import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("saveasART/GhostCostumeTriangularHeadpiece")
prompt = "UNICODE1girl,solo,large breasts, ghost costume, hitodama, triangular headpiece, ,<lora:japaneseGhostCostumeTriangularHeadpiece:1> , night, tombstone, graveyard,, sleeves past fingers, long sleeves, very long sleeves, claw pose, ghost, ghost tail, pale skin, (((see-through))) silhouette, off shoulder, cleavage, no bra,"
image = pipe(prompt).images[0]GhostCostumeTriangularHeadpiece
- Prompt
- UNICODE1girl,solo,large breasts, ghost costume, hitodama, triangular headpiece, ,<lora:japaneseGhostCostumeTriangularHeadpiece:1> , night, tombstone, graveyard,, sleeves past fingers, long sleeves, very long sleeves, claw pose, ghost, ghost tail, pale skin, (((see-through))) silhouette, off shoulder, cleavage, no bra,
Model description
Ghost Costume Triangular Headpiece
Trigger words
You should use Ghost to trigger the image generation.
You should use Costume to trigger the image generation.
You should use Triangular to trigger the image generation.
You should use Headpiece 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 saveasART/GhostCostumeTriangularHeadpiece
Base model
stabilityai/stable-diffusion-2-1