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("kviai/3d-icons")
prompt = "an icon of instagram"
image = pipe(prompt).images[0]3D Icons SDXL
- Prompt
- an icon of instagram
- Prompt
- an icon of an astronaut riding a horse
- Prompt
- a <s0><s1> icon of an astronaut riding a horse, in the style of <s0><s1>
Model description
Model based on stabilityai/stable-diffusion-xl-base-1.0
Trigger words
To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
to trigger concept TOK-> use <s0><s1> in your prompt
Download model
Weights for this model are available in Safetensors format.
- Downloads last month
- 15
Model tree for kviai/3d-icons
Base model
stabilityai/stable-diffusion-xl-base-1.0