diff --git a/.gitattributes b/.gitattributes index 22a1b15fb92547b0f6ce0e23d4b5e733688ec307..5ab76d544a59cdef19275301c82630c739f80ce2 100644 --- a/.gitattributes +++ b/.gitattributes @@ -87,3 +87,14 @@ extensions/stable-diffusion-webui-composable-lora/readme/fig12.png filter=lfs di extensions/stable-diffusion-webui-composable-lora/readme/fig13.png filter=lfs diff=lfs merge=lfs -text extensions/stable-diffusion-webui-composable-lora/readme/fig8.png filter=lfs diff=lfs merge=lfs -text extensions/stable-diffusion-webui-composable-lora/readme/fig9.png filter=lfs diff=lfs merge=lfs -text +Lora/2Dfy[[:space:]](Masterpiece[[:space:]]Edition)[[:space:]]v0.1.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/HerrscherAGGA2023_Smelling_Penis_CONCEPT_V1.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/StS-Breast-Enlarger-Slider-PonyXL-v0.8.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/StS-SDXL-Foreshortening-v2-LyCORIS.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/StS_PonyXL_Detail_Slider_v1.4_iteration_3.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/StS_age_slider_v1_initial_release.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/VillainousFaceHoldXLv2.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/XLA-NP15.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/XLP_NP12.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/crossed_eyes_pony.preview.png filter=lfs diff=lfs merge=lfs -text +Lora/hypnotized_face_pony.preview.png filter=lfs diff=lfs merge=lfs -text diff --git a/Lora/2Dfy (Masterpiece Edition) v0.1.html b/Lora/2Dfy (Masterpiece Edition) v0.1.html new file mode 100644 index 0000000000000000000000000000000000000000..cd16bd8268770b4921b5f59110fb05964cfc8182 --- /dev/null +++ b/Lora/2Dfy (Masterpiece Edition) v0.1.html @@ -0,0 +1,89 @@ + +
+ + + + +
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Very recommended for wallpaper/landscape resolution. Trained with my anime gallery.
Safer weight: 0,4 or 0,5 weight. You can also use 0,2 if you want less changes and up to 0,9 for more changes. My favorite are 0,7 and 0,8 weight.
Stylize your 2.25/2.5D models to 2D and also help 2D models with this XL quality. Do not try with 2.75D or 3D models.
Trained in Animagine XL v3. Please share your images so I can try to upgrade this LoRA.
Things I noticed while testing it: It greatly helps the posture and the general style feels better. It helps with eyes, but sometimes it will need the help of face fix. Hands are also good but since it relies on the model itself it won't always will create very good ones.
+ Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Catty from Undertale
Tags such as 'cat' or 'furry female' may help
+ Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
I'm switching to XL Checkpoints
+ Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
HF: https://huggingface.co/OedoSoldier/detail-tweaker-lora
This is a LoRA for enhancing/diminishing detail while keeping the overall style/character; it works well with all kinds of base models (incl anime & realistic models)/style LoRA/character LoRA, etc.
Apply your own weight; this LoRA can be utilized for any weight up/down to 2/-2!
Note: use a negative weight to reduce details!
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
!! This is the correctly trained version of expressiveH !!
In the last one there was an issue with my files
So here we are now, it looks much better !
Thanks to the people who helped me <3
+ Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
English
This is the outfit Lora from the character "Han Soo-young" in the webtoon "Omniscient Reader's Viewpoint".
The appropriate strength for Lora is between 0.8 and 1.0.
The quality of the design or color of the outfit may not be good
As it is based on PD for Anime 1.0v, this model works best on this basis.
This text was translated using GPT 4o.
한국어
웹툰 "전지적 독자 시점"에 나오는 캐릭터 "한수영" Lora입니다.
Lora의 강도는 0.8~1이 적당 합니다.
의상의 디자인이나 컬러의 퀄리티가 좋지 않을 수 있습니다.
PD for Anime 1.0v을 베이스로 만들었기에 해당 모델에서 구현이 가장 잘 됩니다.
해당 글은 GPT 4o를 사용해 번역하였습니다.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Here I leave a small introduction of the LoRA:
This time I returned with a new concept, Smelling penis, yeah, the art of smelling cocks!
Well the thing is simple, this is trained with Pony so I included furry to train it, I separated all the concepts into two groups and two subgroups:
Girls | Sniff, suck and lick. (The one that includes more data, obviously ~)
Yaoi | Smell, lick. (It is trained with about 20 images)
Furry Girls | Sniff, lick and you know the rest~. (Here it is around 200 to 250)
Yaoi Furry | Smell, lick. (And this one only has 70 images)
What I mean is that it has quite a bit of plasticity, so just use it as you like. ( ̄▽ ̄)ノ
This SD version includes the same dataset that the Pony version uses, but I recommend using furry models for furry art, although it works quite well with models like hassaku, but hey, it's your decision, just play to your liking ~ XD

Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Since the new Hyper-12steps-CFG-LoRA was not yet available on Civitai, I am hereby making it available.
This is not my Lora model!
The rights belong to ByteDance.
Steps: 12
CFG: 5 - 8
Project Page: https://hyper-sd.github.io/
Original Repo: https://huggingface.co/ByteDance/Hyper-SD
Original Paper: https://arxiv.org/abs/2404.13686
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This LORA have been trained for Pony XL and its derivative anime-like models.
