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)
v9 - 100 buzz
Me with 85 buzz
Well guys 14 days is not that long right?
Please read the content and get free buzz daily, getting 100 a day isn't difficult. Civitai | My Buzz Dashboard
@WAI0731 Thanks, after they change generation buzz into blue I was thinking I can't get normal buzz anymore
@DrPunk It's okay, the changes to blue buzz indeed weren't that good.
@WAI0731 I hope you're having fun generating art with your model solo (I laughed at the gallery just now) since you've locked regular people out of it...
I hope you routinely get your models stuck far down the list and people forget about them before they unlock >_>
This pay to use bullshit is for the birds.
Thank you very much for your concern, my model is indeed garbage, and you don't need to download it.
@WAI0731 Rather than jump to a point I didn't make (model being garbage or not), address the practice of locking content behind paywalls for 2 weeks at a time >_>
@MadeThisToPost counterargument: you don't pay for model training and can use model for free after 14 days. I really don't understand how its bad deal? You can use model for free and he can get something after he spend time to train model.
Look at my comment. He even send link how to get buzz easy. Thanks to him I get 100 and can download model :)
@DrPunk Don't participate in the early access system unless you want more "en-shit-ifi-cation" from CivitAI to ensue.
- "You can use model for free" -> Of course I can! What, do you think WAI0731 paid the original artists the model is based on?! Wtf?
None of this should costs anyone any money at all. Nor should it waste your time farming buzz on this site. Please try to understand that this is supposed to be a hosting site and that WAI0731 isn't even profiting from this system. It's just retarding access to regular users.
@MadeThisToPost I skip 99% of "pay to skip" loras but I don't mind checkpoint. Even free stuff need money to work. You just want all stuff for free but when someone want fair trade and you need to give them something (time) you start acting like a child "THIS SHOULD BE FREE".
If he start paying artists to use arts (Its not main topic here) you would pay for using it. No 14 days wait anymore just pay to use. Every single transaction has input and output. If you want huge website to host free stuff -> they need to get money to host it. As far I know you can also get some money when people use your model.
If I can wait (or literally comment/post some random image and get 100 buzz for free) 14 days and download model for free and use it for free or paid X$ for imagine/use....14 days is fair deal.
@DrPunk Dude, you must not know much about the internet...
How do you think HuggingFace works? Or GitHub for that matter. "Huge websites" typically support their activity by correlating their traffic to "advertisement value" (or by having an actual business being run on the site). This buzz shit is all just a CivitAI cash grab as they become ever more greedy middlemen.
This 14 days isn't an endpoint. It's the beginning of a process of artificially inconveniencing users with the intent of making them shell out money to access things.
What you don't seem to understand, is that "THIS SHOULD BE FREE".
a troll, how wonderful! I thought they died out long time ago...
@jtk1996606 Right, because no one would ever argue against measures designed to make stuff they like shittier. That just doesn't happen.
Enough internet for you today XD Like dude, it's not gonna be stuck behind a paywall forever. Just wait 14 days or less if enough people donated buzz back. @WAI0731 works to improve the model. Just think of it going under maintenance or something since you obviously cant wait >.>
@Ventus1893 I'll say this again... as plainly as possible:
The 14 day wait is just the beginning of more annoying measures designed to incentivize people to pay for access. This behavior will lead to more inconveniences designed to draw money from users.
No one should condone or accept this.
Are you people just so dumb you can't acknowledge something till it's already the case?
I really admire your work, just donate 200 buzz to you
V9 has improved on the areas that bothered me in V8.
Thank you for responding so quickly!
This is the top model for creating stunning anime girl illustrations. For those looking to achieve the best results, a small Buzz donation is a worthwhile investment.
:( y no v8 any more i loved it. now i cant gen with it, and v9 doesn't come out for 14 days :( :( :(
If you just need to use online generation, paying 50 BUZZ will give you unlimited access.
I donated 50 to your broke ass, go get v9 :D
I've donated 50 to get generation access, but I liked the results of a previous v8 much-much more.. Can I use it? Or is it only for downloading now?
@JohnnyB1 shocked Pikachu face!
@WAI0731 shocked Pikachu face! I thought it was 50 / generation shocked Pikachu face!
V9 can also make 1360x1360 good?
Also 1660x1060 will be fine?
I ask because I saw that the previous version works at 1360x1360.
1360x1360 is ok, my sample image was generated directly at 1024x1360.
but 1660x1060 is hard to say,
theoretically anything within 1536x1536 should be fine.
@WAI0731 OK. Thanks for the reply, I will try to do something with higher resolutions.
And do you recommend any specific models for ADetailer, such as face? Or still use face_yolov8n.pt?
really really good checkpoint, but need small improve in shadowing ad lightning technique
took me for a surprise when i come on and the other versions weren't up for generation, but i have to say the quality is beyond awesomesauce and plays rather nice with at least the one lora i've been using lol looking forward to seeing what i can do with it.
Thank you for update of Hyper model)
Can I still use v8?
I've donated 50 to get generation access, but I liked the results of a previous v8 much more.. Can I use it? Or is it only for downloading now?
UPD: By "use it" I mean in the CivitAI's generator.
You can only download to use v8,CivitAI site's rules state that a person can only have two models available for online use
@WAI0731 ..OK But, hold on! When I press add resources button there are models with more than 2 options there! https://photos.app.goo.gl/iRpuqK9WGLa5ZC3Y8
How can I define age more accurately? Can I just use age prompt words?
Regarding skin problems, every naked flat-chested person's skin can clearly see the marks of ribs or wrinkles. Is there any clue word that can solve this problem?
add "ribs" to the negative prompts.
@WAI0731 This seems to only make the ribs lighter, but it won't disappear.
@xiaoyan2522957665194 When I tried placing it in the first position of the negative prompts, in most cases, it became difficult to see the appearance of ribs.
Very easy to use. I have no trouble getting good results. Works well with other LORAs. Does a good job of creating the background.
I've been using this model for over a month. I started with v7. I like how the model conveys colors, easy to adjust, easily grasps LORE, and renders backgrounds superbly. I deleted all the other models and now only use this one. I'm very satisfied.
Dropped the 100,000 Buzz needed to unlock this for everyone. Simply one of the best models out there. Have fun, everyone!
appreciate you
You are a legend. Thank you!
thank you 🙏 💕
What a G <3
GOAT!
Based
goat move
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.