discard-icon
vip-icon

WonderMix

WonderMix_v2
WonderMix_v2 Inpainting
Reprint
Last Update:2025-06-21
#landscapes
#Character
#3D
#midjourney
#abstract
#Photorealistic
#retro
#general purpose
#3d render
#ckpt
#fantasy art
#woman
#Cartoon
#Fantasy
#Photography
#Sci-Fi
#video game
#landscapes
#Character
#3D
#midjourney
#abstract
#Photorealistic
#NSFW
#retro
#general purpose
#3d render
#safetensor
#ckpt
#sfw
#fantasy art
#Style
#woman
#Cartoon
#Fantasy
#Photography
#Sci-Fi
#video game
#fp16

Merged model with additional fine-tuning for variety and quality. Midjourney-esque with the ability generate highly detailed photo-realistic images/still frames

Like photorealism? Try my new fine-tune 'Lomostyle'

Capabilities

  • Complex 3D renders

  • Photorealistic images

  • NSFW/SFW generations (use tags: nsfw, sfw in prompt)

  • Abstract art

  • Cartoon stills

  • Landscape photography

  • High compatibility with LoRA models

  • Designed to handle light AND complex prompts.

Hardcore generations are also possible but, that wasn't the main focus of this model. There are much better models for this use case, unless you're looking for a more stylized/artistic hardcore generation.

Limitations

  • Anime (Future updates will add Anime capability.)

  • Occasionally the nsfw/sfw tags don't trigger. This can usually be addressed by:

    • Moving the sfw, nsfw tags towards the beginning or end of the prompt.

    • Using attention/emphasis ((sfw)), or (nsfw:1.2)

  • Strong VAE recommendation. (this is due to fine-tuning)

Models used in the merge

Models used in the merge are included in the version description bellow.

Check out my other models

SDXL

SD1.5

LoRA

Questions or Feedback?

Visit my thread on the Unstable Diffusion Discord Server

View More
Quick Translation
Comment 17
avatar
33dragon dude
Bro, it was going good until the AI fucking ruined it. I literally said "I can't transform into a dragon because this place is too big then the AI turned fucking retarded and kept saying that was inappropriate.
2024-09-24
View Translation
4
2
avatar
33dragon dude
*too small
2024-09-24
View Translation
Like
Reply
Show 1 Replies
avatar
Sev
Just want to add to the pile of people saying this ai ruins it when it starts talking for you. Great premise, completely destroyed by that.
06-13
View Translation
Like
Reply
avatar
Daniel Ball
I think I broke your character.
06-03
View Translation
Like
Reply
avatar
Tehel Adam
The AI just started to speak for me, and i ain't about that
05-25
View Translation
Like
Reply
avatar
まぁるぃ
何かを喋ってもそれを繰り返しAIが喋るだけで女の子がほとんどリアクションを取りません、結果悪魔の一人芝居になって物語が進みません。面白そうな展開なのに実に残念です
03-16
View Translation
Like
Reply
M
Mataki
Its a good concept, but the ai talks as it was the demon, and repeats the menssages, it ruins the experience
02-17
View Translation
Like
Reply
avatar
Riley
I tried to be a nice guy, but stuff happened including me flipping the mean ones off, bitch-slapping Claire, and escaping. I do really like how the AI kind of took what I said and added a bit of embellishment to it, like it described my emotions and tone of voice. Cool bot!
01-29
View Translation
Like
Reply
avatar
Dave
Very nice
01-25
View Translation
Like
Reply
avatar
olgregg80085
I love the concept here, but every attempt at creativity is ruined by the AI being unable to remember anything at all.
01-19
View Translation
Like
Reply
avatar
Zerwer
Hi, the ia is good, but... the repeat of my message on the ia message is bad, change everything of my message
2024-11-04
View Translation
Like
Reply
Create (17.4K)
Favorite (648)
Download (2.3K)
Model Details
Type
Checkpoint
Rating
0
Publish Time
2023-03-20
Base Model
SD 1.5
Model Source: civitai
Version Introduction

Initial Release

VAE Strongly Recommended

https://huggingface.co/stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.ckpt

In webui settings, Uncheck: Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them

Includes

  • WonderMix_v2.safetensors

  • WonderMix_v2.ckpt

  • WonderMix_v2-fp16.safetensors

Merged Models

Note: Many of the sample images use the bad_promptv2 textual inversion. This is not at all required but, if you want to generate identical images to the sample images you can find the textual inversion here:

https://huggingface.co/datasets/Nerfgun3/bad_prompt/tree/main

Other settings:

ETA Seed Noise Delta: 31337

ClipSkip: 1

View More
License Scope
Creative License Scope
Online Image Generation
Merge
Allow Downloads
Commercial License Scope
Sale or Commercial Use of Generated Images
Resale of Models or Their Sale After Merging