Tensor.Art
Create

Async's MIX XL

CHECKPOINT
Reprint


Updated:

893

creator: asyncforai414

Async's MIX XL merge checkpoint model.

This model focuses on producing anime images.

sdxl_vae is vaked in.

Trouble shooting

If you are using webui and the image is black or has a strange tint.

In the settings, turn off "Enable Emphasis" from the StableDiffusion section. In that case, the result will be different from the sample image above.

Image results are different from the sample image above.

The version of WebUI when I created my sample images was 1.7.0, and I did not include any extensions. And I used Negative Embedding such as an14 or an12 to create it, so please download it once and place it in the designated Embedding folder to regenerate it.

an14,an12 Negative Embedding

Async's Negative - v14 | Stable Diffusion Embedding | Civitai

settings

clip skip : 2

ENSD:0

quality prompt

(Depth of field hdr 8k 4k wallpaper cinematic angle, cinematic lighting,:1.5) (masterpiece, best quality:2.0), (Depth of field hdr 8k 4k wallpaper cinematic angle, cinematic lighting,:1.5) (masterpiece, best quality:2.0)

negative prompt

n12_light (an12:1.2) (kneeling 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,:1.5),, an12_light an12 ( 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,:1.5)

example

anime,1girl,(Depth of field hdr 8k 4k wallpaper cinematic angle, cinematic lighting,:1.5) (masterpiece, best quality:2.0), (Depth of field hdr 8k 4k wallpaper cinematic angle, cinematic lighting,:1.5) (masterpiece, best quality:2.0) Negative prompt: an12_light (an12:1.2) (kneeling 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,:1.5),, an12_light an12 ( 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,:1.5) Steps: 45, RNG: CPU, Size: 896x1152, Seed: 2079619126, Model: Async's MIX XL, Version: v1.7.0, Sampler: DPM++ 2M Karras, CFG scale: 7.5, Clip skip: 2, Model hash: 9abe366cab, Hires steps: 45, Hires upscale: 1.25, Hires upscaler: Latent (nearest-exact), Denoising strength: 0.6

Version Detail

SDXL 1.0
More Anime Style. 3.1 < 3.2

Project Permissions

Model reprinted from : https://civitai.com/models/266052

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.