A good prompt will allow you to create magnificent generated images.
You can find prompt examples here.
đź’ˇ Advice for your prompt : You don't need to add keyword like quality (except if you want a specifity) like "masterpiece, 4K, details,... " or in the negative "ugly, dismorphed, ..." the system have already already has a pre-improvement.
Each word carries importance and power, which is why we advise you to test their impact gradually.
In this documentation, we will explain each parameter to help you focus on achieving your desired results.
Parameters
Positive Prompt
Here, you should specify what you wish to see appear, which can include:
- By artist, details, style of art, elements
- A short sentence of character and pose or action
- Animal type
- Anthro/Feral
- Character Specifics
- Solo/Duo/Trio
- Male/Female/Andromorph
- Description of Clothes
Negative Prompt
Elements you do not wish to appear if the generation includes them in previous results (you don't need to add ugly tags : bad interactions, bad legs, missing head, etc.). Here, you can specify the opposite gender you do not want for your character.
Image Size
The size of the image might seem trivial but is necessary for creating quality images according to your character and their pose or action. Of course, the higher the resolution, the better the rendering, but the aspect ratio is just as important, if not more. For instance, choosing a landscape format for an anthro character might result in them not fitting entirely within the frame or leaving large margins. We mainly recommend a landscape size for feral characters and a portrait size for others unless your character is bending or rising, in which case you should test by changing the format.
Emphasizing/De-Emphasizing
⚠️ This parameter should be used with care to avoid distorted details: increase it cautiously.
If you wish to emphasize or de-emphasize a term in your prompt, you can do so on a scale between 0.1 and 2 for this term (e.g., keyword:1.5). Words have a default value of 1.
For example : "Green eyes:1.5" is higher weight than "Green eyes" wrote like this.
If you want decrease the weight of a word (lower than default) you can adjust like this "feet:0.8" (1>0.8) until ":0.1" .
By default, a word will always have a value of 1 (or :1), but this doesn't mean that this is its real power, as not all words have the same power (which is why some need to be increased with this argument to match).
BREAK Control
đź’ˇ BREAK helps you separate different parts of your prompt to prevent them from interfering with each other and gives you better control over the final image.
The BREAK keyword acts like a divider in your prompt. Use it to clearly separate different elements (characters, background, style) so each part gets proper attention during generation.
Prompt : [Character n°1 / Artist /…] BREAK [Background / Scene / Filters/…]
Example:
"anthro wolf, male, muscular, detailed fur, by artist
BREAK
forest background, detailed lighting, photorealistic"
For Multiple Characters:
When working with multiple characters, repeat the main subjects in each section to maintain consistency:
Prompt : [Base of prompt (artist/ style/…)], [character n°1/ Action/…] BREAK [Base of prompt (artist/ style/…)], [character n°2/ Action/…]
Example:
“by artist, duo, forest background, sunset, male wolf, short hair, brown hair, muscular, passionate embrace
BREAK
by artist, duo, forest background, sunset, female fox, blond hair, long hair, lying, sleeping”
This technique ensures both characters remain present throughout the generation while allowing focused control over specific details in each section.
Guideline Keywords
Here are popular keywords you can use in the generation to help you achieve various styles or poses (you can add multiple if it makes sense).
Note: We recommend using E926 tags for optimal image generation (without “_” ). Source of tags here
Artists (non-exhaustive list) :
- by Angellsview3
- by Bebebebebe
- by Braeburned
- by Chunie
- by Dimwitdog
- by Doxy
- by F-r95
- by Fluff-Kevlar
- by Funkybun
- by Hioshiru
- by Jay Naylor
- by Jasonafex
- by Jishinu
- by Kabier
- by Kalahari
- by Kluclew
- by Kuroodod
- by Meesh
- by Mercurial64
- by Raaz
- by Reallynxgirl
- by Redrusker
- by Roanoak
- by Ruaidri
- by Sabuky
- by Seibear
- by Skweekers
- by Smileeeeeee
- by Tsampikos
- by Zackary91
- by Zaush
- by Zica
- …
Scene type / characteristics :
- Solo / Duo / Trio / Group
- [Color] Fur / [Color] Hair
- Male / Female / Andromorph
- Anthro / Feral
- Fat / obese / muscular / feminine
Animal / Others :
Also specify the family of animal with the name example : dog = … dog, canine, canid, …
- Mammals : Lion, Elephant, Tiger, Bear, Wolf, Monkey, Giraffe, Kangaroo, Dolphin, Whale, Horse, Dog, Cat, Pony,
- Birds : Eagle, Parrot, Penguin, Owl, Sparrow, Flamingo, Peacock, Swan, Hummingbird
- Reptile : Crocodile, Snake, Turtle, Lizard, Chameleon, Gecko
- Amphibians : Frog, Salamander, Newt, Toad
- Fish : Shark, Salmon, Clownfish, Tuna, Goldfish, Manta Ray
- Insects : Butterfly, Bee, Ant, Mosquito, Dragonfly, Ladybug
- Mythical creatures : Unicorn, Dragon, phoenix, gryphon
- Pokemon : Pikachu, Charizard, Bulbasaur, Squirtle, Eevee, Jigglypuff, Snorlax, Gengar, Mewtwo, Lucario
- …
Action Pose :
- Sit
- Lying
- Bent over
- Squatting
- Standing
- Running
- Walking
- Flying
- Sleeping
- …
Style / Capture :
- Front view
- Back view
- Hinquarters view
- Side view
- Bottom view
- Top view
- pov view
- Worm's-eye view
- Dutch angle
- close-up
- full body
- …
If you need more help or support for your prompt you can join our community server on discord here.