README.md

---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: >-
    yoko littner, by kaisen chuui, tsukiyo \(skymint\), by masami chie, tengen
    toppa gurren lagann, solo, 1girl, upper body, BREAK (head back:1.1),
    deepthroat, neck bulge, throat bulge, double dildo, holding sex toy, arms
    up, tears, drooling, saliva, tongue out, BREAK pointy breasts, perky
    breasts, see-through silhouette, tanlines, black bikini, scarf, ponytail,
    BREAK outdoors, backlighting, uncensored, rating_explicit, source_anime,
    score_9, score_8_up
  parameters:
    negative_prompt: bar_censor, mosaic_censoring, depth of field
  output:
    url: images/141236177.jpeg
base_model: LyliaEngine/Pony_Diffusion_V6_XL
instance_prompt: None
license: cdla-permissive-2.0
---
# autismmixSDXL_autismmixConfetti

<Gallery />

## Model description 

Mix of pony with some stuff. It&#39;s an attempt at making pony more predictable and less dependent on schizo negatives without removing its comprehension and artist knowledge. Personally I&#39;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 &quot;about model&quot; 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: &quot;score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_anime, BREAK&quot;

From my testing schizo negatives and those negative embeds made for SDXL&#x2F;pony make it worse, but do whatever you want.

If you have any issues running this model I suggest using this webui: https:&#x2F;&#x2F;github.com&#x2F;lllyasviel&#x2F;stable-diffusion-webui-forge

As well as this extension if you get noise outputs:
https:&#x2F;&#x2F;github.com&#x2F;hako-mikan&#x2F;sd-webui-prevent-artifact

## Trigger words

You should use `None` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/LyliaEngine/autismmixSDXL_autismmixConfetti/tree/main) them in the Files & versions tab.