models/AutismMix SDXL - AutismMix_DPO

AutismMix SDXL - AutismMix_DPO

11/5/2025

4:16:24 AM

Related Keywords & Tags

anime,autismix_anon,autismmix_confetti,autismmix_dpo,autismmix_pony,autismmix sdxl,autismmix stable diffusion model,base model,checkpoint,checkpoint xl,loras,model,ponyv6,ponyxl,sdxl 1.0,sdxl anime

A realistic young woman lying on the forest floor with thighs crossed and hands on knees, looking worried. Sunlight creates lens flare with blurred background of mixed evergreen and deciduous trees.

Nero Claudius sitting confidently with a smirk on a throne in a regal castle room adorned with falling petals and roses, anime style.

Native Hawaiian woman with dark skin and long black wavy hair wearing a cream long dress and pearl necklace sitting at a restaurant table with dessert and wine, under a starry night sky.

A cosmic cat silhouette with deep black skin and glowing white eyes, surrounded by swirling nebula clouds and bright celestial lights.

Recommended Prompts

score_9,score_8_up,score_7_up,score_6_up,score_5_up,score_4_up,source_anime,BREAK

score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, score_explicit, Art by wagashi \(dagashiya\), BREAK source_anime, bb \(swimsuit mooncancer\) \(second ascension\) \(fate\), jeanne d'arc alter \(fate\), purple hair, white hair, purple eyes, yellow eyes, long hair, 1girl, ribbon, ahoge, hair ribbon, full nelson, doggystyle, sex, uncensored, (changing room:1.2) background

Recommended Negative Prompts

3d (to achieve traditional anime style)

3d, monochrome, signature, torn clothes

Recommended Parameters

samplers

Euler a

steps

cfg

resolution

1216x832, 832x1216

vae

sdxl_vae.safetensors (235745af8d)

Recommended Hires (High-Resolution) Parameters

denoising strength

0.45

Tips

To get more traditional anime style, add '3d' to negative prompts.

Schizo negatives and negative embeds for SDXL/pony may worsen results.

Use the stable diffusion webui forge for running this model: https://github.com/lllyasviel/stable-diffusion-webui-forge

Use the sd-webui-prevent-artifact extension for noise reduction: https://github.com/hako-mikan/sd-webui-prevent-artifact

Train loras on the AutismMix_pony version for better compatibility.

Creator Sponsors

If you have any issues running this model I suggest using this webui: https://github.com/lllyasviel/stable-diffusion-webui-forge

As well as this extension if you get noise outputs:
https://github.com/hako-mikan/sd-webui-prevent-artifact

Mix of pony with some stuff. It's an attempt at making pony more predictable and less dependent on schizo negatives without removing its comprehension and artist knowledge. Personally I'm using AutismMix_confetti for general use and AutismMix_pony for certain loras. If you want to train a lora on top of autism I recommend doing so in the AutismMix_pony version for better compatibility. The Lightning versions require specific settings to work, read the "about model" information under download.

What is the difference between the models:

AutismMix_confetti is a small amount of AnimeConfettiTune and AutismMix_pony. Has less style swing than pony and better hands. I prefer this one.

AutismMix_pony is a merge of ponyv6 with loras, its more compatible with certain styles made for the base ponydiffusion model.

AutismMix_DPO is AutismMix_confetti+DPO lora, made by request. Very similar to confetti version.

Add 3d to negs if you want a more traditional anime style. Quality tags should be same as ponyv6, but feel free to experiment: "score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_anime, BREAK"

From my testing schizo negatives and those negative embeds made for SDXL/pony make it worse, but do whatever you want.

If you have any issues running this model I suggest using this webui: https://github.com/lllyasviel/stable-diffusion-webui-forge

As well as this extension if you get noise outputs:
https://github.com/hako-mikan/sd-webui-prevent-artifact