AutismMix SDXL - AutismMix_DPO
추천 프롬프트
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
추천 네거티브 프롬프트
3d
3d, monochrome, signature, torn clothes
추천 매개변수
samplers
steps
cfg
resolution
vae
추천 고해상도 매개변수
denoising strength
팁
For better compatibility with certain LoRAs train on AutismMix_pony version.
Add '3d' to negative prompts for a more traditional anime style.
Avoid using schizo negatives and SDXL/pony negative embeds as they may worsen results.
If issues arise running the model, use the webui: https://github.com/lllyasviel/stable-diffusion-webui-forge
Use the extension https://github.com/hako-mikan/sd-webui-prevent-artifact if you encounter noise outputs.
크리에이터 스폰서
If you have any issues running this model, try using this web UI: https://github.com/lllyasviel/stable-diffusion-webui-forge
For noise reduction: 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
모델 세부사항
토론
댓글을 남기려면 log in하세요.






