90 detailed dynamic prompts with fantasy, sci-fi, video game, mythological and historical themes. Each prompt includes setting, background, pose and (mostly) gender-agnostic character details. Now with booru tags!
For ComfyUI, please use https://github.com/adieyal/comfyui-dynamicprompts, and https://github.com/GrvBdgr/comfyui-negativewildcardsprocessor.
The wildcards contain negative wildcards (text surrounded by <! .. !>). If you do not wish to use these, simply remove the <! .. !> text in the wildcards files with your favorite text editor. Use the following regex:
<!.*!>As of v3.0 the wildcards no longer require Loras or embeddings, for compatibility with all models.
Older versions of the wildcards are not recommended for use.
Usage:
Add a description of the character you'd like in the generated image (feel free to use character LoRas), plus any style/quality keywords necessary for the model you're using, then add __ffpc-booru__.
Example:
best quality, masterpiece, 1man, russian (male:1.1), solo, aquamarine eyes, long brown beard, __ffpc-booru__
Some example characters are provided in the character.txt in the downloaded archive, so if you just want to run a few tests, you can use the following prompt:
best quality, masterpiece, __character__ __full-prompt-fantasy__
More diverse character wildcards can be found here: https://civarchive.com/models/118508?modelVersionId=128565
Negative prompt should be whatever the model necessitates, or your preferred negative prompt. Some models have race or gender bias due to the material that was used for training, you can usually use negative prompts to compensate. eg. if your generations come out with female characters despite describing the character as male, add "woman, girl" to the negative prompt, use weights if necessary.
Additional usage notes:
Other than the above, feel free to experiment with additions to the prompt, though most of the wildcards are rather long, so if you want to have a significant impact, weights may be necessary. The prompts rarely use weights above 1.1, so if your additions seem to have no effect, try weights of 1.15 or more.
Description
New LoRas are used in the prompts compared to v1.0, please read the description before use.
Refined existing prompts, added over 20 new prompts. Wildcards have been tested with more models and LoRas.
v1.1 notes
LoRas used:
LightningvfxCreateMore_v1 - https://civitai.com/models/10222/lightningvfx-create-more-consistent-lightning
FirevfxCreateMore_v2 - https://civitai.com/models/9049/firevfx-create-more-consistent-fire
WatervfxCreateMore_v1 - https://civitai.com/models/10750/watervfx-create-more-consistent-water-wip
gothichorrorai_v10 - https://civitai.com/models/39760/gothichorrorai
boneyardai_v10 - https://civitai.com/models/48356/boneyardai
oldegyptai_v10 - https://civitai.com/models/43229/oldegyptai
fairytaleai_v10 - https://civitai.com/models/42260/fairytaleai
bronzepunkai_v20 - https://civitai.com/models/29277/bronzepunkai
baroqueai_v10 - https://civitai.com/models/38414/baroqueai
artdecoai_v10 - https://civitai.com/models/37495/artdecoai
steampunkai10MBLora_10mb - https://civitai.com/models/20830/steampunkai-10mb-lora-extraction
dieselpunkai_9MB - https://civitai.com/models/22462/dieselpunkai
retrofuturismai_v10 - https://civitai.com/models/43465/retrofuturismai
solarpunkai_v20 - https://civitai.com/models/43944/solarpunkai
teslapunkai_v20 - https://civitai.com/models/24150/teslapunkai
piratepunkai_v10 - https://civitai.com/models/45892/piratepunkai
vikingpunkai_v10 - https://civitai.com/models/41364/vikingpunkai
tikiai_v10 - https://civitai.com/models/45012/tikiai
totempunkai_v20 - https://civitai.com/models/31988/totempunkai
stonepunkai_v10 - https://civitai.com/models/51539/stonepunkai
stainedglassai_v10 - https://civitai.com/models/46994/stainedglassai
crystallineai_v10 - https://civitai.com/models/48859/crystallineai
gemstoneai_v10 - https://civitai.com/models/49374/gemstoneai
azulejoai_v10 - https://civitai.com/models/46234/azulejoai
postapocalypseai_v10 - https://civitai.com/models/36848/postapocalypseai
GlowingRunesAI - https://civitai.com/models/51686/glowingrunesai
ConstructionyardAI - https://civitai.com/models/53493/constructionyardai
Textual Inversions (embeddings) used:
style-swirlmagic - https://civitai.com/models/25829/style-swirl-magic
style-rustmagic - https://civitai.com/models/10764/style-rust-magic
style-sylvamagic - https://civitai.com/models/7523/style-sylva-magic
space_style - https://civitai.com/models/7278/space-style-ti
atompunkstylesd15 - https://civitai.com/models/26250/atompunk-style
DarkFantasy - https://civitai.com/models/30287/dark-fantasy-style
FAQ
Comments (4)
I added your post link to my model description, Thanks for sharing. I love it
Sorry, noob here. When I add "__full-prompt-fantasy__" to my prompts it seems to override the specific prompts I made (e.g. "male tiefling bard"), even when i give them a weight of 1.2 or above, and I get a variety of everything. Am I doing something wrong?
It may be down to a variety of factors, but most likely it is a bias of the model you're using. Many models were merged or trained from biased sources (eg. they produce mostly female characters). The character part of the prompt will be less effective on these models, even with high weights.
Additionally, the "bard" part of the prompt is likely to conflict with the wildcards in __full-prompt-fantasy__, as the wildcards already include basic setting and features of the character (eg. "sorcerer" or "warrior"). This is not to say that it won't have an effect, just be aware that you may end up with weird images when including occupation/class in the character prompt (feel free to experiment though).
Also, tiefling is not a commonly known concept by most models, so it may be a tough ask for a generalist model to generate an image of a tiefling, let alone with additional details from the wildcards. You may need a textual inversion or LoRa for that to work, though I couldn't find any tiefling related ones after a quick search.
I suggest you experiment with other models, and find characters that the model can generate even without the wildcards. For instance, if you want a dwarf character (also not necessarily trivial for most models), see what you get from the model with something simple, like "1man, (dwarf:1.1) male". If it looks about right, you have a decent chance of getting dwarven characters when adding __full-prompt-fantasy__
Good luck!
@TxcTrtl Thank you very much for the explanation, that really helped :) I've experimented with some more general and detailled prompts and get more precise results now
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.














