I DO NOT authorize PixAI & Yodayo (and other users) to transfer this model from Civitai.
PixAI users who wish to use this model can do it by using the uploaded one on my PixAI profile from the link below :
https://pixai.art/@vxp/artworks/models
this model generates high-definition Anime-style images.
Great for characters and ambients.
via prompt you can vary the graphic style:
using "ai-generated" prompt you will obtain high detail picture.
omitting it and using "anime style" you will obtain a more simple style.
thanks to TURBO technology it takes only a few steps.
Suggested settings: (see below)
Euler A with 5~8 steps
CFG 1.3 ~ 2.5 (1.3 ~ 1.5 for realistic style, 1.5 ~ 1.8 for semi realistic style, 1.8 ~ 2.5 for anime style)
Suggested prompts : "(masterpiece:1.2), (best quality:1.2), (very aesthetic:1.2), (absurdres:1.2), (detailed background),newest,ai-generated,"
add "intricate" to enhance fine details.
remove "ai-generated" to have more anime style picture.
Suggested negative prompts : "nsfw, lowres, (bad), text, error, fewer, extra, missing, (worst quality), (low quality),jpeg artifacts, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, abstract, bad anatomy, bad hands, bad feet, bad hand, bad hands, bad finger, bad fingers, extra finger, extra fingers, split finger, split fingers, extra digits,"
Description
what new in 2.2!
1) better anatomy
2) better fingers
3) ai-generated no more generate an aggressive contrast image
4) soft skin, more cute face
FAQ
Comments (5)
Can i reup your model on yodayo if i use the format like this(read the description)
For anyone interested in creating custom prompts for (VXP XL Model), I wanted to share some information on how I do it. Here's a command prompt that demonstrates just how easy it is to generate prompts, whether you're using ChatGPT or a local ChatGPT setup.
I'm currently using a local co-pilot with the Gemma2 model and Open WebUI. I’ve trained my own co-pilot and uploaded some knowledge files to guide it on what to generate. However, you can also use ChatGPT or any non-trained co-pilot to achieve similar results. Here’s how you can write a prompt command:
====Command Prompt Example=====
Generate (5 unique character tag sets), starting with (1girl, solo, TYPE-HERE,) -
followed by additional tags related to:
[eye_color] (e.g., PROMPTS HERE),
followed by additional tags related to:
[body_type] (e.g., PROMPTS HERE)
followed by additional tags related to:
[breast_size] (e.g., PROMPTS HERE),
followed by additional tags related to:
[skin_type] (e.g., PROMPTS HERE),
followed by additional tags related to:
[expressions] (e.g., PROMPTS HERE),
followed by additional tags related to:
[hair_length] (e.g., PROMPTS HERE hair),
followed by additional tags related to:
[hair_style] (e.g., PROMPTS HERE),
followed by additional tags related to:
[hair_color] (e.g., PROMPTS HERE),
followed by additional tags related to:
[TYPE_clothing], [TYPE_clothing_accessories], and [landscape_type] (e.g., PROMPTS HERE).
Rules:
- Ensure each tag set is unique with detailed clothing.
- Each tag set should be approximately 25 characters long.
============================
So creating a prompt is pretty simple: just type what you need, and it will take care of the rest. Below is my full list for a maid prompt. You can definitely create prompts for other themes too. I usually focus on getting the clothing and landscapes just right, but you can use the example template to craft your own or ask ChatGPT to help you out.
You can also add other details like poses or specific stuff too, but just make sure that ChatGPT or your local ChatGPT knows what you're asking for. I don't use ChatGPT for this since it censors some prompts, so I prefer using a local model instead.
