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("animte/pixar-sdxl-lora")
prompt = "breathtaking 3D image in the pixar style, pixar-style, cartoon"
image = pipe(prompt).images[0]pixar-sdxl-lora
- Prompt
- breathtaking 3D image in the pixar style, pixar-style, cartoon
- Negative Prompt
- noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo
Model description
This LoRA is adapted from the "Pixar Style SDXL" model originally published on Civitai (https://civitai.com/models/188525/pixar-style-sdxl).
It is designed for image-to-image style transfer, transforming portrait photos into Pixar-inspired cartoon characters.
The code implementation and additional resources can be found in the following GitHub repository: https://github.com/nerlfield/pixar-sd-portraits/tree/main
Trigger words
You should use pixar style 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
- 191
Model tree for animte/pixar-sdxl-lora
Base model
stabilityai/stable-diffusion-xl-base-1.0