Dataset was 160+ images
2500 Steps
Activation tag "Jaune Arc", use with "blond hair, blue eyes, armour"
Works fine with both sfw and nsfw, but not very stable
Strength between 0.7 till 1.5.
Feel free to let me know what can be enchanced.
I'm trying to make all the other RWBY characters XL Loras.

Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
I dunno, R63!Jaune was cute.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Trained on art by Jlullaby, got some help with this one ;getting rid of as much text as possible, specially watermark logo.
Tags: jlullabystyle
Some signature moves: Tentacles, all the way through, cum in mouth, double penetration, triple penetration, reckless sex
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
SDXL LoRA/LoCon for Pony V6/Pony merges, trained on JLullaby's style.
Works well at 1 weight.
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
pendulumCreates the Pendulum, should be used with either of the two following triggers
besides headPuts it not directly infront of the face. My prefered style which I also used in most pictures. Sometimes gets confused with the other one.
infront of head, (Optional: "looking at viewer" -- can be left away I think)puts it infront of the head and makes the person directly stand before you. Usually creates two pendels on either side of the head. Only kinda works.
looking at pendulumMakes the Person look directly at the pendulum. ofc only works correctly with "besides head".
@_@ (Optional: glowing eyes)Creates the circles in the eyes. You can add any eye color to change the color. Obviously needs a upscaler to look good
?Creates a few questions marks around the person. They look pretty good. Highres-fix can fix any broken ones.
pendulum, hypnosisIt likes to create two pendulums, so you need to play around a bit with weight and CFG. But it still works way better than all the other loras for this concept ;)
the hypnosis tag can easily be left away. I just think it makes it a little bit better
@_@Creates the circles in the eyes. Obviously needs a upscaler to look good
--Hand holding Pendulum
-- swinging Pendulum (makes it only swing when trigger used. Doesn't currently work although it is implemented)
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
A Lora to pov of holding money and instant loss.
Trained on 67 images
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Another update, and this one didn't take nearly a year! Sensational! This new version is trained on Pony Diffusion v6, using pretty much the same dataset as V2. PDXL already knows what Penny looks like, but not her clothes. That probably makes about half the dataset redundant, but whatever, it works.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This LoRa is from the character "Pyrrha Nikos" from "RWBY".
Now you can use the LoRa in:

➜ PyrrhaNikosXL, green eyes, red hair, long hair, ponytail, hair between eyes, forehead protector, medium breasts, bare shoulder, gold gorget, cleavage, brown corset, gold armlet, black elbow gloves, single vambrace, black belt, black shorts, red skirt, leg armor, black boots
]--|======[ 💗 My Settings: 💗 ]======|--[
Sampler: Euler A
Steps: 27
CFG: 6
Clip Skip: 2
Width: 768
Height: 1152
Positive Prompt:
score_9, score_8_up, score_7_up, score_6_up, BREAK, Negative Prompt:
line art, watermark, logo, unaestheticXL_Sky3.1, (worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrow, (cropped), extra limb, missing limbs, deformed hands, long neck, long body, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, error, (deformed|distorted|disfigured:1.21), poorly drawn, bad anatomy, wrong anatomy, mutation, mutated, (mutated hands AND fingers:1.21), bad hands, bad fingers, loss of a limb, extra limb, missing limb, floating limbs, amputation, deformed, black and white, disfigured, low contrast, bad-hands-5, blurry, card \(medium\),6 fingers ugly_face monochrome]--|======[ 💗 ]===========[ 💗 ]======|--[
I also have patreon and ko-fi if you want to support me with a donation or if you want to invite me to a coffee <3
+
+Thanks for supporting me :3Add a 👍 or ☆ to receive new LoRA
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
👇👀 Read me! 👇👀This is a unipolar slider for PonyXL. The purpose of this slider is to increase the subject's breast size in a controllable fashion with the LoRA input values. Higher LoRA input values result in larger breasts.
What makes this slider special is that it is largely decoupled from age. Making a breast size slider is not hard, making a breast size slider that doesn't overly influence age is hard. This slider does the best that modern tools allow for decoupling age from breast size, and in my opinion it does a good job at that.
Supported input values are 1 - 5, however going above 3 often yield excessively large breasts. Negative values are not supported for this slider, use at your own peril. Please be aware that whatever breast size you prompt (if any) will be the base that the slider works off of. For example, if you prompt huge breasts and then use a LoRA weight of 3, you're going to get absolutely massive honkers. For the same prompt, if you prompt flat chest instead and use a LoRA weight of 3, the breasts will be much smaller than if you used huge breasts. The LoRA slider works like an offset in this regard.
No Activation prompt. Example prompt:
score 9, score 8 up, score 7 up, (source anime), 1girl, (maid), cleavage, solo, sitting, legs together, thighhighs, cowboy shot, head tilt, (hand on breasts), areola slip, evil smile, open mouth, looking at viewer, blue eyes, blonde hair, long hair, (bedroom, on bed), detailed background, <lora:StS-Breast-Enlarger-Slider-PonyXL-v0.8:2.5>
If you have issues using this LoRA, feel free to send me a message on CivitAI and I will help you out if I can. If you are running into use cases where this LoRA breaks down and/or freaks out, please let me know so I can fix it for future version releases.
