import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("timotheospaul/Rider_Waite_Tarot_Style")
prompt = "rider style, an alchemist in his lab talking to a biblically accurate angel hovering over his workbench, on the bench are splayed magical tools and mystic technologies"
image = pipe(prompt).images[0]Rider Waite Tarot Style
.png)
- Prompt
- rider style, an alchemist in his lab talking to a biblically accurate angel hovering over his workbench, on the bench are splayed magical tools and mystic technologies
.png)
- Prompt
- rider style, buildings of atlantis, time empire, alchemical kingdom
Model description
Generate Rider-Waite Tarot Style images Flux Dev LoRA Main Tigger Phrase is "rider style"
Other useful prompts that appear regularly in the captioning training data:
"halftone print texture"
"halftone printed texture"
"halftone texture"
"halftone printing technique"
"halftone printing effect"
"cross-hatched printing technique"
"cross-hatched texture"
"stippled print texture"
"stippled printing texture"
"stippled texture"
For the Suit objects, try:
"golden chalice(s)"
"golden pentacle coins"
"sprouting wand(s)"
"sprouting leaves"
"sword(s)"
Trigger words
You should use rider style to trigger the image generation.
You should use halftone printing technique to trigger the image generation.
You should use stippled texture to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for timotheospaul/Rider_Waite_Tarot_Style
Base model
black-forest-labs/FLUX.1-dev