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("Jonjew/ZavysCarnival")
prompt = "zavy-crnvl, a solo carnival dancer in mid-twirl, showcasing the movement of their vibrant costume. The focus is on the flowing fabric and the expression of joy on the dancer's face"
image = pipe(prompt).images[0]Zavy's Carnaval - Flux
- Prompt
- zavy-crnvl, a solo carnival dancer in mid-twirl, showcasing the movement of their vibrant costume. The focus is on the flowing fabric and the expression of joy on the dancer's face
- Negative Prompt
- Guidance: 3 Steps: 33
- Prompt
- zavy-crnvl
- Prompt
- zavy-crnvl
- Prompt
- zavy-crnvl
Model description
FROM https://civitai.com/models/738083/zavys-carnaval-flux
Trigger zavy-crnvl Strength 1
Introduction This LoRA captures the vibrant energy and colorful essence of Carnaval, bringing to life the lively atmosphere of parades, costumes, and street celebrations. It emphasizes rich, saturated colors, dynamic motion, and intricate costume details, perfect for creating scenes filled with joy, music, and festive chaos. The LoRA excels in rendering both close-up portraits of costumed dancers and wide shots of bustling streets.
Triggers zavy-crnvl Recommended settings Strength between 0.7 and 1.3.
Trigger words
You should use zavy-crnvl 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
- 9
Model tree for Jonjew/ZavysCarnival
Base model
black-forest-labs/FLUX.1-dev