Changelog:
June 30, 2024 - Initial v1.0 Release
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This is the SDXL version of my Hypnosis Pendululm / Coin on String LoRA built for PonyDiffusion v6 XL. In my opinion, it works much better than SD 1.5 with my previous LoRA even though this being my very first SDXL LoRA. Despite what the example image metadata says, I used AutismMix Confetti to generate all these images and SeraphMix v4.1 to upscale them.
This LoRA does not have an activation tag, but I suggest using (pendulum, hypnosis) to have the LoRA work best. Use only pendulum or coin_on_string in your prompt, not both. Using both will likely yield oddities. I like using pendulum more than coin_on_string because coin_on_string seems more likely to add phantom string and get jumbled up with lines in the background. If you plan to use @_@ or spiral_eyes make sure you also specify an eye color, otherwise it will come out weird. Not sure if that's a PonyDiffusion v6 thing or a thing with this LoRA.
A weight of 1.0 seems to work just fine. You can probably go +/- 0.3 without much issue, but from my testing it's unnecessary.
Example prompt: score_9, score_8_up, score_7_up, source_anime, BREAK, ((pendulum), hypnosis), 1girl, from above, cowboy shot, sitting, open mouth, blue hair, pink eyes, spiral eyes, (sleepy), ((unaware, dazed), arms at sides), cheerleader uniform, facial, cum on body, (gym storeroom), highres, absurdres, masterpiece, best quality, ultra-detailed, illustration, colorful, best quality, ray tracing, (extremely detailed), soft lighting, tracing, soft shadows, detailed face, textured skin, <lora:StS-Pendulum-Hypnosis-Coin-SDXL:1>
Changelog:
Fed. 24, 2024 - Initial release
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This LoRA is for PonyDiffusion v6 XL - for best results use PonyDiffusion v6 XL or merges based off of PonyDiffusion v6 XL like AutismMix.(no seriously, read the description below)
[Updated for v2.0]:
This LoRA (technically LyCORIS) is for adding foreshortening to your images. There are two v2.0 versions - one LyCORIS and one LoKR. I recommend you use the LyCORIS, as the LoKR was made to have a super small and compressed version. As a result, the LoKR version is not as flexible.
Activation tag for v2.0 LoRas is sts-foreshortening-v2 . Recommended weight 0.6 to 1.0 . Because of the sheer percentage of foreshortening pictures on the internet being foot/feet related, this LyCORIS does foot_focus, feet, and soles rather well. This LyCORIS also does arms_outstreched and reaching_towards_viewer well. This LyCORIS pairs well with my detail slider LoRA for PonyXL.
For examples prompts, refer to the included example images. All the metadata is correct in the them except that they were generated with AutismMix Confetti and not SeraphMix4.
Changelog:
Feb. 27 2024 - Initial Release w/ UNET only version
April 18 2024 - Released v2.0 LyCORIS and LoKR versions
~~~
OLD DESCRIPTION FOR V1.0:
This LoRA (technically LyCORIS) is for adding foreshortening to your images. The main thing to know is the difference between the UNET Only version and the standard version. The UNET version stays closer to what would be generated without this LyCORIS, so things like pose, background, and general detail from the original checkpoint can be preserved better. The standard version is trained on both UNET and TE, so it is more transformative. Neither one is inherently better from my testing.
Activation tag for 1.0 LoRAs is foreshortening. Because of the sheer percentage of foreshortening pictures on the internet being foot/feet related, this LyCORIS does foot_focus, feet, and soles rather well. I did remove the foot_focus tag from the training tags to try and make sure this didn't end up being a glorified foot_focus LyCORIS. This LyCORIS also does arms_outstreched and reaching_towards_viewer well.

Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
👇👀 Read me! 👇👀This is a unipolar slider for PonyXL designed to be a versitile way of introducing bokeh and depth of field into generated images. It does not requires the bokeh and depth of field prompts to work. This slider being unipolar means that it's designed to only support positive input values as opposed to a bipolar slider which supports both positive and negative input values. The slider is not tested or guaranteed to work with negative input values.
Higher input values result in more depth of field and bokeh effect. I recommend only going up to a value of 4. It's generally better if you do not add the bokeh and depth of field tags to your prompt along side this LoRA.
Please be aware that a lot of "detail" LoRAs conflict with this LoRA due to detail LoRAs generally trying to minimize all blurriness. This is not something I can work around.
No activation tag. Example prompt:
score 9, score 8 up, score 7 up, source anime, 1girl, solo, (cowboy shot), wolf girl, angry, yellow eyes, slit pupils, black hair, long hair, facial mark, wolf ears, (torn clothes), torn black tunic, tail, jumping, claw pose, open mouth, fangs, sharp fingernails, red fingernails, looking at viewer, night, outdoors, starry sky, full moon, grass, forest, (forced perspective, foreshortening), absurdres, 8k, <lora:StS_DoF_Bokeh_Slider_v0.9:3>
Check out some of my other popular PonyXL Sliders:
(None at the moment - feel free to leave a comment if you find issues!)
