A blue-skinned witch with wavy hair, extra faces, and a large witch hat sits in a castle at night, wearing a white dress and brown cloak.

Recommended Prompts

score_9, score_8_up, score_7_up, source_anime

night, dark environment

score_9, score_8_up, score_7_up, source_anime, night

Recommended Negative Prompts

monochrome

Recommended Parameters

samplers

Euler a

steps

24

cfg

6

resolution

1024x1024, 832x1216

vae

fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors

other models

ShishiroBotanPDXL (783666408355), Ranni_XLPD_CAME (301e9c0f53e1)

Recommended Hires (High-Resolution) Parameters

upscaler

4x-AnimeSharp

upscale

2

steps

12

denoising strength

0.35 - 0.55

Tips

Do not use negatives unless you want to exclude specific elements.

Avoid using parentheses or weights like (:1.2) on tags as they can produce artifacts.

Use the Adetailer extension to improve the sharpness of eyes and avoid burns.

Refer to Basemodel Pony Diffusion V6 for additional tag-related guidance.

Hello everyone,

here is one experimental Checkpoint that allows you to do more darker / better night images. Inspired by my old Dark Incursio Style LoRA for 1.5. It has some small issues, like the spotlight effect on the Character or that hands are pretty bad. Those will be fixed in the near future.

The only prompt you ever need is this positive prompt:

score_9, score_8_up, score_7_up, source_anime
night, dark environment

No need for any negatives. Please dont use any or at least only use negatives, that you dont want in your current image. I sometimes use 3d in negative only, when I wanna switch the style. I'm sick of seeing schizo negatives and schizo positives. I also recommend to not use any () or with weights like (:1.2) on any tags. It can produce some artifacts on your images. To know more about this, check this Article. Anything else for tag related stuff, see Basemodel Pony Diffusion V6.

I also recommend to use the Extension Adetailer, because eyes may not be sharp due to burns.

Settings for generating Images:

  • Sampler: Euler a

  • Steps: 24

  • CFG 6.0

  • Base Resolution 1024x1024


Everything else is specified in the image tags. Make sure to leave a review or a comment if you got good use out of this Mix.

How to use Checkpoints's in auto1111:

  • Download Checkpoint

  • Copy the file to stable-diffusion-webui/models/Stable-diffusion

  • Select your Checkpoint

  • Have Fun!

Previous
Sinister Style SDXL - v1.0
Next
Vixon's White Nova - v1.0

Model Details

Model type

Checkpoint

Base model

Pony

Model version

v0.5PDXL

Model hash

5454c4756c

Trained words

night, dark environment

Discussion

Please log in to leave a comment.

Images by Dark Incursio PDXL - v0.5PDXL

anime Images

base model Images

photorealistic Images

woman Images