v3.1

For best outputs:


 Sampler: DPM++ 2M Karras


 Steps: 28, cfg 7, CLIP skip 2.


 VAE: sdxl_vae.safetensors


 Use the embedding "bad-hands-5" in the neg (included in the example runs)


 In the pos, "masterpiece, best quality".


 This model is SFW / NSFW. It's able to recognize the most common sex positions and it's not POV only, it's able to draw the male partner's body. Remember to mark your NSFW run as NSFW if you plan to post them in the model's gallery.