Changelog:
June 29, 2024 - Initial v0.9 Release
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
👇👀 Read me! 👇👀This is a slider for SDXL PonyXL. Trained on AutismMix Confetti. The purpose of this slider is to enhance the overall detail in an image, and the goal is to have it be robust and versatile enough so that you can put it in pretty much all your prompts. At the moment, it leaves the subject of an image unchanged, but enhances the background details considerably.
No activation tag. This is a unipolar slider LoRA. Recommended weighting is anywhere from 2 to 4. For version 1.4, if you combine it with a style LoRA you can go up to 5 or maybe even 6. I like the style LoRAs here, and there are many to choose from. This LoRA is also useful for Img2Img / Tiled upscaling.
Version 1.4 is geared towards upping detail in background and scenery versus adding detail to the image subject. In fact, it should do very little to the subject to the image in order to allow for great prompt adherence.
Example prompt:
score 9, score 8 up, score 7 up, source anime, 1girl, solo, wolf girl, black hair, long hair, facial mark, wolf ears, black bodysuit, long sleeves, cleavage cutout, gold trim, navel, black pants, black gloves, fur trim, tail, jumping, claw pose, attacking, open mouth, fangs, serious, looking at viewer, from below, night, outdoors, starry sky, forest forced perspective, <lora:StS_PonyXL_Detail_Slider_v1.4_iteration_3:4>
No special negative prompting needed, although the scenery tag is great to add for any scene that is outside. A nice side effect is that largely replaces the need to put anything like "masterpiece" or "high quality" in the positive prompt.
If you generate images with this, please share! I love seeing what people make with my LoRAs and it helps keep me motivated to make more. If you have PonyXL LoRA requests, feel free to leave a comment and I'll look into into it 👍
High positive values may introduce a slight realism style to the images or over sharpen image
̶P̶o̶s̶i̶t̶i̶v̶e̶ ̶v̶a̶l̶u̶e̶s̶ ̶m̶a̶y̶ ̶a̶l̶s̶o̶ ̶s̶c̶a̶l̶e̶ ̶t̶h̶e̶ ̶a̶g̶e̶ ̶o̶f̶ ̶t̶h̶e̶ ̶s̶u̶b̶j̶e̶c̶t̶ ̶a̶ ̶b̶i̶t̶ Fixed in v1.3
̶V̶e̶r̶s̶i̶o̶n̶ ̶1̶.̶2̶ ̶m̶a̶y̶ ̶n̶o̶t̶ ̶a̶d̶d̶ ̶e̶n̶o̶u̶g̶h̶ ̶d̶e̶t̶a̶i̶l̶ ̶t̶o̶ ̶t̶h̶e̶ ̶i̶m̶a̶g̶e̶ Fixed in v1.3
Very high weight values (4<) may introduce multiple subjects in an image when there is only supposed to be one.
̶T̶h̶e̶ ̶L̶o̶R̶A̶ ̶m̶a̶y̶ ̶r̶a̶i̶s̶e̶ ̶t̶h̶e̶ ̶c̶o̶n̶t̶r̶a̶s̶t̶ ̶o̶f̶ ̶t̶h̶e̶ ̶i̶m̶a̶g̶e̶ ̶u̶n̶n̶e̶c̶e̶s̶s̶a̶r̶i̶l̶y̶ ̶ Fixed in v1.4
Changelog:
April 15, 2024 - Initial release
June 26, 2024 - Version 1.2 Release & Added "Known Issues" section
June 28, 2024 - Updated "Known Issues" with item #2
August 7, 2024 - Updated "Known Issues" with item #3
August 8, 2024 - Version 1.3 Beta release, updated Known Issues
August 9, 2024 - Removed v 1.3 Early Access disclaimer from description. A copy of it can be found here: https://pastebin.com/Qwacm6Af
August 9, 2024 - Updated CivitAI Version name to remove Early Access now that version is publicly available
August 10, 2024 - Released v1.4, updated Known Issues and model description
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
👇👀 Read me! 👇👀This is a slider for SDXL PonyXL. Trained on AutismMix Confetti. The purpose of this slider is to allow control of the age of depicted person(s) in generated images.
Negative LoRA values result in younger age. Positive LoRA values result in older age. v1.0 supports both men and woman and can support values between -5 and 5, although I generally recommend sticking between -4 and 4. Anything farther than -5 and 5 is untested.
NOTICE: On April 22, 2024 CivitAI moderator @chipshajen informed me that they are disabling the use of this LoRA with CivitAI's generator service due to "historical abuse with age-slider". There is nothing I can do about this other than recommend you run SD locally or on some other service.
No activation tag required. Goes well with my PonyXL detail slider. Example prompt: score_9, score_8_up, score_7_up, source_anime, (pov), (pov looking up), ((Saber), Fate, Fate Grand Order, Artoria Pendragon, armor, (looking down), (leaning forward)), concerned, arms behind back, hands behind back, head tilt, looking at viewer, detailed eyes, [[eyeshadow]], (mountain) background, <lora:age_slider_v4:2>, absurdres, [[backlighting]]
If you generate images with this, please share! I love seeing what people make with my LoRAs and it helps keep me motivated to make more. If you have PonyXL LoRA requsts, feel free to leave a comment and I'll look into into it 👍
Known Issues:
- May not scale age properly when multiple people are present in image
Changelog:
April 15, 2024 - Initial v1.0 release
April 22, 2024 - Updated cover image to remove small artifacts. Disclosed CivitAI barring this LoRA from being used with CivitAI's generator service.
