SOAP: Style-Omniscient Animatable Portraits
Paper • 2505.05022 • Published • 1
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Luffuly/head-mvimage-diffuser", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]SOAP: Style-Omniscient Animatable Portraits
This repository contains the model of the paper SOAP: Style-Omniscient Animatable Portraits.
- Downloads last month
- 4,594
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support