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/clay_animation")
prompt = "<lora:Clay Animation:1>Clay Animation - Disappointment to triumph, a 3D image showing a student with a disappointed expression, an eraser erasing the low score, and rewriting it into a high score. The mood transitions from despair to triumph. The environment is a study desk with exam papers and stationery. The lighting draws attention to the erasing and rewriting of the score."
image = pipe(prompt).images[0]Clay Animation
- Prompt
- <lora:Clay Animation:1>Clay Animation - Disappointment to triumph, a 3D image showing a student with a disappointed expression, an eraser erasing the low score, and rewriting it into a high score. The mood transitions from despair to triumph. The environment is a study desk with exam papers and stationery. The lighting draws attention to the erasing and rewriting of the score.
Model description
rajkumaralma/clay_animation
Trigger words
You should use Clay Animation page 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
- 8
Model tree for rajkumaralma/clay_animation
Base model
stabilityai/stable-diffusion-xl-base-1.0