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
activation tag: toriel
good tags included in the model: classic outfit, half naked, nude,
good tagging format: score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, <lora>, toriel is action/description, background type, extra tags
CGF of 5-7 yield good results
Steps: 25+
ratio: minimum 1024x1024 for best results
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
What is this LoRA for?
This LoRA is for when you are generating an image where your subject's face is upside down, as when you use aDetailer on an upside down face, you get unusable faces as a result.
It is usable both on 2d and 3d, but 2d seems to be better with upside-down faces overall so may not need this LoRA. I have tested it anyways.
If you appreciate my content, please don't forget to follow me and leave a like and review, I read everything.
It motivates me to create more! :)
How To Use and What Inpaint Denoising Strength to Pick:
Instructions for free HERE
Trigger Word: UPSIDEDOWN
If you have any questions find me here on Discord and I will do what I can to help: https://discord.gg/MmA7FFrR8H
If you would like to support me or get access to some unreleased character LoRA's you can go HERE, I will release them all here when I get 500 followers :)
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Trained on Pony Diffusion V6 XL with 61 pictures.
Best result with weight between : 0.8-1.
Main Prompts : chin grab
Pov prompts : pov
Disembodied prompts : disembodied limb, disembodied arm
Other prompts : hand on another's chin
Commissioned by Ocelot1300 on fiverr
Reviews are really appreciated, i love to see the community use my work, that's why I share it.
If you like my work, you can tip me here.
Got a specific request ? I'm open for commission on my kofi or fiverr gig *! If you provide enough data, OCs are accepted
If you want to get updates on my projects as they go, you can follow me on X
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Trained: Animagine XL 3.1
Generate: Animagine XL 3.1, holodayo, kivitos,
required: nipples_yolov8s.pt
https://civitai.com/models/490259
"<lora:XLA-NP15:0.8> nipples" in the ADetailer prompt field
<lora:XLA-NP15:0.8> nipplesStrength: 0.6-0.8
Detection: 0.6-0.8
必須:nipples_yolov8s.pt
https://civitai.com/models/490259
ADetailerのプロンプト欄に「<lora:XLA-NP15:0.8> nipples,」
・貧乳なら0.4-0.6
・巨乳なら0.6-0.8
Detectionは0.6-0.8くらいで(要調整)
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
for Pony Diffusion V6 XL
required: nipples_yolov8s.pt
https://civitai.com/models/490259
"<lora:XLP_NP12:0.4> nipples" in the ADetailer prompt field
<lora:XLP_NP12:0.4> nipplesStrength: 0.4-0.6
Detection: 0.6-0.7 (coordination required)
必須:nipples_yolov8s.pt
https://civitai.com/models/490259
ADetailerのプロンプト欄に「<lora:XLP_NP12:0.4> nipples,」
・貧乳なら0.3か0.4
・巨乳なら0.4-0.6(0.8までいくと左右の乳首の大きさが不揃いになりやすい)
Detectionは0.6-0.7くらいで(要調整)
+ Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
I've been using the (great) Detail Tweaker by CyberAIchemist for a while now, and I was really curious. I really just wanted to know if I was capable of doing something similar.
I had a lot of fun doing this, and I think it came out pretty great. I wil ldefinitely incorporate it in most of my work going forward.
You should use this between 0.5 and 1 weight, depending on your preference. You can go lower than 0.5 for a more subtle effect, of course.
I also found out that this gives some interesting results at negative weight, sometimes. See the examples to see what I mean.
How to use LoRA's in auto1111:
Update webui (use git pull like here or redownload it)
Copy the file to stable-diffusion-webui/models/lora
Select your LoRA like in this video
Make sure to change the weight (by default it's :1 which is usually too high)
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
LoRA to make the composition of pony diffusion more animated without changing the composition too much.
#trigger
anime (Not required)
#sampler
DPM++ 2M SDE Heun Karras
DPM 2 a Karras
+ Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Collection of All Character in One Models 全角色模型合集
v2.0版本使用5w张图片,在非常充足的算力--4*4090下训练了超过150个GPU小时。
v2版本支持的角色大为提高,包含240个有效的角色文件夹,经评估,支持150~200位明日方舟的有效角色。
v2版本在v1.5版本基础经过多次加练(这也是为什么文件名叫v4)
该模型的训练耗时半个月,花费了大量的人力和物力,将支持角色从80位拓展到150~200位。
如果有机会,该模型依然会不断更新,
特别鸣谢/ 算力兼技术支持:昊天
非常感谢 昊天 同学对本项目的大力支持!
角色数据集使用 waifuc工具搜集。
数据集的标签排序使用 waifuset工具完成。
角色后期的步数平衡在的昊天帮助下完成。
CCIP(角色的还原度)的测试结果:CCIP Test Results
提示词文档:明日方舟全角色使用指南 Guide for All Characters in Arknights | Civitai
Version 2.0 used 50,000 images and was trained for over 150 GPU hours on a powerful hardware setup - 4*4090.
Version 2.0 greatly expanded the supported characters, with 240 valid character folders. Based on evaluation, it supports 150 to 200 valid Arknights characters.
Version 2.0 underwent multiple iterations on top of version 1.5 (which is why the file name is v4).
