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 (51)
Error: Failed to find model version 1177000 for model 404154 pls
my first impression of V12 is very good. kudos to you
Just top model
I have been here since the beginning and V12 does not disappoint. The best anime model gets yet another perfect update.
Thank you! I love you from the bottom of my heart. I could buy you a beer if you come to Thailand.
I think the newest version makes heads look too immature. I feel like they looked better in v11.
Another sad day to be site user
V11 was good, I was used to it, sadly that couldn't be used on site anymore... BUT! V12 pushes more to anime like style, faces are better just as backgrounds, yet, hands get worse. Hope even better stuff on V13 😊
(Mixing all versions maybe? Who knows)
Difficulty in drawing with eyes
The faces look more childish now. I know its not intentional but can you please give to option to switch between models so that we can gen mature models. Thanks!
The only way as merging models into one and give the chose to select what you want, but it's too much work, so owner probably wouldn't do it
@CathyPowers it lips on this model are horrendous. Anime lips work fine. But as soon as i try to give them actual lips. It bugs off. I use 10/7 cgf. And 35-38 steps. No vae. No loras that can cause that.
@FatAssedBitch yes, I know, v11 was much better, this version have better eyes but lacks everything else... Well, I'm a site user only but the creators doesn't seems to care about site users at all... All we can't do is expected next version to be better
@CathyPowers yes. A lot of models have the switch available. So i think its not ultra hard. But i have no idea myself. Its sad there isn't anyway to get multiple models easily. I am pretty sure there is a feature for this. But i can be wrong. I wish the author would release seprate models if its so hard to make it.
@FatAssedBitch each user could put 2 models at time, the other option would be add the switch in the same model, I don't know how hard is making such a thing but... Well, all depends on model owner
Tried a bunch of things with v12 and v11 makes better in all the situations, taking it out of site is very sad
What exactly is wrong with the new version? For me personally, version 12 is more detailed.
@Sargox hands and lips, plus it tend to be more young looking in all aspects
Yes
Thank you!
v11 por que lo quitaste f.................
Does this model support controlnet 15 or 21?
hard to use for 2 characters in 1 generation. always the wrong hair color, the wrong eye color. waste of generation points
can you do a karin uzumaki lora too please? <3
i like~
Does anyone get a lot of images with kanji or numbers that look like the years 2013 / 2018?
Hi friend, I don't know if you're aware but V12 doesn't do age as well as V11. For example in V11 my generations are exactly what I want regarding age but in V12 all the generations look way younger than they should be.
Just wanted to let you know if you would like me to DM you regarding examples let me know!
Hope you are well
You can set "loli" in the negative prompt
I really appreciate how this model doesn't struggle even with something like tf and furries.
Help noob, please. Why the images are so desaturated? Is it requires to install anything else?
Amazing!
This checkpoint is absolutely phenomenal at creating anthro/furry characters. with good prompting, it even does multiple characters, without prompt bleed-through between them. Highly recommend!
Does this checkpoint require an additional VAE?
no
V11 still the best, using it on tensorAI, since civitai just doesn't care about letting people uploaded their models
V12 version feels worse, but some things is better, for example:
-- adding fantasy in prompt, or something related makes everything have explosive bloom by default,
-- hands placements is very inconsistant to prompt compared to V11
-- architecture concepts are way worse than V11
-- concept 3d product drawings sometimes have human features by default
-- adding girl instaid of woman makes character too young looking compared to V11
++ hair glow is regulated
++ hair colors and colors in general is more consistant to prompt compared to V11
++ mature guy is now not extremely muscular ebony hairy mafia boss by default
hi! for no reason known, I can't extract an image that the mais character is a bit far away... its a close up or something close to it... is there anything I can do?
So far, excellent experience using it. Great model!
Hey can I use V8.0 of this please?
As stated multiple times, you're probably speaking of generation on the website. It's not the author's decision. It's Civit AI itself that imposes only the latest model.
Half a year using this totally amazing model and still thinking V3 is the best one, is by far the most responsive and obedient and never get an empty or distorted result. V4, 5, 6 are awful (sorry), V7, 8 are ok, V9 is pretty good, V10 is weird as fuck because have this strange realistic/volumetric looking, V11 is meh, and V12 is amazing if you want something that resembles animation with very flat colors.
So in my opinion V3 and 9 are the best by far, and you can add 12 to that list if you like/want that flat cartoon style in colors.
Best model I've used.
Dear friends, please share some pony models that are good at generating realistic Asian women. I've been looking for a long time and haven't found any. Thank you
Thank you very much @Wang_Yuran
A bit late to answer but try: https://civitai.com/models/658304?modelVersionId=1018371
The best realistic pony checkpoint I've tested yet, and it specializes in asian.
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.