models/AutismMix SDXL - AutismMix_pony

AutismMix SDXL - AutismMix_pony

|
7/1/2024
|
8:03:55 PM
| Comments

Recommended Prompts

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

score_9,score_8_up,score_7_up,score_6_up,score_5_up,score_4_up,BREAK source_anime,clothed,1girl,looking at viewer,dutch angle,indoors,braid

Recommended Negative Prompts

3d,schizo,negative embeds for SDXL/pony

3d,monochrome

Recommended Parameters

samplers

Euler a, DPM++ 2M SDE Karras

steps

25 - 28

cfg

7

resolution

768x1192, 832x1216

vae

sdxl_vae.safetensors (235745af8d)

other models

AutismMix-PASB1_pony (821aa5537f)

Recommended Hires (High-Resolution) Parameters

upscaler

4x-NMKD-YandereNeo-Superlite

upscale

1.3

denoising strength

0.35 - 0.45

Tips

Add 3d to negative prompts if you want a more traditional anime style.

Feel free to experiment with quality tags similar to ponyv6: 'score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_anime, BREAK'.

If you have issues, use the recommended webui and extension to prevent noise and artifacts.

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

Previous
breast size slider - offset
Next
veryBadImageNegative - veryBadImageNegative_v13

Model Details

Model type

Checkpoint

Base model

Pony

Model version

AutismMix_pony

Model hash

821aa5537f