The training of this model took half a month and required a significant amount of manpower and resources to expand the character support from 80 to 150 to 200.
If given the opportunity, this model will continue to be updated.
Special thanks to Hao Tian for their support in terms of computing power and technical assistance.
A big thank you to fellow student, Hao Tian, for their strong support in this project!
The character dataset was collected using the waifuc tool.
The sorting of labels in the dataset was done using the waifuset tool.
The balancing of post-processing steps for character animations was done with the help of Hao Tian.
CCIP (Character Completion Index Percentage) test results can be found here: CCIP Test Results
Guide for All Characters in Arknights: 明日方舟全角色使用指南 Guide for All Characters in Arknights | Civitai
v1.5版本使用20K图片,在v1.0的版本基础上,使用双卡A100 80G 训练了35个GPU小时。
1.5版本共优化了两位角色,新增了167位角色。(85+167)
新增的167位角色有50%~70%的还原度,但不能完全还原,可能是因为训练策略的问题。
更多角色,请期待2.0版本!
其中,有70位角色具有100张图像,每张图被训练了20*2次
有87位角色具有50张图像,每张图被训练了40*2次
羽毛笔和蓝毒的默认服装在v2.0版本中得到优化。
提示词文档:明日方舟全角色使用指南 Guide for All Characters in Arknights | Civitai
该模型永久免费下载。
获得作者许可后可以转载模型,但不得:
冒充作者、付费下载、使用模型盈利,以及一些违反法律法规或做出不当的行为。
Version 2.0 utilized 20,000 images and was trained on dual A100 80GB GPUs for a total of 35 GPU hours, building upon the foundation of version 1.0.
Version 2.0 included optimization for two existing characters and introduced 167 new characters, resulting in a total of 85 + 167 = 252 characters.
The newly added 167 characters achieved a restoration level of 50% to 70%, but it is not a complete restoration. This may be due to the training strategy employed.
More characters to come! Stay tuned for version 2.0!
Among them, 70 characters had 100 images each, with each image being trained 20 * 2 times.
87 characters had 50 images each, with each image being trained 40 * 2 times.
The default costumes of Feather and Blue Poison from Arknights received optimization in version 2.0
The model is available for permanent free download.
With the author's permission, the model can be reproduced, but certain actions are prohibited:
Impersonating the author
Charging for downloads
Using the model for profit-making purposes
Engaging in activities that violate laws and regulations or inappropriate behavior
v1.0版本使用超过3w张图片,在A100 40G 上训练了超过80个GPU小时。
v1.0版本共支持85位角色,后续会持续新增角色,直到达到预期值--238位角色。
v1.0版本的85位角色,是经过我的数据库统计,单人图片多于400的85位角色。
部分角色在默认皮肤上表现欠佳,以我目前的能力,无法将默认皮肤单独筛选出来。
全角色项目长期缺人手,如果您有兴趣,请联系我。
“让每个知名系列的角色都有他的lora,让每一份热爱都可以实现”,
这个是全角色项目的最开始的出发点。
The v1.0 version was trained using over 30,000 images and consumed over 80 GPU hours on an A100 40G.
The v1.0 version supports a total of 85 characters, and more characters will be continuously added until the target of 238 characters is reached.
The selection of the 85 characters in the v1.0 version was based on my database statistics, focusing on characters with over 400 individual images.
Some characters may not perform well with their default skins, and currently, I am unable to filter out the default skins separately based on my current capabilities.
The project for all characters is in need of long-term assistance. If you are interested, please contact me.
The initial goal of the all characters project is to "give every well-known series its own Lora and make every passion come true."
Since I am working on this project in my spare time, I cannot create individual example images for each character. Therefore, I rely on feedback and optimization suggestions from users for the model's improvement.
Please note that this model's content includes some covers that have been rated as PG-13/R/X
Please choose the appropriate age rating based on your needs.
Training model: Pony
Recommend model: Pony Diffusion V6 XL/T-ponynai3/AutismMix SDXL
Training resolution: 1024*1024
Recommended output resolution: 832*1216
特别鸣谢/算力 : Nyan9的显卡租借/我的钱包
Special Thanks/Computational Power: GPU Rental/My Wallet
Discord : https://discord.com/invite/CFpyHceF52
Recommended dataset collection and processing tools: https://github.com/deepghs/waifuc
Possibly the most user-friendly dataset processing UI currently in use:https://github.com/Eugeoter/waifuset

Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Experiment with the scores to get the desired details with the promt:
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,
READ: works with specific models with dpo technology, do not try them with other xl models because it will not work:
Best models:
Pony Diffusion XL V6
Pony Diffusion for Anime
AutismMix SDXL

Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Gives base Pony Diffusion V6 model more defined characters and backgrounds and can improve character/style LoRA accuracy. Comparisons at end of gallery.
Recommended positive prompt: score_9, score_8_up, score_7_up, source_anime
For western style replace source_anime with source_cartoon
If using a character or style LoRA and its style is not preserved remove source_anime
I recommend leaving negative prompt blank. You may put source_anime, source_cartoon, or 3d in the negative to tune the style but try without a negative first.
To use artist tags shown in the examples use art by followed by the artist name.
