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("Keltezaa/Fire_Spirit")
prompt = "bailing_fire, A girl **** entirely of flames stands, her body engulfed in fire. Her form flickers and sways, semi-transparent and composed entirely of fire elements. The flames seem to rise naturally from her, as though she is both part of the fire and its source. The surroundings are blurred, keeping the focus entirely on her fiery presence. The flames ripple and pulse, wrapping around her form, creating an intense yet surreal atmosphere.freckles,masterpiece,best quality,light particle,depth of field,fantasy,blunt bangs,a cute girl,Porta 160 color,shot on ARRI ALEXA 65,bokeh,sharp focus on subject,highest details,photorealistic,high background details,high face details,8k"
image = pipe(prompt).images[0]Fire Spirit
- Prompt
- bailing_fire, A girl **** entirely of flames stands, her body engulfed in fire. Her form flickers and sways, semi-transparent and composed entirely of fire elements. The flames seem to rise naturally from her, as though she is both part of the fire and its source. The surroundings are blurred, keeping the focus entirely on her fiery presence. The flames ripple and pulse, wrapping around her form, creating an intense yet surreal atmosphere.freckles,masterpiece,best quality,light particle,depth of field,fantasy,blunt bangs,a cute girl,Porta 160 color,shot on ARRI ALEXA 65,bokeh,sharp focus on subject,highest details,photorealistic,high background details,high face details,8k
Trigger words
You should use bailing_fire 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
- 12
Model tree for Keltezaa/Fire_Spirit
Base model
black-forest-labs/FLUX.1-dev