As for generating the image I made, I used the (A111 - WebUI Forge version), since I'm not very familiar with ComfyUI. If you're using Forge WebUI also here’s how I’ve set up my maid prompt command:
============================
Generate (5 unique character tag sets), starting with (1girl, solo, maid,) -
followed by additional tags related to:
[eye_color] (e.g., aqua eyes, black eyes, blue eyes, brown eyes, green eyes, grey eyes, orange eyes, purple eyes, pink eyes, red eyes, white eyes, yellow eyes, amber eyes, heterochromia),
followed by additional tags related to:
[body_type] (e.g., slim, athletic, curvy, petite)
followed by additional tags related to:
[breast_size] (e.g., small breasts, big breasts, medium breasts, huge breasts),
followed by additional tags related to:
[skin_type] (e.g., dark-skinned female, pale skin),
followed by additional tags related to:
[expressions] (e.g., seductive, playful, angry, serious, shy, cute smile),
followed by additional tags related to:
[hair_length] (e.g., medium hair, long hair, very long hair, short hair, absurdly long hair),
followed by additional tags related to:
[hair_style] (e.g., medium hair, long hair, very long hair, absurdly long hair, bob cut, inverted bob, bowl cut, buzz cut, chonmage, crew cut, flattop, okappa, pixie cut, undercut, flipped hair, wolf cut, cornrows, dreadlocks, hime cut, bow-shaped hair, braid, braided bangs, front braid, side braid, french braid, crown braid, single braid, multiple braids, twin braids, low twin braids, tri braids, quad braids, flower-shaped hair, hair bun, braided bun, single hair bun, double bun, cone hair bun, doughnut hair bun, heart hair bun, triple bun, cone hair bun, hair rings, single hair ring, half updo, half up braid, half up half down braid, one side up, two side up, low-braided long hair, low-tied long hair, mizura, multi-tied hair, nihongami, ponytail, folded ponytail, front ponytail, high ponytail, short ponytail, side ponytail, split ponytail, star-shaped hair, topknot, twintails, low twintails, short twintails, uneven twintails, tri tails, quad tails, quin tails, twisted hair, curly hair, drill hair, twin drills, tri drills, hair flaps, messy hair, pointy hair, ringlets, spiked hair, straight hair, wavy hair, bangs, arched bangs, asymmetrical bangs, bangs pinned back, blunt bangs, crossed bangs, choppy bangs, diagonal bangs, dyed bangs, fanged bangs, hair over eyes, hair over one eye, long bangs, parted bangs, curtained hair, wispy bangs, short bangs, swept bangs, hair between eyes, hair intakes, single hair intake, sidelocks, asymmetrical sidelocks, drill sidelocks, low-tied sidelocks, sidelocks tied back, single sidelock, widow's peak, ahoge, heart ahoge, huge ahoge, antenna hair, heart antenna hair, comb over, hair pulled back, hair slicked back, oseledets, lone nape hair, alternate hairstyle, hair down, hair up, asymmetrical hair, sidecut, blunt ends),
followed by additional tags related to:
[hair_color] (e.g., aqua hair, black hair, blonde hair, blue hair, light blue hair, dark blue hair, brown hair, light brown hair, green hair, dark green hair, light green hair, grey hair, orange hair, pink hair, purple hair, light purple hair, red hair, white hair, multicolored hair, colored inner hair, colored tips, roots, gradient hair, print hair, rainbow hair, split-color hair, spotted hair, streaked hair, two-tone hair),
followed by additional tags related to:
[maid_clothing], [maid_clothing_accessories], and [landscape_type] (e.g., indoors, outdoors).
Rules:
- Ensure each tag set is unique with detailed clothing.
- Each tag set should be approximately 25 characters long.
============================
Character list for anyone needing:
https://huggingface.co/spaces/cagliostrolab/animagine-xl-3.1/blob/main/wildcard/characterfull.txt
1.96 > 2.2
is this the one that's same as the 1.9 low cost version on pixai? but that one uses DPM++ SDE Karras...
Oh nvm, I see that there is a matching model on Pi.
I was looking for the Illust low cost version instead. Seems it is not available to be DLed