If you want to use more my checkpoint online generation, please visit here.
https://tensor.art/u/762555264535746522
You can run WAI-ANI-NSFW-PONYXL and use its API on SinkIn:
V14 released.
Increased composition diversity and improved model accuracy now allow images to be generated with fewer steps.
Recommended Setting
Steps:20-30
CFG scale: 5-7
Sampler: Euler a/DPM++ 2M Karras
ADetailer face_yolov8n/s.pt use can fix eyes
For the example images
I used 1024x1360,
generated directly without AD or hires fix.
Positive Prompt
score_9, score_8_up, score_7_up,source_anime,Negative Prompt
worst quality,bad quality,jpeg artifacts, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark,V13 released.
Increased body stability and accuracy.
overall balance adjustment.
Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a/DPM++ 2M Karras
ADetailer face_yolov8n/s.pt use can fix eyes
For the example images
I used 1024x1360,
generated directly without AD or hires fix.
Positive Prompt
score_9, score_8_up, score_7_up,source_anime,Negative Prompt
worst quality,bad quality,jpeg artifacts, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark,V12 released.
Style adjustment, background adjustment, and increased stability.
Added more compositions.
Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a/DPM++ 2M Karras
ADetailer face_yolov8n/s.pt use can fix eyes
Positive Prompt
score_9, score_8_up, score_7_up,source_anime,Negative Prompt
score_6, score_5, score_4, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark,v11
Weight adjustment, balancing the art style
All example images(Except the cover) are generated at 1024x1360, without using AD and hires fix.
Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a/DPM++ 2M Karras
ADetailer face_yolov8n/s.pt use can fix eyes
Positive Prompt
score_9, score_8_up, score_7_up,source_anime,Negative Prompt
worst quality,bad quality,jpeg artifacts, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark, V10
Better Background
Clothes details up
Better mature female
Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a/DPM++ 2M Karras
ADetailer face_yolov8n/s.pt use can fix eyes
Positive Prompt
score_9, score_8_up, score_7_up,source_anime,Negative Prompt
worst quality,bad quality,jpeg artifacts, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark, ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
V9 Hyper12step
Please refer to the instructions on the right side of V9 Hyper12step for usage.
V9 released.
v8->v9
adjusted the facial data to make it more versatile, allowing for easier generation of faces across various ages.
added more NSFW materials.
attempted to reduce the generation of some unnecessary details.
Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a/DPM++ 2M Karras
ADetailer face_yolov8n/s.pt use can fix eyes
Positive Prompt
score_9, score_8_up, score_7_up,source_anime,Negative Prompt
worst quality,bad quality,jpeg artifacts, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark, __________________________________________________________________________________________________
hyper12step released.
about size
Various combinations from 768x768 to 1360x1360 can produce good images.
Recommended Setting
Steps: 12
CFG scale: 3.5
Sampler: Euler a
Not very necessary to use ADetailer correction
Positive Prompt
score_9, score_8_up, score_7_up,source_anime,Negative Prompt
score_6, score_5, score_4, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark,PS.The example images use a size of 896x1192. no AD no Hires. fix
__________________________________________________________________________________________________
Version 8 released.
v7->v8
Added some training related to camera angles and backgrounds.
Added more NSFW materials for additional training.
Added some training for special effects.
Optimization of overall composition logic.
Fixed some minor issues.
better eyes and hands.
Recommended Setting
Same as v7
__________________________________________________________________________________________________
Version 7
v6->v7
Fixed the issue where images appeared entirely covered with snowflakes.
Revised the composition logic to be more suitable for general scenarios.
Added new assets for backgrounds, mature women, and clothing.
Ensured consistency with the previous model and further fixed the issue of blurry eyes in medium and long shots.
Fixed some minor issues.
V7 Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a/DPM++ 2M Karras
ADetailer face_yolov8n/s.pt use can fix eyes
Positive Prompt
score_9, score_8_up, score_7_up,source_anime,Negative Prompt
score_6, score_5, score_4, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark,________________________________________________________________________________________________
Regarding the 8step model, it is a lightweight model that can generate images in as few as 8 steps. However, the quality and text comprehension will be relatively lower. If speed is not a major concern for you, it is recommended to continue using version 6.0.
8 STEP Setting
Steps: 8-12
CFG scale: 3
Sampler: Euler a
ADetailer face_yolov8n/s.pt use can fix eyes
Positive Prompt and Negative Prompt same 6.0
__________________________________________________________________________________________________
6.0
v5->v6 Change point
Better Background
better eyes
fix vae
Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a/DPM++ 2M Karras(better eyes)
ADetailer face_yolov8n/s.pt use can fix eyes
Positive Prompt
score_9, score_8_up, score_7_up,source_anime,BREAKNegative Prompt
score_6, score_5, score_4, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark,You can view the Supported art styles from https://civarchive.com/articles/5715
Thank you, DeepDark_Fantasy514, for providing the test.
v4->v5 Change point
Better Background
Clothes details up
Add some mature female
Little better hands and eyes
Recommended Setting
Steps: 30
CFG scale: 7
Sampler: Euler a
ADetailer face_yolov8n/s.pt use can fix eyes
Positive Prompt
score_9, score_8_up, score_7_up,Negative Prompt (THX for snipsnapsnipsnap recommend )
Base:score_6, score_5, score_4, source_cartoon
Optional: source_furry, source_pony can bleaches skin
else: 3d, (censor),monochrome,blurry, lowres,watermark,
I often use it now
[score_6, score_5, score_4, source_cartoon,
3d, (censor),monochrome,blurry, lowres,watermark, ]
Description
FAQ
Comments (63)
Wow, new version
what difference between pony and illustrious version?
