🤖 Model
Animagine XL

Animagine XL

model

Author

CagliostroLab (opens in a new tab)

Uploaded

Jan 10, 2024

Type

Checkpoint

Base Model

SDXL 1.0

License

Fair AI Public License 1.0-SD

Commercial

Yes

Specializes in

Generating portraits of anime-style content.
Rating
8
Great
Size: 6.46 GB
Download IconDownload

Comflowy Review

The latest version has optimized the understanding of instructions, rather than enhancing aesthetics. I believe this direction is correct, as the aesthetics of the model were already good, and what it lacked more was the ability to understand instructions. This is especially true for anime-style content, which can include specific elements like hair, eyes, and so on, all requiring the model to have a better understanding. The newest model has made great improvements in this respect.

The score is 8 out of 10, mainly because it is somewhat lacking in complementary features, such as an Inpainting model.

Creator's sample images


  • Positive Prompt: 1girl, amiya (arknights), arknights, dirty face, outstretched hand, close-up, cinematic angle, foreshortening, dark, dark background, masterpiece, best quality
  • Negative Prompt: nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name,
  • KSampler:
    • Steps: 28
    • Sampler: Euler a
    • CFG scale: 7