import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("rajkumaralma/glitter_style")
prompt = "statue made of glowing crystal tiles,eagle made completely of tiles, scifi, masterpiece, 3d tiles, 3d shadows, neon red,gold, neon yellow background , (masterpiece:1.2), best quality, (hyperdetailed, highest detailed:1.2), high resolution textures, shards, glass, brocken glass, transparent glass, pieces of glass, <lora:ral-glitter:1> ral-glitter"
image = pipe(prompt).images[0]glitter_style
- Prompt
- statue made of glowing crystal tiles,eagle made completely of tiles, scifi, masterpiece, 3d tiles, 3d shadows, neon red,gold, neon yellow background , (masterpiece:1.2), best quality, (hyperdetailed, highest detailed:1.2), high resolution textures, shards, glass, brocken glass, transparent glass, pieces of glass, <lora:ral-glitter:1> ral-glitter
Trigger words
You should use ral-glitter 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
- 6
Model tree for rajkumaralma/glitter_style
Base model
stabilityai/stable-diffusion-xl-base-1.0