Pony is older and less accurate. Worse in terms of poses, hands and face, but has more LORA support, so its ssometimes better for people who have a ton of Pony LORAs.
Its also important to know that pony works a bit different. You should add "score_9, score_8, score_7" in positve and maybe "score_5, score_4" in negative. Score is something like a scale how detailed the picture is.
IL is anime heavy and dont give a fuck about western art
Pony is inspired by My Little Pony, while Illustrious is based on animated characters.
Both models are built on SDXL.
If you're looking for a wide range of expressive styles, Pony might be a good choice. On the other hand, if you prefer more general animated character aesthetics, Illustrious is a solid option.
For even more specialized animation-focused outputs, Animagine may be worth considering.
Some people say "Pony is old," but that's not entirely accurate.
It's more correct to say that Pony was released earlier than Illustrious.
Also, Pony tends to be more challenging to control compared to Illustrious.
For some reason, Invoke cannot find it when I start generating a picture :c
it automatically give shadow to most character combined with better background, very cool
Good
WAI-Mature-illustrious Update
WAI大佬Tensor目前还没有更新最新的V14版本，希望更新一下
Have you considered doing a RealMix for illustrious?
Very good
Update: On v14 a number of tags are overcooking images after 2-3 hires steps.
v14 seems to have substantially worse quality than v12 or v13, which were both excellent.
v14 is washing out heavily with a kind of watercolors with large brush strokes, sort of artifacting.
Fix this I can't use it
我现在用的版本12，有必要下载14吗
yes，it IS best
Good
good
This model works nicely for what I’ve used so far!
chill
great job
it is no longer usable as a checkpoint in civitai.
i will look askance at why would WAI delegitimize people to use his checkpoint here.
either way, i will lay fallow and don't cackhandedly parlay a guess in the ulterior intentions do they have.
nonetheless, this checkpoint is unexceptionally magniferous, it prompts out most outstandingly when it is contradistinguished from other checkpoints.
No one bid for the online use of the model, which led to the website disabling the online feature. I didn’t take any action, and there’s no other reason behind it.
@WAI0731 jeez, i apologize if i ever came across rude or anything. i wasn't cognizant of the policies of this site.
@Skadi_Callipygian_Relishit's ok , it's completely normal that many people are not familiar with the latest rules.
In that case, use the illustrious models, mostly of them are free
Because you can't use it anymore
Fix this!! I can't use it!!
A shame this cant be used anymore. Might as well just delete this checkpoint from the site
Anyone know why it can't be used anymore??
It works now!
Doesn't work anymore why?
Apparently you have to bid for the online use of the model. Seems no one did so it got disabled…..again. It’s sad and annoying the site does this
Fix this again!
I seriously hate this dumb bidding system civitai implemented, Hope it gets fixed again
Auditions suck
One of the best checkpoints, hoping it will be back to civitai
Not work again
Why this suddenly dissapeared, I was training on this one since some Loras I like are not available on illustrious please fix it 🥲🥲
Fix this!! I can't use! Why others use and not other cannot use !
Amazing!!! My only problem is that when I use Hi-Res Fix the results are exaggeratedly sharp and it looks bad.
Someone needs to do it grab the shovels boys
Fix this again
WE NEED THIS BACK AND UPDATED, PLEASE RETURN
Nice Checkpoint
Only WAI Illustrius never fails but WAI Pony I don't know what is happening it doesn't let use then it let use back and then doesn't use again
Now online use requires an auction. I forgot to bid last week, so I can’t use it.
How long will it last? I saw previous versions cant be used free.
THANK YOU FOR LISTENING TO YOUR FANS
A good checkpoint that works well with different models
Again fix this!
I agree fix this!
Or better make V15
Will you update this too and bring it back please?
Broken again
Oh no! Please bring it back! I really love this!
how are people using this model when its off the public for bid???
Because you can just download it and make images yourself
It's still available for download and local use
Just... why?
why I can not use this in civita anymore
Again
Hello! Thanks for the hard work!
Would it be possible for you to bring the Version 14 to SinkIn.ai?
Details
Files
waiANIPONYXL_v140.safetensors
Mirrors
waiANINSFWPONYXL_v140.safetensors
waiANINSFWPONYXL_v140.safetensors
waiANINSFWPONYXL_v140.safetensors
waiANINSFWPONYXL_v140.safetensors
waiANINSFWPONYXL_v140.safetensors
waiANINSFWPONYXL_v140.safetensors
waiANIPONYXL_v140.safetensors
waiANINSFWPONYXL_v140.safetensors
waiANINSFWPONYXL_v140.safetensors
waiANINSFWPONYXL_v140.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.