This is an extract of version 2 of Anime Confetti Comrade Mix. Generally I recommend using the base model instead of this LoRA. However using this LoRA with the base Pony Diffusion model gives you the flexibility to tune how strong you want its effect to be.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
The following images were used for training.
https://www.pixiv.net/artworks/121822133
Enjoy crossed eyes face!
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
適用するとフラットな絵になります。
マイナスで適用すると絵の描きこみが増えます、まぁこっちで使う人が大半ですね。
「flat1」と比べると、マイナス適用時の絵が明るいです。
構図への影響を抑えたい場合は、拡張機能の「LoRA Block Weight」を使用して調整してください。
ーーThe following is Google translationー
Applying it will result in a flat picture.
If you apply it with a minus value, the amount of drawing will increase, well, most people use it here.
Compared to "flat1", the picture when minus is applied is bright.
If you want to suppress the influence on the composition, please adjust using the extended function "LoRA Block Weight".
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Trigger: GloryholeSDXL
Use Adetailer
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Enjoy the empty eyes and hypnotized face!
I trained this LoRA using the images I created with my LoRA.
https://civitai.com/models/577707/testmy-art-style-xenon3134mc-style
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
UPDATE : I built a quick ADetailer model for phones. It works well so far on images generate with this Lora and will probably pick up some other phones too. It's not perfect but it's usable.
If there's more interest I'll keep training the ADetailer.
Pick it up in the extra files section (it's the small Lora, I cant seem to rename it)
Drop it in /models/adetailer and restart auto1111
***********
Finally made something that has been missing for a long time. Proper phones in selfies!
I focused on building a very carefully curated dataset of one specific iPhone type.
The Lora does a pretty good job of adding it.
keywords are : "iphone mirror selfie" and helped along by "<subject> holding iphone"
Have fun! Please post your creations here :)
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
I have long been dissatisfied with the stability of the output fingers, so I created this lora
use score_9,source_anime,good_hands
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Support me on
Weight: 1.0
Trigger words:
Appearance:
<lora:ruby-rose-ponyxl-lora-nochekaiser:1>, ruby rose, short hair, black hair, red hair, grey eyes,
Outfit:
dress, pantyhose, cape, corset, belt,
+ Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
I will start re-making my LoRAs into Pony, so any buzz you can give is appreciated, also reviews with images are welcomed :)
Appearance: RubyRose, 1girl, solo, black hair, red hair, two tone hair, silver eyes
Volume 1 Huntress Outfit: Vol1Huntress, pantyhose, boots, cape, dress, cross-laced footwear, black pantyhose
Pajamas: Vol1Pajamas, pajamas, tank top, sleepwear
Beacon Academy Uniform: SchoolUniform, cape, skirt, jacket, plaid skirt, black pantyhose
Dance Dress: DanceDress, pantyhose, dress, red dress, bow, bare shoulders, formal
Slayer Outfit: SlayerOutfit, scarf, long sleeves, cape, skirt, corset, black pantyhose
Volume 4 Huntress Outfit:
Vol4Huntress, thighhighs, torn clothes, cape, torn thighhighs, boots, zettai ryouiki
Volume 7 Huntress Outfit: Vol7Huntress, fingerless gloves, red skirt, choker, red cape, pantyhose, belt, corset, bandolier
Ice Queendom Lucid Dream Outfit: LucidDreamOutfit, goggles, pantyhose, jacket, red headwear, hood, white undershirt
Also, I started a ko-fi, I appreciate any support you can give if you like what I do :)
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This is a requested character.
Weight: 1.0
Trigger: coco adel
Default Outfit: black headwear, beret, sunglasses, ribbed sweater, long sleeves, corset, black gloves, black pants, black scarf, bandolier
Add multicolored hair, brown hair and brown eyes if necessary.
The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Weight: 1.0
Trigger: mistralrose
Default Outfit: red cape, black dress, corset, white shirt, long sleeves, black skirt, black thighhighs, bandolier
Add gradient hair, black hair, red hair and grey eyes if necessary.
The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Weight: 1.0
Vale: weissvale, scar across eye, ponytail, hair ornament, tiara, white jacket, cropped jacket, high collar, long sleeves, short dress, white dress, earrings, necklace
Mistral: weissmistral, scar across eye, side ponytail, hair ornament, tiara, shrug \(clothing\), short dress, blue dress, long sleeves, earrings, cleavage
Atlas: weissatlas, scar across eye, braided ponytail, tiara, shrug \(clothing\), blue jacket, white dress, cleavage cutout, black gloves, elbow gloves, earrings, belt, pouch
Negative Weiss Schnee: weissqueen, ponytail, peaked cap, military uniform, white cape, white coat, long sleeves, grey pantyhose
I recommend negatively prompting puffy sleeves when generating her Vale and Mistral outfits.
The results of your generations are dependent on the additional LoRAs, weights, and models you use, so it may not work or come out as consistent as my sample images.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
UPDATE:
1-added LoRA of SD XL DPO, NOT TURBO(usual settings for SD XL with this LoRA)
2-added LoRA of SD 1.5 DPO(usual settings for SD 1.5 with this LoRA, Clip Skip 1 for Real, Clip Skip 2 for Anime)
Turbo version can be used ONLY with NOT-turbo checkpoints, while the not-turbo version can be used with both turbo and not-turbo checkpoints.
