models/Moxie Diffusion XL - v1.6

Moxie Diffusion XL - v1.6

|
8/20/2025
|
11:10:56 PM
| Discussion|
0
Young nun wearing traditional black and white habit reading a prayer book inside a convent with stained glass windows and wooden pews.
Japanese nun with black twin-tails wearing a white habit and veil, seated on a bed in a convent infirmary, hands clasped praying, with a crucifix on the wall.

Recommended Prompts

highly detailed, vignette, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain

Recommended Negative Prompts

anime, cartoon, graphic, text, painting, abstract, crayon, graphite, glitch, deformed, plastic, mutated, long neck, ugly, asymmetrical eyes, disfigured, signature, watermark, jpeg artifacts

Recommended Parameters

samplers

DPM++ SDE Karras, DPM++ 2M SDE Turbo

steps

7 - 8

cfg

1 - 3.5

clip skip

2

resolution

832x1216

vae

baked-in VAE - built-in

other models

RM_Niji_v1.0_bf16 (4213b5acf10f), moxieDiffusionXL_v16 (8d8054db43)

Recommended Hires (High-Resolution) Parameters

upscaler

4x-UltraMix_Balanced

upscale

1

steps

2

denoising strength

0.3

Version Highlights

v1.6

Crystal clear has been in my top 3 almost continuously since I found it. I was excited when I saw they posted a Lightning version.

Formerly Turbo Diffusion XL

v1.91

It seems the problem was ZavyChromaXL..

v1.9

I am fairly adamant to use only trained checkpoints when creating these checkpoints. I was excited to see with Zaxious now has a trained checkpoint. I'm pretty curious to play more with this. So far, I'm liking this version quite a bit.

v1.8

I have typically liked ProtoVision and DynaVision more, and used NightVision sparingly. However, lately I like NightVision the best. It seemed like time to incorporate it since there were new releases of NightVision and Zavy (Zavy being one of my long time favorites).

v1.7

Fully SDXL version...

Lightning Versions

v1.6

Crystal clear has been in my top 3 almost continuously since I found it. I was excited when I saw they posted a Lightning version.

v1.51

This is a low percentage merge. I don't find a large difference between 1.50 and v1.51. However, the comparison images seem to be a little sharper and more realistic. I decided to do this merge after playing with the donor checkpoints.

v1.5

As I have been playing more with v1.4, I am finding that I am not as happy with the realism as I initially thought. I resetting it by merging checkpoints of some of my favorite trained checkpoints.

As I have been playing more with v1.4, I am finding that I am not as happy with the realism as I initially thought. I resetting it by merging checkpoints of some of my favorite trained checkpoints.

v1.4

v1.32

This version is a complete ground up re-make using SDXL Lightning checkpoints.


This has a baked in VAE.

  • Sampling Method: DPM++ SDE Karras

  • Sampling steps: 7

  • CFG Scale: 1

  • Clip Skip: 1 or 2

Turbo Versions

v1.2

The anime in this version seems to be more of a realism anime.

v1.12

A re-merge of 1.0 using Vibrant 2.0 instead of 1.0. Everything else remains the same.


v1.1


v1.0


This checkpoint is a Stable-Diffusion merge between the follow 3 SDXL Turbo models.

This has a baked in VAE.

  • Sampling Method: DPM++ SDE Karras

  • Sampling steps: 8

  • CFG Scale: 2 > 3.5

  • Clip Skip: 1 or 2

Previous
Blue Archive Game CG Style - Animagine3.1
Next
Korean Manhwa mix style Pony - Korean Manhwa Mix v1.0

Model Details

Model type

Checkpoint

Base model

SDXL Lightning

Model version

v1.6

Model hash

0fe2e39405

Trained words

N/A

Creator

Discussion

Please log in to leave a comment.

Images by Moxie Diffusion XL - v1.6

anime Images

art Images

base model Images

cyberpunk Images

scifi Images