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
FAQ
Comments (20)
The various PunkAI bundles use lyco instead of lora. The prompts need to be updated for that.
Thanks for the heads up. Corrected with v1.4
@TxcTrtl Typo found in 1.4. "armosphere" instead of atmosphere.
@TxcTrtl Found a "battlefiled" instead of "battlefield"
Typos: Coud instead of Cloud, Balll instead of Ball, Lora:lora: instead of Lora:
"No tags found in wildcard file "lora:lyco:FiveDecorsAIx3:0.6" or file does not exist"
"skscrapers" instead of skyscrapers.
"effets" instead of "effects"
"otherwordly" instead of "otherworldly"
The "wild west" prompt block has coalpunk in it twice. Maybe replace with South of the Border Style? https://civitai.com/models/25749 In the same block, "raliway" instead of "railway."
"primsatic" instead of "prismatic".
I tossed this at ClaudAI to look for typos. Here are some potential issues:
"smiht" - should be "smith"
"sorcrer" - should be "sorcerer"
"sinister|evil} smirk" - extra }
"atlantis," - extra comma
"atmsohpere" - "atmosphere"
"compostion" - "composition"
"compsosure" - "composure"
"taoo" - "taoist"
"shintoist" - missing closing "
"atmoshpere" - "atmosphere"
"envlopled" - "enveloped"
"maelstorm" - "maelstrom"
"atmoshperic" - "atmospheric"
"astorids" - "asteroids"
"lightning {storm|} lora:LightingVFX:0.2," - extra comma
"descendants" - "descending"
"plantefall" - "planetfall"
"intesne" - "intense"
"atmoshpere" - "atmosphere"
Not saying those are issues, just that you may want to do a quick check.
Ei, thanks a lot for the adding! ^^
Hi I'm having problems installing the Cutoff prompt extension for SD. https://github.com/hnmr293/sd-webui-cutoff
Are there any instructions on how to download/install it into SD? I'm not familiar with Git or Python
You can install any extension for the SD webui, by heading to the "Extensions/Install From URL" tab. Paste the link (https://github.com/hnmr293/sd-webui-cutoff) into the "URL for extension's git repository" field, and press Install. You'll need to reload the UI afterwards, or for certain extensions you need to restart the WebUI entirely.
@TxcTrtl thank you so much for that. I watched a youtube video that went over that same thing. I wish there more explicit instructions, but now I know for the future. Much appreciated!
Hi, I'm loving the variability and "imagination" this brings to image creation.
I'm having issues where I'm trying to kick off a batch of 30-50 images. I can see in my terminal that sd-dynamic-prompts has a bunch of errors, which basically means all the images generated ignore any wildcards in the prompt. Has anybody experienced this? Has anybody found a fix? Or a reason to the errors?
What is the exact error that the terminal displays?
Are you trying to create multiple images by increasing batch size? If so, be aware that most wildcards contain LoRas, and you can't generate two images simultaneusly with different LoRas. The result will be that all LoRas will apply to all images in the batch. You can work around this by increasing number of batches instead of batch size (though generation will take longer like that).
@TxcTrtl this is the top of the messages:
=======================================================
Error running process: E:\Stable Diffusion\stable-diffusion-webui\extensions\sd-dynamic-prompts\scripts\dynamic_prompting.py
Traceback (most recent call last):
File "E:\Stable Diffusion\stable-diffusion-webui\modules\scripts.py", line 451, in process
script.process(p, *script_args)
File "E:\Stable Diffusion\stable-diffusion-webui\extensions\sd-dynamic-prompts\sd_dynamic_prompts\dynamic_prompting.py", line 478, in process
all_prompts, all_negative_prompts = generate_prompts(
File "E:\Stable Diffusion\stable-diffusion-webui\extensions\sd-dynamic-prompts\sd_dynamic_prompts\helpers.py", line 93, in generate_prompts
all_prompts = prompt_generator.generate(prompt, num_prompts, seeds=seeds) or [""]
=======================================================
It seems to be listing all the different .py files.
And its a bit variable, depending on what model I choose, I have a different upper limit before error. When using RevAnimated, I can sometimes queue off 20?
When using ManmaruMix, I can safely queue off 15 images.
I'm using batch count, and keeping batch size at 1. I didn't know 2 different LoRAs can't be generated at the same time, but I haven't changed batch size so that should be ok..
Have you tried running upwards of 30+ images in a go?
@banzo The issue seems to be with the sd-dynamic-prompts extension, or the prompt you're trying to feed to it. What exactly is the prompt that results in this error? You may also want to give reinstalling the extension a shot (maybe your client failed to update to the latest version, and an outdated version is causing the issue). If nothing else helps, check the issues of the extension, maybe someone already experienced something similar: https://github.com/adieyal/sd-dynamic-prompts/issues. If not, report a new one, the extension author seems to be quite responsive in the issue threads.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.