LoRA based on sdxl turbo DPO, you can use the TURBO DPO with any stable diffusion xl checkpoint, few seconds = 1 image(3 seconds with a nvidia rtx 3060 12 GB with 1024x768 resolution)
SDXL DPO Turbo Checkpoint: https://huggingface.co/thibaud/sdxl_dpo_turbo/tree/main
Turbo LoRA: https://civitai.com/models/215485?modelVersionId=242807
Turbo Checkpoint: https://huggingface.co/stabilityai/sdxl-turbo
Question: What is DPO SDXL?
Answer: DPO SDXL from hugginface, https://huggingface.co/mhdang/dpo-sdxl-text2image-v1/tree/main
DPO SD 1.5 from hugginface, https://huggingface.co/mhdang/dpo-sd1.5-text2image-v1/tree/main

For ComfyUI: use this LoRA with my workflow for sd xl turbo(change the lora_name): workflow --download here--
For webui 1111: write in the prompt: <lora:sd_xl_dpo_turbo_lora_v1-128dim:1>
1-Sampling method on webui 1111: LCM(install animatediff extension if you don't see it in sampling list)
2-CFG Scale: from 1 to 2,5
3-Sampling steps: from 4 to 8
---
If you want to support me, check out my Patreon: https://www.patreon.com/Shiroppo
Follow me on civitai(!!!): https://civitai.com/user/shiroppo
Follow Me on Twitter/X: https://x.com/ShiroppoTwit
Deviantart: https://www.deviantart.com/shiroppoart
Pixiv: https://www.pixiv.net/users/96490888
---
+ Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps. For more information, please refer to our research paper: SDXL-Lightning: Progressive Adversarial Diffusion Distillation. We open-source the model as part of the research.
Our models are distilled from stabilityai/stable-diffusion-xl-base-1.0. This repository contains checkpoints for 1-step, 2-step, 4-step, and 8-step distilled models. The generation quality of our 2-step, 4-step, and 8-step model is amazing. Our 1-step model is more experimental.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
This LoRA creates eyes with only spirals in them. AI isn't very good with spirals in general, so expect a lot of ringed eyes instead.
NOTICE: This model is not intended for txt2img. Enable this LoRA only when manually inpainting the face (with Inpaint Only Masked enabled) or using the Batch Face Swap extension (https://github.com/kex0/batch-face-swap).
UPDATE:
Added new version for PDXL.
Recommended to use with ADetailer and the eye detector model.
+ Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
By request. I hate how shallow deepthroat is in pony. This lora fixes that.
Use angle tags like "pov" or "side" view. Also:
I opened a Ko-fi page! If you feel the need to support me, you can do so there. Here is the link:
https://ko-fi.com/besollo
As always, all characters are above the age of 18 and consenting. Enjoy!
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
I've noticed there is a lack of Undertale LORAs for SDXL, so I've trained one on Animagine XL v3.x, but can work on some other models (I also trained PonyXL version)
I used around 800 images in total that I could find, with some additions later on. Suffice to say, it can influence style quite a bit (mostly 3.0 models)
Characters:
Asriel, Chara, Frisk, Muffet, Sans, Papyrus, Undyne, Gaster, Toriel, Mettaton, Grillby, Alphys, Flowey, Asgore, Napstablook
Some better, some worse. But I don't recommend trying to generate either Asgore or Napstablook in the version 1.0 - they are overfitted. In the version 1.1 and onwards they work well enough, but be careful about it (but it is usually obvious). There could be some stylistic inconsistency, so it is better to specify.
Parameters:
Trigger words are supposed to be like character_(undertale). Some chararacters can be accurate enough with trigger words alone, but for others it is better to add some more.
The models have been trained on clip skip 2 (except for Base XL ones), and they work at a strength of 1.0 (or even lower, if need to), but it depends on what model you intend to use.
The sampler that I use, unless specified, in the examples is dpmpp 3m sde gpu, with karass scheduler, from ComfyUI.
My latest images have nodes to copy, but it's my personal workflow with a lot of unnecessary elements, so if someone were to use it, they would have to remove them.
Animagine 3.1:
Starting with model 1.2, it surpasses the previous models in its flexibility and capabilities. But stylistically they are quite different, so it is a matter of taste. Personally I like 1.2.5 model for its style, but it has lots of biases since I overfitted it a bit in the beginning, which makes it hard to generate some things.
Base XL:
I've trained the second model, but this time on a base model, which is supposed to make it possible to use LoRA on any model, but not really (anime models seem to struggle a lot). So my examples are not only from Animagine v3 on this one. As of now, it isn't wholly accurate, but it really depends on the model. I trained this model as a substitute, if the other one doesn't work at all.
PonyXL:
This version was trained on civitai, while generally it can have good outputs - it missed some of the characters' features.
+
Use the model without crediting the creator
Sell images they generate
Run on services that generate images for money
Run on Civitai
Share merges using this model
Sell this model or merges using this model
Have different permissions when sharing merges
Willow Schnee from RWBY. Trained on Pony Diffusion V6 XL. Tested at 0.8-1.0 strength.
Trigger word is "rbWillow" and "white hair, blue eyes, mature female" is required.
Add "high collar, purple vest, white shirt, ascot, long sleeves, black skirt, black pantyhose" for her typical look.
A request. Check out my Discord if you want to chat about video games (or yell at me about requests.)
+