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("Cole4444/Moji_Lora")
prompt = "moji_dog"
image = pipe(prompt).images[0]Emoji Lora
- Prompt
- moji_dog
Model description
Moji is a lora for sdxl 1.0 that generates emoji style images from a text description.
When using the model, add the trigger word "moji", and use '_' in place of spaces. The model is not perfect and more unrealistic of a description provided the less predictable the output.
Trigger words
You should use moji to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for Cole4444/Moji_Lora
Base model
stabilityai/stable-diffusion-xl-base-1.0